[hts-users:00561] Re: Label Context
- Subject: [hts-users:00561] Re: Label Context
- From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxxx>
- Date: Thu, 08 Mar 2007 18:54:28 +0900
Hi,
Tamer Fares wrote:
how i can convert a speech file into the corresponding full label
context one?
Most of contexts can be predicted from texts, but some of them are difficult.
To get better quality, manual correction is required.
is this done manually or there is a program for this automatic label
mapping segmentation
Currently we do not provide any program to predict/recognize these unpredictable contexts from speech files.
Regards,
Heiga ZEN (Byung Ha CHUN)
--
------------------------------------------------
Heiga ZEN (in Japanese pronunciation)
Byung Ha CHUN (in Korean pronunciation)
Department of Computer Science and Engineering
Nagoya Institute of Technology
Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan
http://www.sp.nitech.ac.jp/~zen
------------------------------------------------
- References
-
- [hts-users:00558] Label Context, Tamer Fares