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?=