[hts-users:04393] Re: synthesis with STRAIGHT

[Sébastien Le Maguer <slemaguer@xxxxxxxxxxxxxxxxxxxx>]

Hello,

I had such problems when there was some voicing inconsistency between the spectrum side and the f0 (especially, some frame which should have been voiced were considered as unvoiced during the extraction). As it was a specific corpus I added a specific descriptive features. However, maybe by checking the F0 boundaries in the configuration file and playing with it a little bit could help to improve. Of course it could be a complete different reason :D

Good luck,
Sébastien

Erica Cooper <ecooper@xxxxxxxxxxxxxxx> writes:

> Hi,
>
> We've started using STRAIGHT for synthesis, and we've found that for our data, it sounds worse than
> synthesis with hts-engine, despite the STRAIGHT SLT demo voice sounding very nice. We are using the
> exact same data with both STRAIGHT and hts-engine synthesis, but the STRAIGHT-synthesized
> utterances sound 'hoarse.' 1mix, 2mix, and stc are all not so good. I was wondering whether there is any
> advice for which parameters might be changed to solve this.
>
> original hts-engine voice: http://www.cs.columbia.edu/~ecooper/audio/eng_alice01.wav
> STRAIGHT 1mix: http://www.cs.columbia.edu/~ecooper/audio/1mix_alice01.wav
> STRAIGHT 2mix: http://www.cs.columbia.edu/~ecooper/audio/2mix_alice01.wav
> STRAIGHT stc: http://www.cs.columbia.edu/~ecooper/audio/stc_alice01.wav
>
> Thanks,
> Erica


--
Dr. Sébastien Le Maguer
Postdoctorate researcher

Saarland University
Campus C7.4 - room 2.03
D-66123 Saarbrücken
Germany

phone : +49-681-302-70030
Mail: slemaguer@xxxxxxxxxxxxxxxxxxxx
website :  http://www.coli.uni-saarland.de/~slemaguer/