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

[hts-users:00806] Re: catalan hts voices: only silence is generated (sorry ... complete email now)




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.
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.
Dear Nickolay:
Than you very much for your accurate  comment.
The .lf0 files are almost void (4 bytes). When I generated the data
I saw a warning (error opening /dev/mixers) but I ignored it as the
files were created. Now I will check the problem.

Toni

Follow-Ups
[hts-users:00807] 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
[hts-users:00804] Re: catalan hts voices: only silence is generated (sorry ... complete email now), Nickolay V. Shmyrev