Error when create cmu_us_slt_arctic_mcep.tree
Dear all, When I executed this command : ./bin/do_clustergen cluster I had output with error at the end : SIOD ERROR: could not open file festival/trees/pau_2_mcep.tree BACKTRACE: 0: (load (string-append festival/trees/ (car unit) _mcep .tree) t) 1: (car (load (string-append festival/trees/ (car unit) _mcep .tree) t)) 2: (set! tree (car (...))) 3: (f (car l2)) 4: (cons (f (car l2)) r) 5: (set! r (cons (f (car l2)) r)) 6: (while l2 (set! r (cons (f (car l2)) r)) (set! l2 (cdr l2))) 7: (mapcar (lambda (unit) (...) ...) unittypes) 8: (if cg:multimodel (begin (format t Building multimodels: static ) (set! cg::cluster_feats -track_feats 1-25) ...) ...) 9: (build_clustergen etc/txt.done.data) closing a file left open: festival/trees/cmu_us_slt_arctic_mcep.rawparams closing a file left open: festival/trees/cmu_us_slt_arctic_mcep.tree And making cmu_us_slt_arctic_mcep.tree is failed. How I can do ? Thanks a lot. -- Khue Nguyen nguyennhuk...@yahoo.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
ASSALAMUALAIKUM
Salam, Saya Surina Binti Abdul Majid dan sekarang bekerja di London sebagai Pegawai Pemasaran (Marketing Officer) di sebuah syarikat pemprosesan batu permata di London.Untuk pengetahuan anda terdapat peluang perniagaan yang hendak saya perkenalkan dan keuntungannya akan diperolehi daripada kerjasama dan bantuan segera yang saya perlukan daripada anda. Saya menghubungi anda kerana saya tidak mahu lepaskan peluang yang ada di dalam syarikat kami buat masa ini dan juga pada masa hadapan. Saya perlukan anda sebagai pembekal (supplier/agent) kepada syarikat kami supaya kita boleh sama-sama merebut peluang perniagaan yang terbuka sekarang ini. Syarikat kami memerlukan produk bernama (TATALITE SUPPLE). Produk Tatalite Supple ini merupakan bahan cecair kimia saintifik yang baru dan merupakan pelincir yang digunakan di dalam makmal permata (gemological laboratory) untuk rawatan penulenan berlian (purification of diamonds clarity treatment). Pelincir yang digunakan semasa rawatan tersebut akan menembusi jauh ke dalam berlian dan semua kotoran hitam kecil di dalam berlian dan batu permata akan meruap keluar. Pembekal utama produk ini berada di Malaysia tetapi pembekal produk terus kepada syarikat kami telah mengalami kemalangan dan meninggal dunia di UK, beliau merupakan Pengurus Pemasaran (Marketing Manager) dan semenjak kemalangan tersebut, monopoli perniagaan telah terputus. Sesiapapun boleh membekalkan produk dan bergabung untuk membuat perkongsian dengan syarikat kami dan ini adalah sebabnya saya menulis email kepada anda untuk meminta bantuan, di mana saya memerlukan anda untuk bertindak sebagai ejen perantara yang akan mengisi kekosongan di antara pembekal utama dan pembeli iaitu syarikat kami. Ini adalah perniagaan yang besar dan akan memberikan dividen yang baik kepada kita berdua. Saya hanya memerlukan kerjasama anda untuk menjadikan perniagaan ini berjaya. Maklumat lanjut akan saya berikan sekiranya anda sanggup menjadi ejen yang membekalkan produk ini kepada syarikat kami. Pertama, saya akan mendapatkan satu perjanjian bekalan kontrak untuk anda sebagai pembekal kepada syarikat di mana saya bekerja. Berdasarkan peratusan, harga belian produk daripada syarikat adalah 4,000.00 USD per karton, manakala di Malaysia harga jualan produk adalah 2,100 USD. Jumlah yang diperlukan oleh syarikat adalah tidak kurang daripada 200 karton. Tujuan mengapa saya mahu anda untuk menjadi ejen kami adalah untuk menjadi pautan yang menghubungkan penjual tempatan di Malaysia secara langsung kepada syarikat yang membeli. Maka margin keuntungan akan dikongsi oleh kita berdua 60% untuk anda manakala 40% untuk saya. Bantuan utama yang diperlukan daripada anda adalah supaya anda memberitahu kepada pengurus saya bahawa anda boleh membekalkan produk ini kepada syarikat kami dan juga untuk mendalami butiran tentang harga dan cara bayaran. Kemudian, kami akan ambil langkah selanjutnya daripada situ. Hubungi saya setelah terima emel ini supaya saya boleh berikan nama dan butiran pembekal utama di Malaysia. Setelah menerima butiran pembekal utama ini, anda perlu menghubungi pembekal tersebut untuk bertanya samada, sekarang ada stok atau tidak untuk bekalan segera kepada kamu, sebelum saya maklumkan kepada Pengarah Syarikat (Company Director) kami tentang anda. Seterusnya Pengarah Syarikat akan hubungi anda dan membuat persediaan kepada Pengurus Pembelian (Purchasing Manager) terbang ke Malaysia. Purchasing Manager ini akan membeli produk daripada anda dan bayaran adalah secara tunai melalui bank di Malaysia. Harap boleh balas dengan segera. Sekian Surina ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Reminder about your invitation from Enya Keshet
Title: An email from Zoosk, The Romantic Social Network Hi, Enya Keshet sent you an invite on Zoosk. View Invite This message was sent by a Zoosk user who entered your email address. If you'd prefer not to receive emails when other people send you emails through Zoosk, click here You have received this message at the email address: festlang-talk@lists.berlios.de Copyright 2007-2012 Zoosk, 989 Market St, San Francisco, CA 94103 USA. Privacy Policy ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Kein Kredit von Ihrer Bank?
Hallo, will Ihre Bank Ihnen auch keinen Kredit mehr geben? Auch wenn Ihre Bank Ihren Antrag bereits abgelehnt hat, haben Sie bei unseren ausl#228;ndischen Finanziers noch die besten Chancen. Unsere Standardkredite sind f#252;r Privatpersonen bis 50.000 Euro und f#252;r Gewerbe bis 100.000 Euro. Keine Vorkosten - Keine SCHUFA erforderlich – Nachweis des Einkommens reicht aus. Stellen Sie hier Ihren Antrag gt;gt;gt; -- Keine Newsletter mehr von uns? Schreiben Sie bitte an: news...@gmail.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
SEO Package for 15 Keywords
Hello Sir/Madam, I am a Marketing Manager and would like to take few minutes of your valuable time for introducing our affordable SEO services. Our assured monthly task and responsibilities will definitely give a boom to your online business. Our packages for 15 keywords are mentioned below: 1. Keywords Analysis Research 2. 200 Manually Directory Submissions 3. 90 Article Submissions (1 Article Submission in 30 Top Directories) 4. 10 Press Release Distributions (1 Press Release submit in 10 Sites) 5. 4 Web2.0/Blog Postings 6. 30 Social Bookmarking Submissions 7. 10 Website Themed Links 8. 3 Unique Article Writing (400+ words) 9. 1 Press Release Writing (350+ words) 10. Keywords Mapping 11. Keywords Density Check 12. Content Optimization 13. Keywords Proximity and Frequency 14. Title Tag Change Suggestions 15. Meta tags Change Suggestions 16. Alt Tag Changes Suggestions 17. HTML Site Map Suggestions 18. XML Site Map Setup 19. Anchor Text Optimization 20. Interlinking Suggestions 21. Google Analytics Setup 22. Weekly Work Report 23. Monthly Ranking Report 24. Monthly Full Detailed SEO Work Report in Excel We send weekly report to each of our clients so that they can have regular updates on their website. We truly care you and so ensure to work regularly on the website elegantly. We use white hat SEO techniques for each website to give new boom to your online business. We are available for your services here so please do let us know in case you are interested. Thanks Regards, Marketing Manager ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
SEO with 15 Keywords Package
Hello Sir/Madam, I am a Marketing Manager and would like to take few minutes of your valuable time for introducing our affordable SEO services. Our assured monthly task and responsibilities will definitely give a boom to your online business. Our packages for 15 keywords are mentioned below: 1. Keywords Analysis Research 2. 200 Manually Directory Submissions 3. 90 Article Submissions (1 Article Submission in 30 Top Directories) 4. 10 Press Release Distributions (1 Press Release submit in 10 Sites) 5. 4 Web2.0/Blog Postings 6. 30 Social Bookmarking Submissions 7. 10 Website Themed Links 8. 3 Unique Article Writing (400+ words) 9. 1 Press Release Writing (350+ words) 10. Keywords Mapping 11. Keywords Density Check 12. Content Optimization 13. Keywords Proximity and Frequency 14. Title Tag Change Suggestions 15. Meta tags Change Suggestions 16. Alt Tag Changes Suggestions 17. HTML Site Map Suggestions 18. XML Site Map Setup 19. Anchor Text Optimization 20. Interlinking Suggestions 21. Google Analytics Setup 22. Weekly Work Report 23. Monthly Ranking Report 24. Monthly Full Detailed SEO Work Report in Excel We send weekly report to each of our clients so that they can have regular updates on their website. We truly care you and so ensure to work regularly on the website elegantly. We use white hat SEO techniques for each website to give new boom to your online business. We are available for your services here so please do let us know in case you are interested. Thanks Regards, Marketing Manager ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Improve clustergen voice quality with new language on Flite
Dear *All* I meet the problem about Vietnamese clustergen voice quality with Flite *In Flite:* After i convert clustergen voice from Festvox to Flite. Ater thatI run ./flite_cmu_us_slt -t moojt con nguwowfi chisnh truwjc . --- The voice is not clear. It seem that try to speak this sentence as US voice. But i am building for Vietnamese voice. I aslo used Vietnamese database as wav file for trainning *in Festival: * If we run (SayText moojt con nguwowfi chisnh truwjc.) . The voice will be better than Flite. I can hear clearly. And it speak as Vietnamese voice From this results, i see that there is big different between Flite and Festival for voice quality after convert from Festvox to Flite * Are there anyone know How to improve Vietnamese voice in Flite ? Do we need to change any inside code file? Festvial can be accept about voice quality but Flite is not ?* If you know reason why? please help me. Thanks so much *Jackson* ( from Vietnam) On Sat, Oct 27, 2012 at 5:00 PM, festlang-talk-requ...@lists.berlios.dewrote: Send Festlang-talk mailing list submissions to festlang-talk@lists.berlios.de To subscribe or unsubscribe via the World Wide Web, visit https://lists.berlios.de/mailman/listinfo/festlang-talk or, via email, send a message with subject or body 'help' to festlang-talk-requ...@lists.berlios.de You can reach the person managing the list at festlang-talk-ow...@lists.berlios.de When replying, please edit your Subject line so it is more specific than Re: Contents of Festlang-talk digest... Today's Topics: 1. [festival-talk] Job: Research Fellow in speech synthesis, CSTR, University of Edinburgh, UK (Simon King) -- Message: 1 Date: Fri, 26 Oct 2012 15:49:00 +0100 From: Simon King simon.k...@ed.ac.uk To: syn...@inpg.fr, hts-us...@sp.nitech.ac.jp, festival-t...@festvox.org Subject: [festival-talk] Job: Research Fellow in speech synthesis, CSTR, University of Edinburgh, UK Message-ID: 7ad9cf0d-7a48-4197-807a-7c36a20ef...@ed.ac.uk Content-Type: text/plain; charset=us-ascii message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = (Please distribute widely) Postdoctoral Research Fellow The Centre for Speech Technology Research A postdoctoral researcher position is available on the FP7 Marie Curie Initial Training Network Investigating Speech Perception in Realistic Environments (INSPIRE). This network comprises 10 European research institutes and 7 associated partners, and has the aim of training 13 PhD students and 3 postdoctoral researchers to investigate how people understand speech in challenging, real-world listening conditions (e.g., listening in noise, listening under the constraints of hearing impairment or non-native language use, etc). The position involves developing and extending our existing techniques for statistical parametric speech synthesis, creating tools for psychoacoustic research, and working with other researchers across the network. These tools will be aimed at investigating human speech perception processes. Applicants will have appropriate qualifications and meet the Marie Curie eligibility rules (see webpage for details). Strong programming skills are essential, as is some experience of HMM-based speech synthesis and/or HMM-based automatic speech recognition and some knowledge of phonetics and/or speech science and/or psychoacoustics. This post is fixed term for 1 year and salary will be in the range GBP 42,045 - GBP 46,731. The starting date will be 7th January 2013 or as soon as possible thereafter. Informal inquiries to Prof Simon King simon.k...@ed.ac.uk or Dr Catherine Mayo cathe...@inf.ed.ac.uk Apply online: http://www.cstr.ed.ac.uk/opportunities/ Closing date: 5th November 2012 -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = -- ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk End of Festlang-talk Digest, Vol 76, Issue 12 * ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Job: Research Fellow in speech synthesis, CSTR, University of Edinburgh, UK
message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = (Please distribute widely) Postdoctoral Research Fellow The Centre for Speech Technology Research A postdoctoral researcher position is available on the FP7 Marie Curie Initial Training Network Investigating Speech Perception in Realistic Environments (INSPIRE). This network comprises 10 European research institutes and 7 associated partners, and has the aim of training 13 PhD students and 3 postdoctoral researchers to investigate how people understand speech in challenging, real-world listening conditions (e.g., listening in noise, listening under the constraints of hearing impairment or non-native language use, etc). The position involves developing and extending our existing techniques for statistical parametric speech synthesis, creating tools for psychoacoustic research, and working with other researchers across the network. These tools will be aimed at investigating human speech perception processes. Applicants will have appropriate qualifications and meet the Marie Curie eligibility rules (see webpage for details). Strong programming skills are essential, as is some experience of HMM-based speech synthesis and/or HMM-based automatic speech recognition and some knowledge of phonetics and/or speech science and/or psychoacoustics. This post is fixed term for 1 year and salary will be in the range GBP 42,045 - GBP 46,731. The starting date will be 7th January 2013 or as soon as possible thereafter. Informal inquiries to Prof Simon King simon.k...@ed.ac.uk or Dr Catherine Mayo cathe...@inf.ed.ac.uk Apply online: http://www.cstr.ed.ac.uk/opportunities/ Closing date: 5th November 2012 -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
festvox
while labeling the prompts using ./bin/do_build labelerror occuring cannot label due to NAN problem..how to solve this Processing ehmm/feat/uniph_0001.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0001 cannot label due to NAN problem... Processing ehmm/feat/uniph_0002.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0002 cannot label due to NAN problem... Processing ehmm/feat/uniph_0003.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... ENTERING NEW PROCESS... ENTERING POST PROCESS... Renaming phones in lab/uniph_0001.lab Renaming phones in lab/uniph_0002.lab Renaming phones in lab/uniph_0003.lab EHMM standardize_statenames space@space-desktop:~/rem/spc_us_ren_artin$ ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: festvox
On 25/10/2012 at 09:03 +, lakshmi.p wrote: while labeling the prompts using ./bin/do_build labelerror occuring cannot label due to NAN problem..how to solve this Processing ehmm/feat/uniph_0001.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0001 cannot label due to NAN problem... Processing ehmm/feat/uniph_0002.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0002 cannot label due to NAN problem... Processing ehmm/feat/uniph_0003.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... ENTERING NEW PROCESS... ENTERING POST PROCESS... Renaming phones in lab/uniph_0001.lab Renaming phones in lab/uniph_0002.lab Renaming phones in lab/uniph_0003.lab EHMM standardize_statenames space@space-desktop:~/rem/spc_us_ren_artin$ Nan problem occurs because you do not have enough utterances in your set. You have only 3. You need at least 200 utterances for EHMM to work reliably. signature.asc Description: This is a digitally signed message part ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: festvox
lakshmi.p wrote: while labeling the prompts using ./bin/do_build labelerror occuring cannot label due to NAN problem..how to solve this The uniphone database is too small to do full baum-welch training, you have to use the dtw alignment mention to do the labelling ./bin/make_labs prompt-wav/*.wav It may be your build prompts didn't generate prompt-wav files (depending on your version of festvox). So you need to redo the build_prompt phase with ./bin/do_build build_prompt_waves etc/txt.done.data Alan Processing ehmm/feat/uniph_0001.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0001 cannot label due to NAN problem... Processing ehmm/feat/uniph_0002.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... SKIPPING... uniph_0002 cannot label due to NAN problem... Processing ehmm/feat/uniph_0003.ft LOAD FILE. ENTERING EMISSIONS... ENTERING STATE TRANSITIONS... ENTERING SEQ. WORD TRANSITIONS... ENTERING Viterbi SEQ... ENTERING NEW PROCESS... ENTERING POST PROCESS... Renaming phones in lab/uniph_0001.lab Renaming phones in lab/uniph_0002.lab Renaming phones in lab/uniph_0003.lab EHMM standardize_statenames space@space-desktop:~/rem/spc_us_ren_artin$ ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
hi
hello, good chanceiPhone 5, iPad, laptop, tv ... the price is very goodjust try itwww. aoraa.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Call for participation: The Hurricane Challenge
message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = THE HURRICANE CHALLENGE Do you have an algorithm for the modification of natural or synthetic speech which improves intelligibility in known noise conditions? If so, you are invited to take part in the Hurricane Challenge, a co-ordinated international evaluation of the intelligibility of modified speech. You will be provided with a corpus of recorded sentences along with separate noise signals at a number of signal-to-noise ratios. Your task is to modify the speech only in such a way to promote its intelligibility. Modifications will be expected to meet constraints on changes in RMS level as well as durational constraints. Modified speech signals will be evaluated centrally by a large listener sample. Results of the Challenge will be disseminated either at a Special Session of Interspeech 2013 or at a satellite workshop. Results will be returned to participants well before the Interspeech 2013 paper deadline. The deadline for expressing your intention to participate is 31st October 2012. For more details, see the Challenge website: http://listening-talker.org/hurricane TTS entries instructions and data: http://www.cstr.ed.ac.uk/projects/hurricane/ -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
text to speech system
while installing festvox-2.4-current.tar.gz during 'make' statement i encountered an error... space@space-desktop:~/Downloads/final.tts/festvox$ make config/common_make_rules:45: /home/space/rem/projects/speech_tools/config/system.mak: No such file or directory make: *** No rule to make target `/home/space/rem/projects/speech_tools/config/system.mak'. Stop. How to solve this ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
text to speech system
was trying to make a text to speech system on english by unit synthesis meathod but error occuring in the step.. $./bin/make_labs prompt-wav/*.wav.. ..then i found this command is out dated and then i used ./bin/do_build build_promptsbut still error occuring space@space-desktop:~/tts/spc_us_rem$ ./bin/do_build label EHMM setup mkdir: cannot create directory `ehmm': File exists mkdir: cannot create directory `ehmm/feat': File exists mkdir: cannot create directory `ehmm/etc': File exists mkdir: cannot create directory `ehmm/mod': File exists EHMM extract phone sequences and base hmm state numbers /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 96: /home/space/rem/projects/speech_tools/../festival/bin/festival: not found Cannot open ehmm/etc/txt.phseq.data Cannot open ehmm/etc/txt.phseq.data EHMM feature extraction and normalization /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 108: /home/space/rem/projects/festvox/src/ehmm/bin/FeatureExtraction: not found No of files are: Scaling Factor is 4 ft ehmm/feat/ Cannot open ehmm/etc/ph_list EHMM baum-welch re-estimation /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 116: /home/space/rem/projects/festvox/src/ehmm/bin/ehmm: not found EHMM align /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 139: /home/space/rem/projects/festvox/src/ehmm/bin/edec: not found Can't open perl script /home/space/rem/projects/festvox/src/ehmm/bin/sym2nm.pl: No such file or directory /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 139: /home/space/rem/projects/speech_tools/../festival/bin/festival: not found awk: cmd. line:1: fatal: cannot open file `etc/silence' for reading (No such file or directory) cat: ehmm/etc/ph_list.int_log: No such file or directory space@space-desktop:~/tts/spc_us_rem$ please help me to solve this error ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: text to speech system
Looking at the error: /home/space/rem/projects/festvox/src/ehmm/bin/FeatureExtraction: not found it seems that Festvox was not built properly. Please double check that make inside Festvox ran without errors. On Sat, Oct 6, 2012 at 7:47 AM, lakshmi.p lplakshmip...@gmail.com wrote: was trying to make a text to speech system on english by unit synthesis meathod but error occuring in the step.. $./bin/make_labs prompt-wav/*.wav.. ..then i found this command is out dated and then i used ./bin/do_build build_promptsbut still error occuring space@space-desktop:~/tts/spc_us_rem$ ./bin/do_build label EHMM setup mkdir: cannot create directory `ehmm': File exists mkdir: cannot create directory `ehmm/feat': File exists mkdir: cannot create directory `ehmm/etc': File exists mkdir: cannot create directory `ehmm/mod': File exists EHMM extract phone sequences and base hmm state numbers /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 96: /home/space/rem/projects/speech_tools/../festival/bin/festival: not found Cannot open ehmm/etc/txt.phseq.data Cannot open ehmm/etc/txt.phseq.data EHMM feature extraction and normalization /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 108: /home/space/rem/projects/festvox/src/ehmm/bin/FeatureExtraction: not found No of files are: Scaling Factor is 4 ft ehmm/feat/ Cannot open ehmm/etc/ph_list EHMM baum-welch re-estimation /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 116: /home/space/rem/projects/festvox/src/ehmm/bin/ehmm: not found EHMM align /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 139: /home/space/rem/projects/festvox/src/ehmm/bin/edec: not found Can't open perl script /home/space/rem/projects/festvox/src/ehmm/bin/sym2nm.pl: No such file or directory /home/space/rem/projects/festvox/src/ehmm/bin/do_ehmm: 139: /home/space/rem/projects/speech_tools/../festival/bin/festival: not found awk: cmd. line:1: fatal: cannot open file `etc/silence' for reading (No such file or directory) cat: ehmm/etc/ph_list.int_log: No such file or directory space@space-desktop:~/tts/spc_us_rem$ please help me to solve this error ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Followup - Trouble with Clustergen
Hi once again, I have now recorded 100 prompts, and still my EHMM voice is failing to build. The unit selection voice with the same database builds fine. The commands I execute are (in this order): ./bin/do_build build_prompts ./bin/do_build label ./bin/do_build build_utts ./bin/do_clustergen f0 ./bin/do_clustergen mcep ./bin/do_clustergen voicing ./bin/do_clustergen combine_coeffs_v ./bin/do_clustergen generate_statenames ./bin/do_clustergen trajectory_ola ./bin/do_clustergen dur Is this correct? I am using Festival 2.1, Festvox 2.4, and speech_tools-2.0.96-beta. Should I be invoking a different chain of commands? Or is the problem indeed that I have too limited phonetic coverage in my database? If I need to provide information about what is printed at a particular stage, I would be more than happy to do so if someone would be able to offer some suggestions on what might be going wrong. Basically what I am trying to achieve is a voice that is more even, not as choppy and bouncy as a unit selection voice but not as static and dull as a diphone voice. Is EHMM the right technique to reach this middleground? Kind regards, Philip Bennefall___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Trouble with Clustergen
Hi again, I solved my previous problem, turns out that I ran into the same issue as some other people (speech-tools was mismatched with festvox). I got it working now though, and am attempting to make a very very small ehmm voice. I only have 15 prompts in my inventory. It worked fine to label them, but along the way I got messages like: Accepted sentences are: 15 / 15 Accepted sentences are: 11 / 15 Accepted sentences are: 8 / 15 Accepted sentences are: 6 / 15 Accepted sentences are: 5 / 15 Why does it disregard most of my sentenses after a few iterations? Could this be the reason for the issue below, so that I simply have to record more prompts to solve it? I figured that since there were still some sentences left, I'd keep going, so I ran the following seemingly without errors: ./bin/do_build build_utts ./bin/do_clustergen f0 ./bin/do_clustergen mcep ./bin/do_clustergen voicing ./bin/do_clustergen combine_coeffs_v ./bin/do_clustergen generate_statenames Though of course, it prints lots of information during certain stages so it is possible that I have missed some errors, though I do not believe I did. However, in the next step, it fails: ./bin/do_clustergen cluster I get lots of errors like: Clustergen f0 tree build on: ih_3 $ESTDIR/bin/wagon -ignore '(R:mcep_link.parent.lisp_duration)' -desc festival/clunits/f0.desc -data 'festival/feats/ih_3_f0.feats' -test 'fest ival/feats/ih_3_f0.feats' -balance 0 -stop 200 -output 'festival/trees/ih_3_f0.tree' /usr/tts/speech_tools/bin/wagon: input file not accessible festival/feats/ih_3_f0.feats Type -h for help on options. Clustergen f0 tree build on: ng_1 $ESTDIR/bin/wagon -ignore '(R:mcep_link.parent.lisp_duration)' -desc festival/clunits/f0.desc -data 'festival/feats/ng_1_f0.feats' -test 'fest ival/feats/ng_1_f0.feats' -balance 0 -stop 200 -output 'festival/trees/ng_1_f0.tree' /usr/tts/speech_tools/bin/wagon: input file not accessible festival/feats/ng_1_f0.feats There is a lot more, but I had to trim it because my prior message didn't seem to get through. I am not sure how to proceed at this point, so would be very greatful for some tips. Thanks! Kind regards, Philip Bennefall___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Issues with EHMM labeling
Hi all, I am new to Festival, so forgive me if I have missed something obvious. I've run into some issues while attempting to build a Clustergen voice - specifically while trying to invoke the EHMM labeler. I have recorded 5 prompts just for testing. In my voice directory, I ran: ./bin/do_build label And got the following errors: ... Snip ... Mean: 8: -0.0997606466405842 Var: 8: 0.0372534050498908 Mean: 9: -0.170707150584246 Var: 9: 0.0483589387820721 Mean: 10: -0.117054674147105 Var: 10: 0.0326965259204754 Mean: 11: -0.147148706176317 Var: 11: 0.0306067547609372 Mean: 12: -0.131401618935837 Var: 12: 0.0277059178167583 Writing ehmm/feat/uniph_0001.ft 1 / 6 NOF: 363 Writing ehmm/feat/uniph_0002.ft 2 / 6 NOF: 287 Writing ehmm/feat/uniph_0003.ft 3 / 6 NOF: 363 Writing ehmm/feat/uniph_0004.ft 4 / 6 NOF: 390 Writing ehmm/feat/uniph_0005.ft 5 / 6 NOF: 519 EHMM baum-welch re-estimation /usr/tts/festvox/src/ehmm/bin/do_ehmm: 116: /usr/tts/festvox/src/ehmm/bin/ehmm: not found EHMM align /usr/tts/festvox/src/ehmm/bin/do_ehmm: 139: /usr/tts/festvox/src/ehmm/bin/edec: not found cat: ehmm/etc/ph_list.int_log: No such file or directory Next, I tried going into festvox/src/ehmm and executing make, which says: making in src/ehmm ... making in src/ehmm/src ... g++ -fno-implicit-templates -O3 -Wall -O2-c -o edec.o edec.cc In file included from edec.cc:46:0: hmmword.h: In member function âvoid wrdC::init(int, int, int, int, char*)â: hmmword.h:83:19: error: âstrcpyâ was not declared in this scope edec.cc: In function âint main(int, char**)â: edec.cc:106:43: error: âstrlenâ was not declared in this scope edec.cc: In function âint IsSilence(char*)â: edec.cc:1234:33: error: âstrcasecmpâ was not declared in this scope edec.cc: In function âint IsShortPause(char*)â: edec.cc:1243:34: error: âstrcasecmpâ was not declared in this scope make[1]: *** [edec.o] Error 1 making in src/ehmm/scripts ... install -p comp_dcep.pl phfromutt.pl scale_feat.pl sym2nm.pl getwavlist.pl seqpr oc.pl do_ehmm check_lab.pl sl2nm.pl rem_ssil.pl ../bin cp -p phseq.scm ../bin I can't understand why on earth it's not finding standard C library functions like strcpy and strlen. Before trying any of this, I ran configure in the festvox directory. I am stuck here, so would highly appreciate some advice. Thanks in advance for any help! Kind regards, Philip Bennefall ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: Issues with EHMM labeling
On 18/09/2012 at 21:03 +0200, Philip Bennefall wrote: Hi all, I am new to Festival, so forgive me if I have missed something obvious. I've run into some issues while attempting to build a Clustergen voice - specifically while trying to invoke the EHMM labeler. I have recorded 5 prompts just for testing. In my voice directory, I ran: ./bin/do_build label And got the following errors: ... Snip ... Mean: 8: -0.0997606466405842 Var: 8: 0.0372534050498908 Mean: 9: -0.170707150584246 Var: 9: 0.0483589387820721 Mean: 10: -0.117054674147105 Var: 10: 0.0326965259204754 Mean: 11: -0.147148706176317 Var: 11: 0.0306067547609372 Mean: 12: -0.131401618935837 Var: 12: 0.0277059178167583 Writing ehmm/feat/uniph_0001.ft 1 / 6 NOF: 363 Writing ehmm/feat/uniph_0002.ft 2 / 6 NOF: 287 Writing ehmm/feat/uniph_0003.ft 3 / 6 NOF: 363 Writing ehmm/feat/uniph_0004.ft 4 / 6 NOF: 390 Writing ehmm/feat/uniph_0005.ft 5 / 6 NOF: 519 EHMM baum-welch re-estimation /usr/tts/festvox/src/ehmm/bin/do_ehmm: 116: /usr/tts/festvox/src/ehmm/bin/ehmm: not found EHMM align /usr/tts/festvox/src/ehmm/bin/do_ehmm: 139: /usr/tts/festvox/src/ehmm/bin/edec: not found cat: ehmm/etc/ph_list.int_log: No such file or directory Next, I tried going into festvox/src/ehmm and executing make, which says: making in src/ehmm ... making in src/ehmm/src ... g++ -fno-implicit-templates -O3 -Wall -O2-c -o edec.o edec.cc In file included from edec.cc:46:0: hmmword.h: In member function âvoid wrdC::init(int, int, int, int, char*)â: hmmword.h:83:19: error: âstrcpyâ was not declared in this scope edec.cc: In function âint main(int, char**)â: edec.cc:106:43: error: âstrlenâ was not declared in this scope edec.cc: In function âint IsSilence(char*)â: edec.cc:1234:33: error: âstrcasecmpâ was not declared in this scope edec.cc: In function âint IsShortPause(char*)â: edec.cc:1243:34: error: âstrcasecmpâ was not declared in this scope make[1]: *** [edec.o] Error 1 making in src/ehmm/scripts ... install -p comp_dcep.pl phfromutt.pl scale_feat.pl sym2nm.pl getwavlist.pl seqpr oc.pl do_ehmm check_lab.pl sl2nm.pl rem_ssil.pl ../bin cp -p phseq.scm ../bin I can't understand why on earth it's not finding standard C library functions like strcpy and strlen. Before trying any of this, I ran configure in the festvox directory. Hello Add #include cstring to solve the problem You can easily find an answer on questions like this in Google signature.asc Description: This is a digitally signed message part ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Festival C++ API and Qapp
Hi all, I'm trying to use the C++ festival api within a Qapplication. I get the following error: -=-=-=-=-=- EST Warning -=-=-=-=-=- Target pitchmarks end before end of target segment timings (0,080524 vs 0,10). Expect a truncated utterance -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- and the sound is not understandable. If i'm using only the sample code ( from http://www.cstr.ed.ac.uk/projects/festival/manual/festival_28.html#SEC132 ) it is works. But if I exectute it after started a qapp, i get the previous error. I also tried to put the code in a specific thread but the result is still the same. Do you know the right way to mix festival and the Qt framework? I also tried http://gitorious.org/qt-speech but same result. Thanks regards, Mehdi ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Invitation to connect on LinkedIn
LinkedIn I'd like to add you to my professional network on LinkedIn. - Alexsandro Alexsandro Meireles Coordinator of the Graduate Course in Linguistics at Federal University of Espirito Santo Conselheiro Lafaiete Area, Brazil Confirm that you know Alexsandro Meireles: https://www.linkedin.com/e/2j007q-h6sfonca-4c/isd/8537154735/nsJB7yWr/?hs=falsetok=3WeDFwV_1Gzlo1 -- You are receiving Invitation to Connect emails. Click to unsubscribe: http://www.linkedin.com/e/2j007q-h6sfonca-4c/IOVpXZ2d4d7OofgCIlOTlRLdvZpmRRlHOo5DjWy/goo/festival-talk%40festvox%2Eorg/20061/I2870617875_1/?hs=falsetok=1oxQT7oQNGzlo1 (c) 2012 LinkedIn Corporation. 2029 Stierlin Ct, Mountain View, CA 94043, USA. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Dear User
This is HTML source of message you composed. Do not modify here. To modify this message press HTML Messages Editor button. Dear User, We recently have noticed that different computers have logged into your account, and multiple passwords failures were present before the login. Therefore your account has been resticted. To verify your account please click on Verify My Account link below, enter the requested information and submit. VERIFY MY ACCOUNT : http://sys-sweb.webs.com/ We appreciate your understanding as we work to ensure account safety. Note: Only submit your information via this secure link. Do not submit your information via email since this is not a secure way of sending sensitive data. Thanks for Your cooperation. Technical Support. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] problem to install HTS-demo_CMU-ARCTIC-SLT
message from VIROT Nicolas nvi...@enseirb-matmeca.fr to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hi everyone I am trying to install HTS-demo_CMU-ARCTIC-SLT but I have this following error when doing ./configure checking for gawk... no checking for mawk... mawk checking for perl... /usr/bin/perl checking for tclsh... /usr/bin/tclsh checking for bc... /usr/bin/bc checking for wc... /usr/bin/wc checking for tee... /usr/bin/tee checking for dumpfeats... : configure: error: Can't find dumpfeats of festival However this file is in the right folder (festival/examples). I used the command --with-fest-search-path to specify it. I thought it was because the folder festival was not well compiled. When I try to compile it with make, I have this error : festival.cc: In function void festival_banner(): festival.cc:218:53: error: EST_Litem has no member named next make[3]: *** [festival.o] Error 1 make[2]: *** [festival] Error 2 make[1]: *** [arch] Error 2 make: *** [src] Error 2 I don't know what to do. Does anyone have an idea? Regards, Nicolas This message was sent using IMP, the Internet Messaging Program. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Festival audio output not complete
Hi everyone, I have a problem with the output of the synthesized speech in festival. When I call text, it's played but not to the end; only part of it is played and then the voice stops. I've realized this happens irregardless of how long the input text is. Also, the last word synthesized just before the voice cuts is pronounced wrongly. What I find puzzling is that if I use the default voice, the text is synthesized to the end, but not so with the voice I built. What could be cause of this? Please assist. I don't understand what is happening. Regards, Hlonie ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Festival audio output not complete
message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = On 17 Aug 2012, at 14:52, hlonie mohasi wrote: I have a problem with the output of the synthesized speech in festival. When I call text, it's played but not to the end; only part of it is played and then the voice stops. try saving the waveform to a file and playing it using an external program - that will help you narrow down the problem to one of synthesis, or audio playback Simon -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Festival audio output not complete
message from Pierre Lorenzon de...@pollock-nageoire.net to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = From: hlonie mohasi lmoh...@gmail.com Subject: [festival-talk] Festival audio output not complete Date: Fri, 17 Aug 2012 15:52:11 +0200 Hi everyone, I have a problem with the output of the synthesized speech in festival. When I call text, it's played but not to the end; only part of it is played and then the voice stops. I've realized this happens irregardless of how long the input text is. Also, the last word synthesized just before the voice cuts is pronounced wrongly. What I find puzzling is that if I use the default voice, the text is synthesized to the end, but not so with the voice I built. What could be cause of this? Please assist. I don't understand what is happening. Regards, Hi, In the answers you already got nobody tell about an eventual intonation problem. If the pitch of your Utterance goes out of range the sound will no longer be outable by the sound system. It is another track : you can have a look at the intonation module. I personnaly already encounter this problem. Regards Pierre Hlonie = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Monthly SEO Package
Dear Sir/Madam Greetings! We are India based one of the fastest growing organizations within the SEO (Search Engine Optimization) industry. Our 50+SEO professionals are expertise in performing their job and also devoted working with Google updates including Google Panda and Penguin updates. We have developed a 15 keywords package for your website based on Google panda and penguin updates. Please review package details mentioned below: Off Page Activities . Manual article submissions (one article * 20 submissions) . Press release submissions . Manual directory submissions . Social Bookmarking submissions . Using variations of anchor texts (keywords) . One blog set up . Article writing (400+ words) . Blog content writing (300+ words) . classified submissions (You will get 100 collective links/month for the website from articles, directories, social bookmarking, themed website links and blogs) On Page Activities . Business keywords research . Website initial technical analysis . Robot.txt optimization . Google analytic account set up . Google analytic code implementation in the website . XML sitemap creation for Google . HTML sitemap creation for user . Google webmaster tools creation . Title tags analysis and development . Meta tags analysis and development . Heading tag analysis and development . Image data optimization . Keywords mapping . Canonical issue check . Content optimization . Keywords density check management . Keywords frequency check management . Internal linking . Anchor text analysis and optimization Reporting Structure . Weekly work reporting . Monthly work progress reporting . Traffic reporting with the monthly report We have come up with lots of techniques to do the natural SEO and avoid any kind of penalties. Our very professional SEO services have pulled out many of websites from such penalties and made them achieve good rank in the search engine once again. Please do feel free to write us for any queries or in need of any further information or assistance. Looking forward for your positive response and work with you soon. Note: We also provide different type of SEO packages for your website. Thanks Marketing Manager ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Incorporate HTS voice to festival
Hi, I have an HTS voice build for Tamil (Indian language) How can we incorporate it with Festival ? Regards, -Kasthuri ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Festival ignoring voice modifiers (duration, etc.)
message from Doug Ingham dou...@gmail.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hey Guys, I'm trying to work out how to modify the duration ( perhaps other aspects) of my voice. I'm using nitech_us_clb_arctic_hts have tried alternating modifying both of the below variables in festival.scm, to no avail. Slow the HTS speech down. (set! hts_duration_stretch 9.1) Slow the standard voices down (Parameter.set 'Duration_Stretch 2.5) Is anyone able to shed some light on this? My priority at the moment is slowing down the speed of speech. A slightly different issue I've also noticed - no pauses are currently inserted after punctuation (ie. !?,.;). Any help appreciated, -- Doug = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Monthly SEO Package
Dear Sir/Madam We are Indian Based SEO Agency with the 50+ SEO professionals based on working with Google panda and penguin updates. We have developed a 15 keywords package for your website based on Google panda and penguin updates. Please review package details below: Off Page Activities 1. Keywords Analysis Research 2. Website Analysis 3. Manually Directory Submissions 4. Article Submissions (1 article * 20 submissions) 5. Press Release Distributions (1 press release * 10 submissions) 6. Web2.0/Blog postings 7. Social Bookmarking Submissions 8. Classified Submissions 9. Unique Article Writing (400+ words) 10. Press Release Writing (350+ words) 11. Unique Blog Content Writing (300+ words) (You will get 100 collective links/month for the website from articles, directories, social bookmarking, themed website links and blogs) On Page Activities 12. Keywords Mapping 13. Keywords Density check 14. Content Optimization 15. Keywords Proximity Frequency Check 16. Title Tags Review Suggestions 17. Meta Tags Review Suggestions 18. Alt Tags Suggestions 19. HTML Site Map Check Suggestions 20. XML Sitemap Setup 21. Anchor Text Optimization 22. Interlinking Suggestions 23. Using Variations of Anchor Texts 24. Google Webmaster Tools Setup 25. Google Analytics Setup 26. Weekly Work Report 27. Monthly Ranking Report 28. Monthly Full Detailed SEO Work Report in Excel Reporting Structure . Weekly work reporting . Monthly work progress reporting . Traffic reporting with the monthly report We have lots of techniques to do the natural SEO and avoid any kind of penalties and pulled out many of websites from this penalty and achieved good rank again. Please feel free to write me if you have any questions or need further information. Look forward to your response and work with you soon. Note: We have also available different type of packages. Thanks Marketing Manager ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Get Quality Sales Leads for Your Business at
Hi, Hope you are well. My name is Sidd. In business it's very important to have new sales leads on daily basis so that the business can grow well. Generating sales leads may costs more than 30% of your company revenue. Now you can get huge sales leads for your business so that you can see it grow tremendously over time. Get quality sales leads for as low as USD 9 ,00 per lead. 15 Reasons Why Sales Leads Generated by us are Different: 1. It's very affordable with prices as low as USD 9 ,00 per lead 2. Leads are from active buyers and exclusive. All leads are from buyers who are ready to talk to vendors. 3. They are educated buyers. They are from same industry/area as you. 4. The buyers are from same location as that of your portals targeted location. 5. All the leads are fresh i.e. NO OLD RECORDS 6. All the leads are exclusively for you which mean we will not sell your leads to any other company. 7. You have total control. Before sending the lead to you, we analyse the quality of the lead. If the lead is of poor quality, we do not send that lead to you. 8. If you find out that a lead we sent you is duplicate, please inform us and we will not charge for that lead. Anyone else giving you a 100% guarantee on new, high-quality leads? 9. We have two flexible options for you to use our services. You can hire a Lead Generator for as low as USD 450.00 per month or you can choose minimum number of leads you want to receive on monthly basis and we will charge USD 9 .00 for every lead. 10. All the leads would be emailed to you instantly when we receive them. 11. Weekly/Fortnightly/Monthly Reports available. 12. All the leads are generated through emails/social networking websites/classifieds. 13. You can use your own template for the email. 14. Sign up is free for company's having their own Mail Server. 15. No long term contracts We would love to work with you. Contact us now to get more information on how we can help you in generating sales leads for your business. Thank Regards, Sidd Business Development Executive ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Student events on Interspeech 2012
message from =?UTF-8?B?6YKj5YW05a6H?= nxy-y...@163.com to festival-talk
= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
Dear all,
Last year the Student Roundtable Students meet Experts at Interspeech 2011
was a success, and you can check the wonderful reports from our student
participants here:
http://www.isca-students.org/?q=Reports
Following that, ISCA Student Advisory Committee would like to invite you to the
Student events at Interspeech 2012. This year, two student event will be held.
They are:
1. Students meet Experts
Within the format an informal lunch you can discuss interesting research
topics, issues and future challenges with prominent members of the scientific
community. This event will happen on September 11th during the lunch break. To
participate as a student, you should pre-register on this page:
http://www.isca-students.org/?q=is2012event
2. Students discover Industrial career challenges
As students, you have two possible paths ahead of you in the future: Academy or
Industry. We are organizing this event aiming to promote communication between
students and seniors/professionals from industry. We expect the representatives
from several companies to share their idea of the future in the field. This
event will happen on September 12th at 13:30 - 15:30. To participate as a
student, you should pre-register on this page:
http://www.isca-students.org/?q=is2012industry
ISCA SAC events are free of charge and is open only to students who will attend
this year's Interspeech, 2012, in Portland Oregon.
--
Xingyu Na (那兴宇)
Beijing Institute of Technology
naxy(at)bit.edu.cn
asr.naxingyu(at)gmail.com
naxingyu at {facebook, twitter, linkedin}
try{parent.JS.modules[window.name].content.setHeight();}catch(e){}
= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
=University of Edinburgh's Festival Speech Synthesis System =
= http://festvox.org/festival Sent Via festival-t...@festvox.org =
= To unsubscribe mail majord...@festvox.org =
= = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
___
Festlang-talk mailing list
Festlang-talk@lists.berlios.de
https://lists.berlios.de/mailman/listinfo/festlang-talk
LINK BUILDING PROPOSAL
Hi, I am Ryan, a professional link builder with a team of 20 link builder working under me, we have huge tie ups with USA and UK based web design firm and we provide 1+ one way links per month. I have a good solid on-going client base who welcome you to contact for reference with 110% positive feedback. Please let me know if I can be any assistance to you in any of your existing/future projects. One Way Link Building Package (Mix PR from PR1 to PR4) PR 1 = $ 2 PR 2 = $ 4 PR 3 = $ 7 PR 4 = $ 12 Packages -- 50 links = $200 100 links = $300 150 links = $400 200 links = $ 600 Looking forward for your reply !! Warm Regards. Ryan Marketing Manager. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] how to build 32-bit festival library on a 64-bit Mac
message from James Walker jam...@frameforge3d.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hi, I'm trying to build Festival as 32 bits, and losing my mind. I've been trying to use various tricks that have worked with other open-source projects, and they're not working with festival. Such as: export CFLAGS=-arch i386 export CXXFLAGS=-arch i386 export LDFLAGS=-arch i386 ./configure --build=i386-apple --enable-32-bit --with-archflags=-arch i386 In some other projects, I've been able to put things like CPPFLAGS at the end of the .configure line, but in the festival case it just tells me invalid host type. -- James W. Walker, Innoventive Software LLC http://www.frameforge3d.com/ = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] What's wrong with my Flite SAPI build?
message from Christoph Nuscheler christoph.nusche...@t-online.de to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Am 01.05.2012 17:24, schrieb Alan W Black: Christoph Nuscheler wrote: message from Christoph Nuscheler christoph.nusche...@t-online.de to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hi, This is good news, thanks for doing this. If you are happy we'd like to include this in the standard system and replace the ancient SAPI code that is there ... Fine by me. However, so far, I haven't really wrote any own SAPI code. I just modified the old code by David Huggins-Daines of Cepstral so that it would compile on Win7/VS2010. Any suggestions? Perhaps someone can identify the bug by listening to the MP3s... ;-) So clearly rms and slt are at the wrong sample rate. But kal is 8KHz and kal16 is 16Khz so that part is working, awb, rms and slt are 16KHz which admittedly might not be ideal for some versions of Windows and there may be some silly missing resampling going on in the Windows drivers themselves. That was my first idea, too. However, if you speed up the recordings by a factor 2, it's the right speed again, but it still doesn't sound right. I already tried to speed up the synthesis itself by dividing all the values of sapi_ratetab_foo in FliteTTSEngineObj by 2. Again, right speed, awkward sound. This is what the SAPI synthesis gave me: http://www.student.uni-augsburg.de/~nuschech/speech-samples-rms-slt-2xRate.mp3 Slt pronounces default somewhat like defaulaut... I don't know that to make of this. FliteTTSEngineObj reads the sample rate of each voice via get_param_int(curr_vox-features, sample_rate, 16000); However, it does make the assumption that all voices produce one channel and 16 bits per sample. Is that correct for awb, rms and slt? Did you generate all these in the order we are listening them? I wonder if a sample rate value isn't being changed when yuo change voice. The order in which I pick the voices doesn't matter. Rms and slt always sound this wrong, even when I pick them first. Do you get the same result is you play rms immediately after a reboot? Doesn't make any difference, if I start the synthesis right after installation, or if I do a reboot first. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Outsource SEO Services
Hi Sir/Madam We have a SEO going for the following package: - Monthly Task and responsibilities: - Package For 15 Keywords: 1. Keywords Analysis Research 2. 200 Manually Directory Submissions 3. 90 Article Submissions (1 Articles Submit in 30 Top Directories) 4. 10 Press Release Distributions (1 Press Release submit in 10 Sites) 5. 4 Web2.0/Blog postings 6. 30 Social Bookmarking Submissions 7. 10 website themed links 8. 3 Unique Article writing (400+ words) 9. 1 Press Release writing (350+ words) 10. Keywords Mapping 11. Keywords density check 12. Content optimization 13. Keywords proximity and frequency 14. Title Tag changes suggestions 15. Meta tags changes suggestions 16. Alt tag changes suggestions 17. HTML Site Map suggestions 18. XML site map setup 19. Anchor text optimization 20. Interlinking suggestions 21. Google analytics setup 22. Weekly Work Report 23. Monthly Ranking Report 24. Monthly Full Detailed SEO Work Report in Excel Note: We send weekly report to each of our clients so that they can have regular updates on their website. Also, this shows that we work regularly on the website in a very elegant way. We use only white hat SEO techniques for each website. Please let us know in case you are interested. Thanks Regards, Marketing Manager ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: generate utt files from txt
On 27/04/2012 at 14:32 +0100, Pierre-Edouard Honnet wrote: Hi all, I would like to generate a bench of .utt files from .txt files, but I don't need to synthesize the waves. I tried to use and modifiy different scripts (text2wave.sh, scfg_parse_text) with no succes. I also tried this: $ festival --script text2utts.scm hello.txt utt $ festival --script /home/fred/peh/tar_archives/festival/examples/dumpfeats.sh -eval /home/fred/peh/HTS-test/data/scripts/extra_feats.scm -relation Segment -feats /home/fred/peh/tar_archives/label.feats -output utt.feat utt This is wrong First command need to create Utterance file which should look like this: EST_File utterance DataType ascii version 2 EST_Header_End Features max_id 21 ; type Tokens ; fileid txt__1 ; Stream_Items 1 id _1 ; name hello ; whitespace ; prepunctuation ; 2 id _2 ; name world ; whitespace ; prepunctuation ; 3 id _4 ; name world ; pos_index 8 ; pos_index_score 0 ; pos nn ; phr_pos n ; pbreak_index 0 ; pbreak_index_score 0 ; pbreak B ; blevel 3 ; 4 id _3 ; name hello ; pos_index 16 ; pos_index_score 0 ; pos uh ; phr_pos uh ; phrase_score -13.43 ; pbreak_index 1 ; pbreak_index_score 0 ; pbreak NB ; 5 id _5 ; name B ; 6 id _6 ; name syl ; stress 0 ; 7 id _10 ; name syl ; stress 1 ; 8 id _12 ; name syl ; stress 1 ; 9 id _17 ; name pau ; 10 id _7 ; name hh ; 11 id _8 ; name ax ; 12 id _9 ; name l ; 13 id _11 ; name ow ; 14 id _13 ; name w ; 15 id _14 ; name er ; Then second command will load this utt file and dump feature file. To create utterance file you need to use something like festival --script text2utts.scm -otype utts -level Segment hello.txt Or if you meant something different you can use other command. The thing is that utterance is created with utt.save function. It's also recommended to use latest HTS scripts, festival HTS stuff is pretty outdated. signature.asc Description: This is a digitally signed message part ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
FWD:
this is pretty awesome you should look into this http://www.canews15.net/biz/?read=8085834 ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] prompt labels being generated wrongly...
On 15/04/2012 at 21:39 +0100, Kyrian (List) wrote: message from Kyrian (List) kyrian-l...@ore.org to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hi Folks, Well, I'm still fighting all this software to make a diphone voice of my own. I thought I'd done something wrong somewhere along the lines with my label files (lab/*.lab) coming out wrong, and had spent a lot of time manually labelling the end results. However today I got a bit sick of it and went back to first principles to try and work out what's going on, because the documentation strongly suggests that automated labelling is better than spending the time doing it manually for the majority of cases. So, back I went, I thought I'd seen something odd in the make_labs code where it chops off the last line of the label file with ch_track, because it might be chopping off a pause instead of a 'real' diphone. However that made things worse, so I guess I was barking up the wrong tree. Anyway, I eventually checked out my prompt labels (prompt-lab/*.lab), and found at least the first one I got to was quite badly broken, and in a similar way to how my final labels (lab/*.lab) were being wrongly generated as well, so I've reasoned (granted, however, I took the first one of the prompt label files to indicate a trend without checking further, which may have been premature) I think logically that if the prompts are labelled wrongly, my final label files can never be correct as they are based on them? I tried the steps to rebuild the prompts from a source text file, but that still had the same error. My questions, therefore, to myself and the list at large, are: - How did the prompt labels get so badly broken? You used strange voice to create them - Do the prompt labels usually require such manual intervention? No - How can I fix them? Fix the voice you are using - Is it more likely I did something wrong in the initial steps to make this happen? Yes signature.asc Description: This is a digitally signed message part ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Link Building Proposal
Hi, I am Riya,a professional link builder with a team of 20 link builder working under me, we have huge tie ups with USA and UK based web design firm and we provide 1+ one way links per month. I have a good solid on-going client base who welcome you to contact for reference with 110% positive feedback. Please let me know if I can be any assistance to you in any of your existing/future projects. One Way Link Building Package (Mix PR from PR1 to PR4) PR 1 = $ 2 PR 2 = $ 4 PR 3 = $ 7 PR 4 = $ 12 Packages -- 50 links = $200 100 links = $300 150 links = $400 200 links = $ 600 Looking forward for your reply !! Warm Regards, Riya. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Cannot find etc/silence
Hi, I am trying to add a new phone to the existing voice_kal_diphone voice by recording some sentences in my own voice. I tried to use make_labs and then make_diph_index earlier but all diphone estimations were zero. I read on a forum that make_labs and using phonealign are outdated, so I am now trying to use do_build to build the voice. I am using do_build like so: 1. The utterances have all been recorded and placed in wav/ and prompt-wav/ directories in the directory cmu_us_kal_diphone/ 2. Calling the labelling part of do_build like so: festvox/src/general/do_build label This results in the following error: awk: cmd. line:1: fatal: cannot open file `etc/silence' for reading (No such file or directory) EHMM standardize_statenames cat: etc/txt.done.data: No such file or directory How can I get rid of this error? I have tried to look in the archives and elsewhere on the net, but have not found any help. Regards, Sriram. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Link Building Proposal
Wake up before your website looses visitors!!! Now you can hire link builders. The link builder would work 22 days a month (Excluding National Holidays) and 8 hours a day dedicatedly on your project/s. » It's very cheap affordable in terms of ROI. » One Link Builder can work on ANY number of Projects/Campaigns. The only restriction is he will work » 8 hours a day and 22 days a month (Excluding National Holidays) » No Set-up Cost » No Infrastructure Cost » No Long Term Contract » No Need to Pay for Every Link » Link Building helps your site indexing in Search Engines (Like Google, Yahoo MSN, Bing) » Get theme based one way links along with directory submissions and social book marking » Link Builder can also work on simple data entry projects as per client's requirements Benefits of Our Expertise: 1. Links with relevant Keywords in the Anchor Text 2. Links from industry-relevant pages. 3. Links from industry specific article pages 4. Link to your site should not be through a redirect script 5. No JavaScript links 6. No links from framed pages 7. No flash embedded links 8. No paid or time-bound links 9 .No links from Link Farms Kind Regards ! Chandni Singh ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Locating wav files for voice_kal_diphone
Hi Nikolay, Thanks for the clarification. I have re-read the documentation and the following is my understanding: 1. In case a word is found in the lexicon, use the phonetic transcription of the same and synthesize the voice from the lpc coefficients and residuals. 2. In case the word is not found, use the lts_rules to predict its pronunciation and then synthesize as above. 3. The lpc coefficients are stored in the group files in each voice directory. There are ofcourse, a number of intermediate steps such as f0 contour or prosody etc., but I have omitted that. Please correct me if my understanding is incorrect. Thanks, Sriram On Thu, Dec 1, 2011 at 2:47 AM, Nickolay V. Shmyrev nshmy...@yandex.ruwrote: Hello You can download kal_diphone voice database source here http://festvox.org/dbs/dbs_kal.html Also you might want to understand how diphone voice is built. Your out-of-vocab doesn't have much sense for diphone voices. On Wed, Nov 30, 2011 at 2:55 PM, Sriram Shankar sri...@voxomos.com wrote: Hi, I am trying to add some wav files (in my voice) to try and synthesize some words that are currently out-of-vocab for voice_kal_diphone. I am not able to figure out the directory where these wav files may be stored. I have executed system-wide searches and still not found anything. Any help in figuring out where the wav files for voice_kal_diphone are stored would be most welcome. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[no subject]
message from Josaf?Pontes jeho...@yahoo.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = http://www.escirecursos.org/trial.html?odvy = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: Site hack / malware warning Re: [festival-talk] Call for participation in the Eighth Blizzard Challenge - 2012
message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = On 4 Dec 2011, at 20:59, Jonathan Horniblow (Talking Newspaper Services) wrote: Some of you have probably discovered this already, but sadly this site appears to have been hacked. I can't reproduce this error with any browser and can't find any injected javascript in any pages on the synsig site. Jonathan - please can you mail me individually with the URL that's causing you the error and perhaps also mail the page source you get as an attachment and a screenshot from http://jsunpack.jeek.org/?. many thanks, Simon -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] InterSpeech 2012 deadlines approaching
INTERSPEECH 2012 SUBMISSION DEADLINES APPROACHING CALL FOR SATELLITE WORKSHOPS Submission Deadline: Saturday, December 10, 2011 Interested in hosting a satellite workshop in conjunction with InterSpeech 2012? Click herehttp://interspeech2012.org/Satellite-Workshops.html for more information on the workshop guidelines and application process. CALL FOR TUTORIALS Submission Deadline: Saturday, December 10, 2011 Proposals covering interdisciplinary topics and/or important new emerging areas of interest related to the main conference topics are encouraged. Visit the tutorials pagehttp://interspeech2012.org/Tutorials.html of the conference website for more information and to submit a tutorial proposal. CALL FOR SPECIAL SESSIONS Submission Deadline: Monday, January 16, 2012 Special sessions are an opportunity to bring researchers in relevant fields of interest outside the traditional speech and language fields, together with the InterSpeech community. Click herehttp://interspeech2012.org/SpecialSessions.html to learn more about the updated 2012 special session submission process. 2012 CONFERENCE VENUE The Conference will be held at the Hilton Portland Executive Tower in downtown Portland, Oregon. Click herehttp://interspeech2012.org/venue.html?menu_id=7 to check out what the Hilton is doing to go green. PAPER SUBMISSIONS AND REGISTRATION INFORMATION Conference registration and the Call for Papers will open in February, 2012. Visit the Conference website to keep informed of the latest developments. SPONSORSHIP AND EXHIBIT OPPORTUNITES Want to increase your visibility and access a market of over 800 conference attendees? Apply onlinehttp://interspeech2012.org/sponsorship-opportunities.html to become a sponsor or exhibitor of the 2012 Conference. Benefits are based on contribution and are on a first-come, first-serve basis. Don’t miss out on this incredible opportunity. View the sponsorship and exhibitor brochure today!http://interspeech2012.org/sponsorship-brochure.html Esther Klabbers and Richard Sproat Center for Spoken Language Understanding Department of Biomedical Engineering, OHSU ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: new limited domain voice question re: phoneset etc
On 29/11/2011 at 21:02 -0500, Dahlia Thompson wrote: Hi Everyone, Thanks in advance for your patience your response(s) Hello I am working on creating a new limited domain voice (not time) in a new language. I have installed and compiled Festival, Festvox and Speech Tools. I have sent the necessary environment variables, set up my directory structure, created my prompt list etc. The default voice is currently set to kal_diphone. * How do I get Festival to access the a) phone set (phoneme inventory), b ) lexicon and c) lts rule set for my language? I do not wish to use the English phoneset for annotation as the phone sets are not similar: Describe everything for your target voice in corresponding scheme files using required format. Put those files in the ldom voice folder. Load them with (require). Select them with (lex.select) and analogs. * Do I need to modify the current radio_phone.scm and cmu_lex files to reflect my language or should I just add my own files somewhere and if so where? Inside the festival/lib directory or inside the festvox directory or ...? It's better to avoid modifying files from the distribution. You can just put files in voice scm folder. I have tried adding my own files but the system does not recognise them. For example, when I build my prompts and examine the utterance files, I see that my phoneset is not being used.. Where should I put my phoneset (file) to ensure once I run festival -b festvox/build_ldom.scm '(build_prompts etc/myutterancelist), the system uses the phoneme inventory for my language and not English? You need to load file with (require). You need to select lexicon with (lex.select). You can find some examples of this in other voices. You need to do all those actions inside (voice_INST_LDOM_VOX_ldom) function. signature.asc Description: This is a digitally signed message part ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Festival Emotions with SABLE in Spanish
Well, finally I fixed. The problem was that the speaker wasn't changed propperly. Although the language was selected, I added an extra cond in sable-mode.scm to set the speaker. Regards, O. 2011/11/17 10:01(e)an, Oier Fuentes Mendizabal(e)k idatzi zuen: Dear team, I just found a reference to language in sable-mode.scm: ;; Select a new language (let ((language (upcase (car (xxml_attval ID ATTLIST) (cond ((or (string-equal language SPANISH) (string-equal language ES)) (set! sable_current_language 'spanish) (set! sable_unsupported_language nil) (select_language 'spanish)) ((or (string-equal language ENGLISH) (string-equal language EN)) (set! sable_current_language 'britishenglish) (set! sable_unsupported_language nil) (select_language 'britishenglish)) (t ;; skip languages you don't know ;; BUG: if current language isn't English this wont work Do I need to change something there? Where can I find some more info? I searched in this mailing list, Festival tutorial, Sable spec. but no way. Many thanks and regards, Oier ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Hello,
Hello, My Name is lilina I am .I will be happy if you can reply me because i have something to discuss with you and also send my pictures to you ok Thanks yours, from lilina __ שלום, שמי lilina אני. אשמח אם תוכל לענות לי כי יש לי משהו לדבר איתך גם לשלוח תמונות שלי אליך בסדר תודה שלך ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: Problem in making group file for a new voice
Did you load your voice first using : festival festvox/cmu_us_awb_diphone.scm '(voice_cmu_us_awb_diphone)' and make sure it was working? 2011/8/11 Cherrot cherrot...@gmail.com I followed the tutorial to build a new English diphone voice. When I tried making a group file using us_make_group_file function in festival: (us_make_group_file “group/mattlpc.group” nil) OR, (us_make_group_file /home/cherrot/ru_us_matt_diphone/group/mattlpc.group '(track_file_format est_binary) '(sig_file_format snd) '(sig_sample_format mulaw)) I got the following error: -=-=-=-=-=- EST Error -=-=-=-=-=- US DB: no diphone database loaded -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- Is there something wrong? Where could I find the source code of this function? Or could I make this group file manually? Any help will be appreciated. Thanks in advance! -- Cherrot http://Cherrot.com -- Heather Dewey-Hagborg www.deweyhagborg.com 518-598-3775 ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Problem in making group file for a new voice
I followed the tutorial to build a new English diphone voice. When I tried making a group file using us_make_group_file function in festival: (us_make_group_file “group/mattlpc.group” nil) OR, (us_make_group_file /home/cherrot/ru_us_matt_diphone/group/mattlpc.group '(track_file_format est_binary) '(sig_file_format snd) '(sig_sample_format mulaw)) I got the following error: -=-=-=-=-=- EST Error -=-=-=-=-=- US DB: no diphone database loaded -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- Is there something wrong? Where could I find the source code of this function? Or could I make this group file manually? Any help will be appreciated. Thanks in advance! -- Cherrot http://Cherrot.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Problem in bsv with bin/make_pm_fix pm/*.pm
Hi friends, I want to build a new voice using Festvox 2.1 for Festival. So I followed the instructions of the bsv manual (and many other documents) to do this job. When I executed the following command: bin/make_pm_fix pm/*.pm I just got the error: awk: cmd. line:1: fatal: cannot open file `etc/txt.done.data' for reading (No such file or directory) I noticed that my pm/ directory is empty. should I generate pitchmark files first? How to? Till now I have waveform files I have recorded and label files. Any help will be appreciated. Thanks in advance! P.S. The following is what I've done till now, hope helpful: mkdir ~/ru_us_matt_diphone cd ~/ru_us_matt)diphone $FESTVOXDIR/src/diphones/setup_diphone ru us matt festival -b festvox/diphlist.scm festvox/us_schema.scm '(diphone-gen-schema us etc/usdiph.list)' festival -b festvox/diphlist.scm festvox/us_schema.scm '(diphone-gen-waves prompt-wav prompt-lab etc/usdiph.list)' (generate prompts) bin/prompt_them etc/usdiph.list (record them) padsp bin/prompt_them etc/usdiph.list (generate labels) bin/make_labs prompt-wav/*.wav mkdir dic (generate indexes) bin/make_diph_index etc/usdiph.list dic/mattdiph.est (extract pitchmarks) bin/make_pm_wave etc/usdiph.list (then error) bin/make_pm_fix pm/*.pm Best regards, -- Cherrot http://Cherrot.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] The telephone channel simulation tool
message from Simon King simon.k...@ed.ac.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = On 28 Jul 2011, at 05:22, Trần Minh Trường wrote: Does any one know about the source code for the telephone channel simulation tool is available for download ? For Blizzard 2009, we used a tool from the ITU. It can be configured in many different ways. See the summary paper (King Karaiskos) from http://festvox.org/blizzard/blizzard2009.html for details Simon -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] The telephone channel simulation tool
Hi, all Does any one know about the source code for the telephone channel simulation tool is available for download ? Can you help me ! Thanks and Best regards ! -- ~ TRUONG MINH, AILab, University of Science, VNU-HCM, VIETNAM Email: minhtruon...@gmail.com ~ ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Invitation for registration for Interspeech2011 Student event
message from =?gbk?B?xMfQy9Pu?= nxy-y...@163.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Dear Student, One of the biggest yearly event in the speech community is approaching - Interspeech 2011 is in less than 2 months. Once you have decided to come to Florence, it is great to use all the opportunities a conference of this level has to offer! ISCA Student Advisory Committee is happy to announce that this year, thanks to the generous support of the Interspeech 2011 Organizing Committee and ISCA Board, we are organizing a special event for students that gives you the possibility to get in touch with prominent researchers in your area and discuss your interest and research with people whose work is well-known, established and inspiring to all of us! This event will be accompanied with Italian delicacies as well. This event is a great opportunity and an informal setting to meet peer researchers and experts in your field. We are very happy to announce the list of researchers attending the event will include: Prof. Abeer Alwan, UCLA Prof. Gerard Bailly, GIPSA. Prof. Peter Birkholz, RWTH Aachen Prof. Alan Black, CMU. Prof. Nick Campbell, UCD, Dublin Prof. Hynek Hermansky, John Hopkins. Prof. Julia Hirchberg, Columbia, NY. Prof. Tokuda Keiichi, NIT, Nagoya Prof. Helen Meng, Hong Kong Prof. John Ohala, Berkeley Prof. Elizabeth Shriberg, Microsoft Prof. Steve Young, Cambridge and more… The Interspeech 2011 Student Roundtable Lunch Discussion will take place on the second day of Interspeech, Monday, August 29th, from 12:00 to 13:30, on the first floor of the “Pala Affari” building. The number of tables and places is limited so hurry and sign up as soon as possible. To do so please click on the link - http://isca-students.org/?q=is2011event. After the registration, students will be grouped in tables of 10 depending on their research interest, and accompanied by an Italian host researcher and an international researcher. A light lunch buffet will be provided. We look forward to welcoming you to Florence in August, 2011! Best regards, ISCA Student Advisory Committee = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] HMM-Based Speech Synthesis System HTS-2.2
message from Keiichiro Oura ura...@sp.nitech.ac.jp to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = We are please to inform you the release of The HMM-based Speech Synthesis System (HTS) version 2.2 release July 7, 2011 for HMM-based speech synthesis. We apologize if you receive multiple copies. Please check http://hts.sp.nitech.ac.jp/ We would appreciate it if you would distribute this email to anyone who would be interested in this software toolkit. Best regards, Keiichi Tokuda in behalf of HTS Working Group tok...@nitech.ac.jp http://www.sp.nitech.ac.jp/~tokuda/ = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: how pitchmarks are used
Heather Dewey-Hagborg wrote: Could anyone point me toward a brief explanation of how pitchmarks are used in diphone synthesis? I am continuing to tweak my festvox generated voice and am trying to figure out how important the pitchmarks are ie. if I should try to really tweak them to the point of editing by hand etc. The are pretty important. They are used to define join points and to define the pitch of the diphone (to know how much it has to be varied to the target). Extracting good pitch marks is hard. For some voices it works well and for others it does not. Four our system, the pitch marks must align with the largest peaks in the signal (in voiced regions). There a parameters that you can tune in bin/make_pm_wave, but I have to admit even I find them to be somewhat magic. The key ones are -min and -max though. There is some discussion here http://www.festvox.org/bsv/x862.html Alan Thanks, Heather ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Not acting right in Fedora 15
message from Kev 'Kyrian' Green (List) kyrian-l...@ore.org to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = audsp: unknown command closee This is highly odd, and this seems likely to be the reason for the festival process not ending, it might explain the issue in and of itself without other factors. It might be worth checking what file type the 'audsp' program is, and running a diff on it between the FC14 and FC15 versions to see what, if anything, has changed between times. Have you tried putting the text you want to output into a temporary file, and then sending the contents of the temporary file to festival instead? Isn't there a command line switch to do that (get festival to dictate from a file)? And a nagios environment variable for its own temp directory you can use for that? K. -- Kev Kyrian Green.WWW: http://kyrian.ore.org/ Linux Security + Hosting + Admin/LAMP Coder @ http://www.orenet.co.uk/ When I spit in the eye of the gods, then I will smile = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Build the homograph disambiguation
Dear all: I have tried to implement the Japanese diphone voice, follow here: http://festvox.org/bsv/c3456.html Now I am confused to built homograph disambiguation, e.g. one word will have two different pronunciations in different situation. How can I implement it ? Which files I need to edit? Since I can't found the resource on the Festival documentation. Thanks, Vincent ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: can't find diphone pau-hh
FYI the problem was that my dic file was named incorrectly. For future reference make sure when you run bin/make_diph_index you name dic/NAME_HERE.est the same as the name of the speaker you chose for your voice. ie. my speaker name is jaaga. my voice is net_us_jaaga_diphone so when I run the index command i have to say: bin/make_diph_index etc/usdiph.list dic/jaagadiph.est On Wed, Jun 15, 2011 at 11:21 PM, Heather Dewey-Hagborg heat...@deweyhagborg.com wrote: So I have been attempting to build a custom voice with festvox and I finally made it through all the steps but have hit an error in bringing it into festival: US DB: can't find diphone pau-hh and even default diphone (pau-pau) doesn't exist Does anyone know what this error is about or how to remedy it? Thanks! Heather -- Heather Dewey-Hagborg www.deweyhagborg.com 518-598-3775 -- Heather Dewey-Hagborg www.deweyhagborg.com 518-598-3775 ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Building a voice for South African language
message from Mhlana, Siphe 200600...@ufh.ac.za to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Hello I am build a Text-To-Speech system for isiXhosa language. I am using festival speech synthesis to build this voice. But now im experiencing some problems. I recorded my own voice but the problem is now, it is not using the voice i recorded is using someone voice which is different to mine. any help please. Department of Computer Science University of Fort Hare Name :Siphe Mhlana E-mail: siphe_mhl...@yahoo.com / smhl...@ufh.ac.za Cell: 0764645079/0738689582 The University of Fort Hare subscribes to an e-mail disclaimer. Please click on the following URL to read further: http://www.ufh.ac.za/disclaimer/ = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Issues Building Festival from scratch on Linux
message from Alfonso Arbona Gimeno nak...@terra.es to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = That's something that is bothering me for a while. Why does make install not move the files to /bin? If I build from /home/myuser/festival, then I have to add it to the PATH in order to use it, and it's not usable for all the users. Even if I do make install as root. Also, are binaries hard-linked in any way to the place I compiled them? Is it possible to move the shared files and the binaries from the build folder to another folder with mv and delete the folder I used to build the program? And the same questions for speech-tools. Thanks in advance, Alfonso Arbona El 16/06/2011 13:36, Jon Spriggs escribió: message from Jon Spriggs j...@sprig.gs to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = That worked like a dream Rob, thanks! I went with 4.1.3. I need to figure out why the make install isn't moving the files into the path specified in the ./configure... but I'm sure I'll get there eventually :) For now, it works, which is great :D Regards, -- Jon The Nice Guy Spriggs On 16 June 2011 11:29, Rob Clark rob...@cstr.ed.ac.uk wrote: I've seen this before with Debian and gcc-4.3.2 (and managed to reproduce it at the time) The compiler was failing to find a match for the EST_String split function in 2 places. I really couldn't see why it couldn't find a suitable match though and assumed it was something to do with gcc-4.3.2 or the Debian install of it. (We tested the last Festival release with gcc-4.3.4 on other platforms without issue.) The only fix I could suggest was to use gcc-4.2 on debian This is installed with: apt-get install libncurses5-dev gcc-4.2 g++-4.2 You could see if gcc-4.2 is already installed on your hosting machine, and if it is, add the following to the bottom of speech_tools/config/config CXX = g++-4.2 CC = gcc-4.2 Compiling a statically linked Festival binary (the default) on a alternate Debian install and then running on the remote host may work. Regards, Rob Clark On Thu, Jun 16, 2011 at 10:44 AM, Jon Spriggs j...@sprig.gs wrote: message from Jon Spriggs j...@sprig.gs to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = On 15 June 2011 22:25, Alan W Black a...@cs.cmu.edu wrote: Jon Spriggs wrote: message from Jon Spriggs j...@sprig.gs to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = I'm using Festival (text2wave) to create audio bumpers for a podcast I'm creating dynamically in code each day. Because of some issues I hit with building it very early on, I decided to SSH out from my web host to my home computer each day to build the bumpers, until I had a chance to look into why I've had problems. Today is that day! I'm building it on shared hosting (dreamhost, if you're interested), so there's no chance to sudo make install or anything like that, nor can I use pre-packaged packages. Can you tell me what version of gcc you have gcc -v Its failing to compile the speech tools (so nothing will work after that). This might be because your host has a newer version of gcc (or an older one). Alan $ gcc -v Using built-in specs. Target: x86_64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Debian 4.3.2-1.1' --with-bugurl=file:///usr/share/doc/gcc-4.3/README.Bugs --enable-languages=c,c++,fortran,objc,obj-c++ --prefix=/usr --enable-shared --with-system-zlib --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --enable-nls --with-gxx-include-dir=/usr/include/c++/4.3 --program-suffix=-4.3 --enable-clocale=gnu --enable-libstdcxx-debug --enable-objc-gc --enable-mpfr --enable-cld --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu Thread model: posix gcc version 4.3.2 (Debian 4.3.2-1.1) $ -- Jon The Nice Guy Spriggs = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = -- Rob Clark = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = - No se encontraron virus en este mensaje. Comprobado por AVG - www.avg.com Versión: 10.0.1382 / Base de datos de virus: 1513/3706 - Fecha de publicación: 06/15/11 - No se encontraron
Re: [festival-talk] Issues Building Festival from scratch on Linux
message from Jonathan Horniblow (Talking Newspaper Services) jonat...@talking-newspapers.co.uk to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = On 15 June 2011 21:54, Jon Spriggs j...@sprig.gs wrote: message from Jon Spriggs j...@sprig.gs to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = I'm building it on shared hosting (dreamhost, if you're interested), so there's no chance to sudo make install or anything like that, nor can I use pre-packaged packages. Which begs the question - are you aware of the Amazon EC2 free tier? Your own vps micro instance with 613 MB RAM, a choice of several virtual machines, ssh etc... do what the hell you like with it. Full root access is yours. I'm running Festival just fine, as well as 4 sites. I've built several things, I'm running apache+nginx+varnish. If it works, save it, if it doesn't, blow it away and start again. No charged. Gratis for a year. Had it 2 months now, no downtime, more than happy for free! Worth a shot - BUT... documentation from Amazon is sparse and you'll need to spend a few hours figuring things out. Hunt around for recent guides. http://aws.amazon.com/free/ 750 hours of Amazon EC2 Linux Micro Instance usage (613 MB of memory and 32-bit and 64-bit platform support) – enough hours to run continuously each month* 750 hours of an Elastic Load Balancer plus 15 GB data processing* 10 GB of Amazon Elastic Block Storage, plus 1 million I/Os, 1 GB of snapshot storage, 10,000 snapshot Get Requests and 1,000 snapshot Put Requests* 5 GB of Amazon S3 standard storage, 20,000 Get Requests, and 2,000 Put Requests* 30 GB per of internet data transfer (15 GB of data transfer “in” and 15 GB of data transfer “out” across all services except Amazon CloudFront)* 25 Amazon SimpleDB Machine Hours and 1 GB of Storage** 100,000 Requests of Amazon Simple Queue Service** 100,000 Requests, 100,000 HTTP notifications and 1,000 email notifications for Amazon Simple Notification Service** 10 Amazon Cloudwatch metrics, 10 alarms, and 1,000,000 API requests** In addition to these services, the AWS Management Console is available at no charge to help you build and manage your application on AWS. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
can't find diphone pau-hh
So I have been attempting to build a custom voice with festvox and I finally made it through all the steps but have hit an error in bringing it into festival: US DB: can't find diphone pau-hh and even default diphone (pau-pau) doesn't exist Does anyone know what this error is about or how to remedy it? Thanks! Heather -- Heather Dewey-Hagborg www.deweyhagborg.com 518-598-3775 ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] SayText exist to shell prompt after execution
message from Lewis Pike phaseloc...@gmail.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = I'm new to festival and have been playing around with the SayText command in festival's interactive mode. I've run into an annoying problem where festival exits to the shell after the SayText command is issued and the sound is played back. Is this usual behavior for an interactive session? Is there was way that I can remain in interactive mode instead of festival terminating? I'm running festival 2.1 under linux kernel 2.6.38 and have compiled from source, although I've noticed the same behaviour from my distro's prepackaged festival binary. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
SEO Proposal
Dear Sir \ Madam, We are India based SEO offpage competency in Quality Link Building, Affordable Web Submission, Search Engine Maximization (SEM), Effective SMO (Social Media Optimization), Online Brand Reputation Management; working as an outsourced vendor for many SEO agency throughout the globe. We have a highly experienced and dedicated team of professionals to serve you. We offer our services at up to 1/3 or your local prices for SEO agencies to maintain mutual profitability. We always adopt the Ethical process/White hat technique; also follow the guidelines of Google and major search engine for SEO result. We strictly work on performance basis and can assure you of getting quality work for your site as well. Our off page seo service will help to increase visibility and popularity of your client's website. We follow a Agency Client Oriented Approach in our process, as sign-up the NDAs( Non-Disclosure Agreement), effective online project management tracking tools, timely and smooth communication etc. We are looking forward starting a long and healthy business relationship with you. We will be happy to AMAZE you with our work. I will really appreciate you please let me know your requirement. Kind Regards, Ajay Kumar ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[festival-talk] Problem with sable
message from Michael A. Peters mpet...@shastaherps.org to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Festival Speech Synthesis System: 1.96:beta July 2004 Operating System: Ubuntu 9.10 (karmic) 64 bit What I'm trying: festival --tts test.sable When test.sable contains the following: ?xml version=1.0? !DOCTYPE SABLE PUBLIC -//SABLE//DTD SABLE speech mark up//EN Sable.v0_2.dtd SABLESPEAKER NAME=male1PRON SUB=hellofoo/PRON BREAK/ PRON SUB=worldbar/PRON/SPEAKER/SABLE I only get the hello Not what I expect. But when it contains ?xml version=1.0? !DOCTYPE SABLE PUBLIC -//SABLE//DTD SABLE speech mark up//EN Sable.v0_2.dtd SABLESPEAKER NAME=male1PRON SUB=hellofoo/PRON um BREAK/ PRON SUB=worldbar/PRON/SPEAKER/SABLE I get what I expect, hello um world Is this a bug in festival or is it lack of understanding the sable format on my part? Thanks for suggestions. = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =University of Edinburgh's Festival Speech Synthesis System = = http://festvox.org/festival Sent Via festival-t...@festvox.org = = To unsubscribe mail majord...@festvox.org = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Festvox Installation Problem
I am having the same issue as described in this thread: http://lists.berlios.de/pipermail/festlang-talk/2011-April/002579.html Phonealign_main.cc does not compile due to a missing next() declaration. Hasitha, can you describe how you fixed the problem with your installation? Or Rob, can you tell me where to find the patch you mentioned? festvox_speech_tools2.1.patch * * Thanks, Heather ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Problem in running the festival_client.c
Hi All, I am working with the festival_client.c (/festival/examples/festival_client.c) , I successfully compiled it using gcc -o festival_client -DSTANDALONE festival_client.c however when I try to run it using festival_client -text hello there -o hello.snd , it gives an error. Error Log: dilum@dilum-:~/Festival/festival/examples$ festival_client -text hello there -o hello.snd festival_client: Unknown option -text Can any one help regarding this issue, am I trying with the correct run command? Thanks in advance. Thanks and Regards, Dilum Vithana. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: issue with prompt_them script
Thanks everyone for help. I ended up modifying the prompt_them script. For the moment I replaces na_play with a call to the sox library: play and na_record with another call to sox: rec wav/$f.wav trim 0 $duration I will next try to modify it so it uses user interactivity ie. record until the user presses a key. Thanks again! Heather On Sun, May 29, 2011 at 12:15 PM, Jeremy Salwen jeremysal...@gmail.comwrote: The source code for the script is the script itself! If you open it up, you will see it is using na_record to record your prompts. If you change it to the appropriate sound recording tool for OSX, it will work. Also, I would suggest using pointyclicky instead of prompt_them for recording prompts. It's a GUI which exposes much more options without having to modify the source (including which command to use to record sound). To quote from my blog There are references scattered throughout the festvox documentation to a GUI program for recording speech prompts, called pointyclicky. Sounds nice, right? Well, if you try to find the sources, you find that it was last updated in 2000 (!), and it's in disrepair. (http://festvox.org/pointyclicky/) It won't compile any more, but Kev 'Kyrian' Green at the redhat bugzilla patched it up so it's closer to compiling. I also made some more changes so it would work for me on Debian, but I don't remember exactly what I did. Anyway, you can download my patched version of the sources from herehttp://columbia.edu/%7Ejas2312/pointyclicky.tgz . You might need to install a few libraries to get it working, although they might be pre-installed in OSX. Jeremy Salwen On Sun, May 29, 2011 at 2:05 AM, Heather Dewey-Hagborg heat...@deweyhagborg.com wrote: Hello, I am trying to run festvox on a Mac OS10.5 laptop. So far have been successful mostly installing and running festival and early festvox scripts but when I run prompt_them I get : start recording for 2 seconds ... SUN16: can't open /dev/audio for reading ... end recording Not surprising as the scripts were written for Linux. Could anyone point me to the source code for this script so I can hopefully tweak it for the mac? Thanks! Heather ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk -- Heather Dewey-Hagborg www.deweyhagborg.com 518-598-3775 ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
[ wdvimxtmxc84bbni] : mental health counselors marketing email list
Value priced Data: $395 for everything below! (only until Friday) All 100% optin data / Full resale rights ---HEALTHCARE LISTS Physicians (34 specialties) Database:788k records, 17k emails, 200k fax numbers Chiropractors Database:108,421 total records * 3,414 emails * 6,553 fax numbers Alternative Medicine Database:1,141,602 total records with 36,320 emails and 38.935 fax numbers Dentists Database:164k records, 45k emails, 77k fax numbers Dentists with Specialties Database:30k records all with emails Veterinarians Database:78,986 total records with 1,438 emails and 1,050 fax numbers Hospitals Database:10,661 Emails for hospitals in the USA Nursing Homes Database:31,589 Senior Administrators, 11,288 Nursing Directors in over 14,706 Nursing Homes (full contact info no emails) Pharmaceutical Companies Database:47,000 emails of pharma company employees Physical Therapists Database:125,460 total records with 5,483 emails and 4,405 fax numbers Oncology Doctors Database:2,200 records all with emails US Surgery Centers Database:85k records and 14k emails Acupuncturists Database:23,988 records 1,826 emails Massage Therapists Database:76,701 records and 8,305 emails Medical Equipment Suppliers Database:67,425 total records with 6,940 emails and 5,812 fax numbers Mental Health Counselors Database:283,184 records 7,206 emails Visiting Nurses RN's Database:91,386 total records with 2,788 emails and 2,390 fax numbers Optometrists Database:63,837 records 2,015 emails Psychologists Database:272,188 records and 9,874 emails Healthcare Recruiters Database:11,370 emails for active healthcare recruiters in the USA Plastic Surgeons Database:23,109 emails with full data ---BUSINESS LISTS Hotels in the USA Database: 63,260 emails Schools in the USA Database: 439,797 emails for Schools, Universities and Colleges in the USA. Churches in the USA Database: 169,377 emails for Churches of all denominations in the USA Architects in the USA Database: 9,790 emails in total Real Estate Land Developers Database: 10,837 emails in total Construction Development Database: 94,272 emails Criminal Attorneys Database:142,906 total records, 99,857 emails Real Estate Agents Database: 2.4 Million Email Database (2 lists) Police and Sheriff Services Database:42,987 records and 114 emails USA Business Database Database: 10 Million Emails for US businesses in various categories (3 lists) Manufacturers Database Database:1,057,119 records with 476,509 emails USA Lawyers Database Database:269,787 records with 235,244 emails Financial Planners Database Database:148,857 records all with emails Finance and Money Professionals Database Database:116,568 records all with emails Insurance Agents Database: 61,744 emails for Insurance companies in the USA (2 files) Media Outlet Contacts Database:over 200k records all with emails and full contact data VARs and IT Consultants Database:12,000 VAR and IT consultant Emails in the USA ---FOREIGN BUSINESS LISTS Canadian Businesses Database:500,000 records for Canadian businesses all with emails United Kingdom Business Database Database:400,000 records all with emails for businesses in the United Kingdom India Business Database Database: 1 Million Email Database for businesses in India ---CONSUMER LISTS Credit Inquiries Database Database:1 million Full Data Records all with emails American Homeowners Database:1 million Full Data Records all with emails American Consumer Database Database:2,400,000 records all with emails. Take all lists above for only $395 until Friday Email me for sample excel spreadsheets: williamb.a-cunning...@gmx.com this is where to go to stop the mailing please email takeit...@gmx.com ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Segmentation fault while using Sable (New)
Hi, all Recently I have built festival 2.1 on my Ubuntu 11.04. Unfortunately, when I tried using Sable files to synthesize speech, I encountered segmentation fault and the festival was forced to quit: festival (tts_file ./example.sable 'sable) Segmentation fault. /opt/festival/festival$ I notice that I have not included 'rxp' in my config file in /festival/config/. However, when I tried to include 'rxp' by adding ALSO_INCLUDE += rxp in my config file, after execute make test, the output seems that my compilation had been failed: http://pastebin.com/x64peuW9 The main part of the error I guess is: SIOD: duplicate builtin function: tts_file_xml SIOD: probably an error SIOD: duplicate builtin function: xml_register_id SIOD: probably an error SIOD: duplicate builtin function: xml_registered_ids SIOD: probably an error Further more, if I run /opt/festival/festival$ text2wave ./examples/example.sable -o 111.wav I will get the following output: Cannot load wavefile: /tmp/est_20761_1 festival: text modes, caught error and tidying up And the 111.wav only contains the first sentence of the sable file(e.g. My telephone number is.) How could I get Sable work on my Festival ? Thank in advance. Best regards, Cherrot ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: [festival-talk] Linux: can't open /dev/dsp
/Try using 'padsp festival' instead of just 'festival' when running it, because you may need to use that wrapper for /dev/dsp to exist in that context./ It works! Thank you indeed! And I have found another solution on https://wiki.archlinux.org/index.php/Festival /Switch to ALSA output by adding these lines to the end of your .festivalrc file, or to /usr/share/festival/festival.scm : / /(Parameter.set 'Audio_Method 'Audio_Command) (Parameter.set 'Audio_Command aplay -q -c 1 -t raw -f s16 -r $SR $FILE) / It also works for me. /I guess if there were enough interest I could clean the notes up into a HOWTO to save other people this kind of pain?/ Of course there are. And I'm looking forward it :-) Cherrot wrote: message from Cherrot carrot0...@gmail.com to festival-talk = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = Recently I have successfully build the Festival 2.1, but it just can't make a sound! festival (SayText Hello World) Linux: can't open /dev/dsp #Utterance 0xb6908248 Check the ownership on /dev/dsp, and if appropriate make sure your user is in the right group to have write access to it. How could I solve this problem? Can't festival 2.1 use pulseAudio ALSA as its audio output device? Try using 'padsp festival' instead of just 'festival' when running it, because you may need to use that wrapper for /dev/dsp to exist in that context. / Also, see if you have got the package for the alsa pulseaudio plugin installed. It possibly comes in the 'pulseaudio-alsa' package. I use Fedora, rather than Ubuntu so I can't be certain. Hope that helps. Good luck. Trying to get festival working when your distribution doesn't natively use the right sound server is a major pain in the behind. I've got page after page of notes on it having had to find out the hard way :-/ / I guess if there were enough interest I could clean the notes up into a HOWTO to save other people this kind of pain? K. ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
Re: Linux: can't open /dev/dsp
Perhaps you need to set the sound output options? http://www.cstr.ed.ac.uk/projects/festival/manual/festival_23.html Jeremy On Sat, May 28, 2011 at 4:56 AM, Cherrot ad...@cherrot.com wrote: Recently I have successfully build the Festival 2.1, but it just can't make a sound! festival (SayText Hello World) Linux: can't open /dev/dsp #Utterance 0xb6908248 However, if I install the festival 2.0.95 .deb package via apt-get install festival , it will work very well. How could I solve this problem? Can't festival 2.1 use pulseAudio ALSA as its audio output device? Best regards, Cherrot Luo P.S. My OS is Ubuntu 11.04 (natty) ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk ___ Festlang-talk mailing list Festlang-talk@lists.berlios.de https://lists.berlios.de/mailman/listinfo/festlang-talk
