[hts-users:00047] Re: hts_engine binary format
- Subject: [hts-users:00047] Re: hts_engine binary format
- From: Heiga Zen / Byung-Ha Chun <zen@xxxxxxxxxxxxxxxx>
- Date: Wed, 9 Jun 2004 00:36:50 +0900
- Organization: Dept. of Computer Science, Nagoya Inst. of Tech.
Hi Elliot,
On Tue, 8 Jun 2004 11:24:21 -0400
"Elliot Moore" <em80@xxxxxxxxxxxxxxx> wrote:
> What is the purpose of the hts_engine conversion?
> What exactly is it changing in the HTK formatted mmf that is so important?
> It doesn't seem to make a difference if that step is skipped and the speech signals are synthesized.
The main purpose of the hts_engine conversion is to reduce the size of acoustic models.
HTK mmf format contains too much information for HMM-based speech synthesis.
> I need to know because I haven't been including that step in a multi-speaker
> recognition/synthesis application and the synthesized speech so far as been unintelligible.
> I want to make sure that this isn't the reason and I want to know what the hts_engine is anyway.
I think it isn't the reason.
Best regards,
Heiga Zen / Byung-Ha Chun
------------------------------------------------
Heiga Zen (in Japanese pronunciation)
Byung-Ha Chun (in Korean pronunciation)
Department of Computer Science and Engineering
Graduate School of Engineering
Nagoya Institute of Technology
Japan
e-mail: zen@xxxxxxxxxxxxxxxx
web: http://kt-lab.ics.nitech.ac.jp/~zen
------------------------------------------------
- References
-
- [hts-users:00044] hts_engine binary format, Matthew Lee
- [hts-users:00045] Re: hts_engine binary format, Heiga Zen / Byung-Ha Chun
- [hts-users:00046] Re: hts_engine binary format, Elliot Moore