Yes, actually I have try record the sound by 11025Hz, but the output is still not good... You said that I can modify the extraction parameter, which file can I modify in Festival? Actually I am editing the parameter in bin/make_pm_wave. Finally, except modify this file, which files or steps can we do to improve the output quality?
Thanks and regards Vincent 2012/2/17 Nickolay V. Shmyrev <[email protected]> > On 17/02/2012 at 11:41 +0800, Siu Meng Lei wrote: > > Thank you for you suggestion. > > And also I have one more question, after I follow the step, I found > > that the final output quality is but. > > It mentions that Getting good pitchmarks is important to the quality > > of the synthesis, and I review the information in this web site: > > http://festvox.org/bsv/x862.html, and compare my .pm file, the graph > > is very different, see here http://i43.tinypic.com/28i450h.png, > > there are many red lines, and I open my .pm file, the content is sth > > like that: > > > > > > EST_File Track > > DataType ascii > > NumFrames 466 > > NumChannels 0 > > NumAuxChanels 0 > > BreaksPresent true > > file_type 14 > > EST_Header_End > > 0.010042 1 > > 0.020083 1 > > 0.030125 1 > > 0.040188 1 > > 0.050229 1 > > 0.060271 1 > > ...... > > ...... > > > > > > Is my .ps file correct? Since there are too many pitch mark..... if > > not correct, how can I fix it? > > Actually I have edit the script bin/make_pm_wave, but the output is > > still bad. > > Pitchmarks are good > > Graph use different because you only added spectrum pane, not waveform > pane. You can add waveform pane with the right click > > Your spectrum shows that your speech is not properly recorded. It's not > 16khz but 11khz original. You will not be able to build a voice from it > flawlessly unless you will modify the extraction parameters. > > >
_______________________________________________ Festlang-talk mailing list [email protected] https://lists.berlios.de/mailman/listinfo/festlang-talk
