Dear Doctor
So y in the Training.pl u used the HCompv to compute the global variance as u will start a flat starting ; while i saw that in the labelling file that the phonemes sequences accompanied with its corresponding boundaries
Thanks Alot
Tamer Fares
From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxxx>
Reply-To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
Subject: [hts-users:00572] Re: Speech Segmentation
Date: Sat, 10 Mar 2007 17:56:51 +0900
>Hi,
>
>Tamer Fares wrote:
>
>>You didn't answer me about the most important question of the
>>HCompV and HERest (flat starting) while there is a phonemes
>>boundaries in the mono and full context labeling for each phomeme
>
>Both HCompV and HERest do not require any phoneme boundaries.
>They need phoneme sequences only.
>
>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
>------------------------------------------------
>