[hts-users:00677] Re: Speaker Adaptation

["Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxx>]

Hi,

Tamer Fares wrote (2007/05/17 19:34):

> I recorded my own utterances and it was trained and synthesized using the HTS 2.0
>
> Can I adapt my voice to another voice ? (I read that 20 utterance is 
> sufficient for the adaptation to the target speaker)

Although speaker independent or adaptively trained models are preferred,
you can adapt your voice to another one's voice.

Regards,

Heiga ZEN (Byung Ha CHUN)

--
------------------------------------------------
Heiga ZEN     (in Japanese pronunciation)
Byung Ha CHUN (in Korean pronunciation)

Department of Computer Science and Engineering
Nagoya Institute of Technology
Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan

http://www.sp.nitech.ac.jp/~zen
------------------------------------------------