[hts-users:00126] some questions about hts

[eem1lz <eem1lz@xxxxxxxxxxxx>]

hi all,

I am doing the project of speech coding  based on HMM . the method I am using was described in the paper " a low bit rate speech coder using HMM-based speech recognition/ synthesis techniques" by Keiichi Tokuda, Takashi Masuko, Jun Hiroi, Takao Kobayashi and Tadashi Kitamura.  thanks a lot  for what they did in the speech coding.

 

I am trying to use HTS to achieve speech recognition in one part of the project. but as a new user, I have no idea  about HTS. so I put some quesitons here and hope someone help me.

 

1. how can I train a hidden markov model and get mean, variance, mix weight, transition matrix and model definition files by using HTS? (the model is 3-state with no skip)

 

2. how can I get phoneme sequence and state durations from mel cepstrum by using phoneme recogizer , and then decode them back to mel cepstrum?

 

I will appreciate it if you would like to provide any manual or draft.

 

thank you for any help.