[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:02026] Re: Fwd: Re: Poor voice quality & embedded reestimation (monophone) errors


Hi

Check if pause/silence regions are mostly composed of samples of amplitude zero in your training utterances. If so, replace them by white noise and re-calculate mgc.

Ranniery


On Tue, 16 Jun 2009, Tomasz Kuczmarski wrote:

Yes, the whole process passed in one go uninterrupted.

Please find some samples attached.

I can send some samples of the same utterances synthesized by Festival
clunits voice built on the exact same database of speech for comparison if
needed.



2009/6/16 Xavi Gonzalvo <xavi.gonzalvo@xxxxxxxxx>

Did you do the train in one go?

Can we listen to any sample?

Try to train a voice with 100 files, it usually helps to see any errors.
100 files are usually enough to have some samples for each phone and it
should sound something intelligible.

Regards


2009/6/16 Tomasz Kuczmarski <faqster@xxxxxxxxx>

They seem fine. I used the same limits for pitchmark extraction while
building a clunits voice for Festival. At that time, PDA has successfully
found pitch periods.

2009/6/16 T$Bs(Bth B$Ba(Blint <toth.b@xxxxxxxxxxx>

Sorry for the basic question, but are the low and high limits of f0
extraction set fine?

Best Regards,
B$Ba(Blint T$Bs(Bth

Tomasz Kuczmarski $Bm(Brta:

 The labelling is fine. I have hand checked the bigger part of the
database. Moreover, I have built a unit selection synthesizer on this
database and it works well.

I am just wondering whether eliminating any of the presented errors
would help improve the quality.






--
Best regards,

Tomasz Kuczmarski



e-mail: faqster@xxxxxxxxx
skype : faqster




--
Xavi.




--
Best regards,

Tomasz Kuczmarski



e-mail: faqster@xxxxxxxxx
skype : faqster



--
Best regards,

Tomasz Kuczmarski



e-mail: faqster@xxxxxxxxx
skype : faqster



--
Best regards,

Tomasz Kuczmarski



e-mail: faqster@xxxxxxxxx
skype : faqster


References
[hts-users:02015] Poor voice quality & embedded reestimation (monophone) errors, Tomasz Kuczmarski
[hts-users:02016] Re: Poor voice quality & embedded reestimation (monophone) errors, Tomasz Kuczmarski
[hts-users:02017] Re: Poor voice quality & embedded reestimation (monophone) errors, Simon King
[hts-users:02018] Re: Poor voice quality & embedded reestimation (monophone) errors, Tomasz Kuczmarski
[hts-users:02021] Re: Poor voice quality & embedded reestimation (monophone) errors, Tóth Bálint
[hts-users:02022] Re: Poor voice quality & embedded reestimation (monophone) errors, Tomasz Kuczmarski
[hts-users:02023] Re: Poor voice quality & embedded reestimation (monophone) errors, Xavi Gonzalvo
[hts-users:02024] Fwd: Re: Poor voice quality & embedded reestimation (monophone) errors, Tomasz Kuczmarski