[hts-users:01222] Re: WER Comparison of HTK and HTS

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

Hi,

Junichi Yamagishi wrote (2008/03/13 2:15):

> Thus, in theory, there is no differences between them. What I confirmed is
> "accuracy" of HTS, in other words, Heiga's magic (bug fix, flooring, and 
> so on).

Compared with HTK, HTS uses double precision in many parts.
And variance flooring is explicitly used in decision-tree construction.

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