[hts-users:03895] Re: HTS model and Speech Recognition

[Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>]

Hi,

For example,,,
HERest in HTS support HMM, MSD-HMM, HSMM, and MSD-HSMM.
HVite in HTS support only HMM.
HTS demo scripts are written for using MSD-HSMM.

Thus, if you use *HMM*, you can use HVite in HTS for recognition.

Regards,
Keiichiro Oura




2013/11/8 Ibrahim Sobh <im_sobh@xxxxxxxxxxx>:
>
>
> Thank you!  So what is the purpose of HVite of the HTS?! (what is it used
> for?!)
>
>
>
>> Date: Sat, 2 Nov 2013 15:34:58 +0900
>> From: uratec@xxxxxxxxxxxxxxx
>> Subject: [hts-users:03872] Re: HTS model and Speech Recognition
>> To: hts-users@xxxxxxxxxxxxxxx
>> CC: uratec@xxxxxxxxxxxx
>
>>
>> Hi,
>>
>> In HTS demo scripts, MSD-HSMM (MSD for F0, HSMM for state duration) is
>> trained.
>> But, HVite/HDecode support only HMM.
>> So, HMM training is required for recognition.
>>
>> Regards,
>> Keiichiro Oura
>>
>>
>> 2013/11/2 Ibrahim Sobh <im_sobh@xxxxxxxxxxx>:
>> > Hi,
>> >
>> > I have trained HMM models using HTS scripts based on lf0, mgc and I have
>> > added some other features in other streams. I have synthesized speech
>> > successfully.
>> >
>> > *** Can I use the same HMM models for speech recognition task ( using
>> > HVite
>> > and/or HDecode)? How in practical steps?
>> >
>> > (For example, using HVite version of HTS is enough?!)
>> >
>> > Best Regards
>> > Sobh
>>