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

[hts-users:02136] Re: hts_engine_API-1.01 + flite


Maybe, many techniques are used in festival online demo.
For example...

H. Zen, T. Toda, M. Nakamura, and K. Tokuda, “Details of
Nitech HMM-based speech synthesis system for the Blizzard
Challenge 2005,” IEICE Trans. Inf.&Syst., vol. E90-
D, no. 1, pp. 325–333, 2007.

If the quality of HTS2005 is required, you can download demo scripts for model training from HTS web site.

Keiichiro Oura

Stas wrote:

I am using * flite + hts_engine_API-1.01+ hts_voice_arctic_slt-1.00 <http://downloads.sourceforge.net/hts-engine/hts_voice_arctic_slt-1.00.tar.gz>* from http://hts-engine.sourceforge.net <http://hts-engine.sourceforge.net/>.

However, I can not get the same synthesized speech quality as in HTS demos
on festival online demos, (http://www.cstr.ed.ac.uk/projects/festival/morevoices.html), using the same voice.
The synthesized speech sounds much more buzzy.

1) How can I synthesis speech, using flite + hts_engine_API-1.01+ hts_voice_arctic_slt-1.00 <http://downloads.sourceforge.net/hts-engine/hts_voice_arctic_slt-1.00.tar.gz> with the same quality
    as in the demos?

2) What speech encoder is used in hts_engine_API-1.01?

Thank you,


[hts-users:02111] hts_engine_API-1.01 + flite, Stas