[hts-users:00327] about modifying voice's characteristic

["lei liu" <wenshiliu@xxxxxxxxx>]

Hi

 

I want to modifying voice's characteristic through modifying the f0.

 

for example: 

 

if I want  to stress   some   phonemes,

I must find the position of the phonemes in the f0s' sequence.

 

 

In  the   " HTS + festival " demo , hts_engine  can do that,

but it modify the whole sentence's f0s.

 

certainly we can modify the engine to modify  some  phonemes' f0s through their durations.

 

 

But I found that 

in the "HTS - demo ", it generate the "mcep" and "pit" file to generate speech,

so I want to modify the "pit"  file by hand  to change voice's   characteristic.

 

I see the "pit" file  is generated by "HMGenS" which is modified .

I think that modifying the "HTS-1.1.1_for_HTK-3.2.1.patch" can do that ,   and maybe it is similar to modifying the hts_engine.

 

 

 

I want to kown  that is there  any other ways to open the "pit" file and modify the values in it.

 

 

thank you very much, and 

Best regards