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

[hts-users:02018] Re: Poor voice quality & embedded reestimation (monophone) errors


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.

2009/6/16 Simon King <Simon.King@xxxxxxxx>

On 16 Jun 2009, at 01:10, Tomasz Kuczmarski wrote:

I found that there was more warnings in the log file. I must have overlooked them:

Looks like your label files are not a good match to the corresponding waveforms in some cases. So,check that first: listen to a random sample of waveforms and check that the label files match (e.g., did the speaker read the sentence correctly).

Simon


--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.





--
Best regards,

Tomasz Kuczmarski



e-mail: faqster@xxxxxxxxx
skype : faqster

Follow-Ups
[hts-users:02020] Re: Poor voice quality & embedded reestimation (monophone) errors, Luis Uebel
[hts-users:02021] Re: Poor voice quality & embedded reestimation (monophone) errors, Tóth Bálint
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