Speech rate modeling in synthetic speech (Sascha Fagel )

Subject: Speech rate modeling in synthetic speech
From:    Sascha Fagel  <sascha.fagel(at)TU-BERLIN.DE>
Date:    Mon, 13 Jun 2005 09:56:26 +0200

Dear list,

I am looking for (sub segmental) speech rate models implemented in speech
synthesizers (segmental reduction etc. is a bit out of my focus). Synthetic
speech at low rate e.g. with MBROLA often sounds like slow motion speech and
at high rate it sounds time compressed and hyperarticulated. Are there
synthesizers that implement different speech rates adequately? And if so,
how do they do that? Any hints and refs are welcome.

Best regards
Sascha


******************************************
Dr. Sascha Fagel
Technical University Berlin
Communication Science
Secr. TEL10-1
Ernst-Reuter-Platz 7
10587 Berlin
Fon +49(30)314-24527
Fax +49(30)314-79883
Email: sascha.fagel(at)tu-berlin.de
http://fourier.kgw.tu-berlin.de/fagel.html
******************************************