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

[hts-users:04238] vowel descriptive features

To: hts-users@sp.nitech.ac.jp
Subject: [hts-users:04238] vowel descriptive features
From: Sébastien Le Maguer <slemaguer@coli.uni-saarland.de>
Date: Wed, 11 Mar 2015 15:50:59 +0100
Delivered-to: hts-users@sp.nitech.ac.jp
List-help: <mailto:hts-users-ctl@sp.nitech.ac.jp?body=help>
List-id: hts-users.sp.nitech.ac.jp
List-owner: <mailto:hts-users-admin@sp.nitech.ac.jp>
List-post: <mailto:hts-users@sp.nitech.ac.jp>
List-software: fml [fml 4.0 STABLE (20040215/4.0.4_BETA)]
List-unsubscribe: <mailto:hts-users-ctl@sp.nitech.ac.jp?body=unsubscribe>
Reply-to: hts-users@sp.nitech.ac.jp

Hello,

I just want to indicate that using festival 2.4 the resulted full labels only contain values "0" or "x" for the "vowel of syllable" feature. The delimiters of this feature are "|" on the left and "/C:". I checked for hts 2.3alpha and 2.3beta. It happens for both version

Kind regards,
Sébastien
-- 
Dr. Sébastien Le Maguer
Postdoctorate researcher

Saarland University
Campus C7.4 - room 2.03
D-66123 Saarbrücken
Germany

phone : +49-681-302-70030
Mail: slemaguer@coli.uni-saarland.de
website :  http://www.coli.uni-saarland.de/~slemaguer/

Prev by Date: [hts-users:04237] creating context-dependent decision trees
Next by Date: [hts-users:04239] manipulating a trained voice
Previous by thread: [hts-users:04237] creating context-dependent decision trees
Next by thread: [hts-users:04239] manipulating a trained voice
Index(es):
- Date
- Thread