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

[hts-users:01931] Re: Reg. The source models for MLSA synthesis


Hi, Vijayaditya

The mixed excitation source model is not supported in hts_engine.
If this model is required, you should edit functions as follows in lib/HTS_vocoder.c (hts_engine API 1.01).

HTS_Vocoder_initialize_excitation()
HTS_Vocoder_start_excitation()
HTS_Vocoder_get_excitation()
HTS_Vocoder_end_excitation()

Regards,
Keiichiro Oura

Vijayaditya Peddinti wrote:
Hi ,
I have been using the MLSA synthesis in the HTS engine for generating the speech samples.
However I have found that it does not use the mixed excitation source model.
Could you please specify if the code for implementing this model is already present or should it be written from the scratch?

Regards,
Vijayaditya P.
Speech Lab,
Language Technology Research Center,
IIIT -Hyderabad


References
[hts-users:01930] Reg. The source models for MLSA synthesis, Vijayaditya Peddinti