From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxxx>
Reply-To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
Subject: [hts-users:00193] Re: diffrences between merge and cat
Date: Wed, 11 Jan 2006 02:45:15 +0900
Hi,
liulei_198216@xxxxxxxxxxx wrote:
But I puzzle how festival works together with hts_engine.
I have read the "perl script" and found that hts_engine gets .lab
files from /tmp/tmp.lab to systhsize speech.
when we use "festival" to input text from command line ,we will
get real-time speech.
My question is
How does the festival trigger hts_engine to systhsiz speech
after .lab files are generated from festival?
I have also read festival manul and found it systhsize speech
through concatenating units,
but how does the hts_engine work with festival?
1. Festival extracts utterance information from an input text.
2. The uttrance information is saved as "utt.feats" on working
directory.
3. Festival calls htsvoice.pl.
4. In htsvoice.pl, the utterance information is converted to
corresponding context-dependent label sequence.
5. hts_engine is called from htsvoice.pl.
6. A waveform is synthesized and saved in raw audio format.
7. RIFF header is appended to raw audio by sox.
8. Resultant wav file is loaded by festival,
Please see hts.scm included in our hts voices.
In the next festival release (2.0?), hts_engine will be integrated
as a function of the festival.
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
------------------------------------------------