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

[hts-users:00804] Re: catalan hts voices: only silence is generated (sorry ... complete email now)


В Вск, 23/09/2007 в 00:00 +0200, Antonio Bonafonte пишет:
> (sorry for previous incomplete email)
> 
> Dear all,
> I am trying to building Catalan voices using hts.
> I have download the HTS-demo: in English, as it is, it works perfectly.
> 
> In Catalan, the log file is very similar to the English one. The output
> wav files have the appropriated duration .. but the amplitude does not 
> represent speech: is almost zero, in some files, with a small pulse.
> 
> 
> Do you have any suggestion?

From my experience MLSA do generate complete silence with initial click
when predicted f0/mcep parameters aren't correct. For example if
different step is used or predicted f0 has negative sign in pau region
(this happens sometime too, I don't know why). 

So the right way I think is to dump all predicted track and then look
for unusual things and their reason.

Attachment: signature.asc
Description: =?koi8-r?q?=FC=D4=C1?==?koi8-r?q?_=DE=C1=D3=D4=D8?= =?koi8-r?q?_=D3=CF=CF=C2=DD=C5=CE=C9=D1?= =?koi8-r?q?_=D0=CF=C4=D0=C9=D3=C1=CE=C1?= =?koi8-r?q?_=C3=C9=C6=D2=CF=D7=CF=CA?= =?koi8-r?q?_=D0=CF=C4=D0=C9=D3=D8=C0?=


Follow-Ups
[hts-users:00806] Re: catalan hts voices: only silence is generated (sorry ... complete email now), Antonio Bonafonte
References
[hts-users:00800] catalan hts voices: only silence is generated (sorry ... complete email now), Antonio Bonafonte