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

[hts-users:01308] Re: Questions of HMGens


Hi,

孙敬伟 wrote (2008/04/03 12:48):

> Thank you very much for the answer.
>  
> By the way, I am using HTS2.1SRC1

I think you're using HTS-2.0 binary rather than HTS-2.1RC1 one 
because I found the following lines in HTS-2.1RC1_for_HTK-3.4.patch:

+   printf(" -c n    type of parameter generation algorithm            0\n");
+   printf("          0: both mix and state sequences are given        \n");
+   printf("          1: state sequence is given,                      \n");
+   printf("             but mix sequence is hidden                    \n");
+   printf("          2: both state and mix sequences are hidden       \n");

Furthermore, -b option was changed to -g option, -b option had different meaning,
and -W and -Y options were added in HTS-2.1RC1.

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

References
[hts-users:01300] Endianism problems, Nicholas Volk
[hts-users:01302] Re: Endianism problems, Heiga ZEN (Byung Ha CHUN)
[hts-users:01303] Re: Endianism problems, Ore, Brian M CTR USAF AFMC AFRL/RHCP
[hts-users:01304] Re: Endianism problems, Heiga ZEN (Byung Ha CHUN)
[hts-users:01305] Questions of HMGens, 孙敬伟
[hts-users:01306] Re: Questions of HMGens, Heiga ZEN (Byung Ha CHUN)
[hts-users:01307] Re: Questions of HMGens, 孙敬伟