[hts-users:00519] Re: HTS question about creating a new voice for the Ca

[hts-users:00519] Re: HTS question about creating a new voice for the Catalan language

Subject: [hts-users:00519] Re: HTS question about creating a new voice for the Catalan language

From: "Oriol Vinyals Argelaguet" <oriol18@xxxxxxxxx>

Date: Wed, 14 Feb 2007 09:45:38 -0500

Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:references; b=EFaGBEBD1toOOj8qedJzfRCIF7d261n1SEUoSGXQbqJBezYA2Y9SHOcpQHxh7xEq5rTDt6e5Dx/7nOVqZ8nveyuHK8txPa+G1BxrRxXQtS4p7l419ujdzFo4CyiEZU9uJKVUlP91wYD+A6dFHlhOqcUwgayp4tbIcn3WIuE2dlM=

Dear Heiga,

I did not do that as I didn't know the questions were phoneset dependant. Is there any way to do it automaticly? Otherwise I will do it by hand so I can do the voice training again and see if this solves my problem.

Best,

Oriol

On 2/14/07, Heiga ZEN (Byung Ha CHUN) <zen@xxxxxxxxxxxxxxxx> wrote:

Hi,

Oriol Vinyals Argelaguet wrote:

> Some information of the training database: 5500 seconds of speech,
> labeled using sphinxtrain (there is some missalignment ...), and a new
> phoneset defined for the catalan language. We are currently constructing
> a bigger and hand-labeled database and we use this one as a temporary
> solution.

Did you adjust questions for tree-based clustering (under data/questions directory) to your phoneset?

Best 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://kt-lab.ics.nitech.ac.jp/~zen
------------------------------------------------