From: malcolm@interval.com (Malcolm Slaney)
Date: Fri, 13 Oct 1995 10:55:51 -0700
Subject: Speech Synthesis at CCRMA
Message-Id: <v02130500aca456c4b30d@[199.170.106.94]>

Next Thursday (Oct. 19th) Perry Cook will be presenting a survey of new
directions and implementations of singing synthesizers.  Perry, for his PhD
thesis built one of the best sounding synthesizers I've heard.  It's really
wonderful to watch his vocal tract synthesizer in action and it sounds
great.

This seminar will be a combined seminar with between the Hearing Seminar
and the DSP group at CCRMA.  We'll be meeting in the Ballroom at 2:15PM.

        Who:    Perry Cook (CCRMA)
        When:   Thursday October 19th at 2:15PM    ***** Note Different Time ***
        What:   New Research and Implentations in Speech Synthesis
        Where:  CCRMA Ballroom (main floor of the Knoll at Stanford)

Don't miss this chance to hear about the best work in singing synthesizers!

And don't forget John Hajda talk on Timbre Perception today (Friday) in the
library at 1PM.

-- Malcolm


From: prc@ccrma.Stanford.EDU (Perry Cook)
Date: Fri, 13 Oct 95 09:28:51 -0700
Subject: Talk Description


New Research and Implementations in Speech Synthesis
Perry Cook, Stanford CCRMA

This will be a brief survey of new research directions
and new implementations in the synthesis of the human
voice.  I will cover some papers I've dug out over the
last year, which I used as the basis for a talk I gave
on "Future directions in Singing Synthesis Research" in
Greece this summer.  I'll then survey the papers and
topics of interest from the International Congress of
Phonetic Sciences conference in Stockholm this summer.
I'll finish by giving a brief introduction to the
Distinctive Regions (DR) model, as an extension/refinement
of the basic acoustic tube model of the vocal tract.
I'll demo the new DR-based text to speech system, BigMouth,
from Trillium Research in Calgary, CA.