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

[hts-users:01932] Re: Reg. The source models for MLSA synthesis


Vijayaditya Peddinti wrote:

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?

Some research groups have their internal versions of hts_engine which support mixed excitation, but official HTS release doesn't support it. If I remember correctly, DFKI's Java version of hts_engine, which has been integrated to DFKI's TTS engine MARY, supports mixed excitation, and its source codes are open.

Best regards,

Heiga ZEN (Byung Ha CHUN)

Heiga ZEN (Byung Ha CHUN)
Speech Technology Group
Cambridge Research Lab
Toshiba Research Europe
phone: +44 1223 436975

This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email ______________________________________________________________________
[hts-users:01930] Reg. The source models for MLSA synthesis, Vijayaditya Peddinti