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

[hts-users:00713] Re: the score of HVite


   
      Oh,  I see .  
                                            thanks

----- Original Message ----- 
From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxx>
To: <hts-users@xxxxxxxxxxxxxxx>
Sent: Thursday, June 14, 2007 10:00 AM
Subject: [hts-users:00712] Re: the score of HVite


> Hi,
> 
> Heng Lu wrote (2007/06/14 10:50):
> 
>> it is speaker-dependent
>>
>>>> why the scores I get are all above 0 which is very different from the 
>>>> log likelihood score in the speech recongnition (always a minus number) ?
> 
> Usually speaker-dependent model (trained using a few hours of speech) gives much higher likelihood to the training data than 
> speaker-independent model used in speech recognition (trained using hundreds/thousands of hours of speech).
> 
> 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:00709] the score of HVite, Heng Lu
[hts-users:00711] Re: the score of HVite, Heng Lu