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, <[email protected]>wrote:
> Send Festlang-talk mailing list submissions to
> [email protected]
>
> 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
> [email protected]
>
> You can reach the person managing the list at
> [email protected]
>
> 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 <[email protected]>
> To: [email protected], [email protected],
> [email protected]
> Subject: [festival-talk] Job: Research Fellow in speech synthesis,
> CSTR, University of Edinburgh, UK
> Message-ID: <[email protected]>
> Content-Type: text/plain; charset=us-ascii
>
> message from Simon King <[email protected]> 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 <[email protected]> or Dr
> Catherine Mayo <[email protected]>
>
> 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 [email protected] =
> = To unsubscribe mail [email protected] =
> = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
>
>
>
> ------------------------------
>
> _______________________________________________
> Festlang-talk mailing list
> [email protected]
> https://lists.berlios.de/mailman/listinfo/festlang-talk
>
> End of Festlang-talk Digest, Vol 76, Issue 12
> *********************************************
>
_______________________________________________
Festlang-talk mailing list
[email protected]
https://lists.berlios.de/mailman/listinfo/festlang-talk
