[hts-users:00679] Re: Speaker Adaptation

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

Hi,

Tamer Fares wrote (2007/05/17 22:21):

> You mean with "Adaptively trained models" that I record new training 
> data with another voice (raw) and prepare the Lab files and mcp then I 
> trained it
>
> Then I take the trained new voice(will be the target voice) to be used 
> for my voice adaptation 
>
> Is this right? 

Sorry, I cannot understand.
Please refer to HTKBook Section 9.2 for detail of adaptive training.

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
------------------------------------------------