Speech Research, Anyone familiar with phoneme/viseme mapping to face renderings

MS Sapi supports phoneme and viseme callbacks,
useful for selecting, say, a 3D rendered picture of
a face posed in the given phoneme/viseme.

Poser 6 can render faces.

Anybody know about this type of thing?

Pertial



----== Posted via Newsfeeds.Com - Unlimited-Uncensored-Secure Usenet News==----
http://www.newsfeeds.com The #1 Newsgroup Service in the World! 120,000+ Newsgroups
----= East and West-Coast Server Farms - Total Privacy via Encryption =----

> MS Sapi supports phoneme and viseme callbacks,

"Baldi" the animated head, mouth, and tongue in the CSLU Toolkit
does this.
http://cslu.cse.ogi.edu/toolkit/

Sincerely,
James
--
www.readsay.com - maker of the ReadSay PROnounce English literacy system
400 MHz PDA included: $499 -- http://www.readsay.com/PROnounce.html

We work with virtual speech animation (see www.inovani.com) and from our
experience
you need to know what phonemes/visemes occur in the speech stream some
milliseconds
before they will sound in the speakers if you want natural speech animation.
The reason for
this is that you start forming the sound with your mouth before you actually
say the sound.
(Try to say "sugar" and "simple", and check how you look when the "s"
sounds - its influenced
by the next sound - and that has to be taken into account when animating).

MS Sapi which follows SAPI 5.1 only gives you the phonemes/visemes at the
time when
they sound through the speakers... and that is a bit to late to get
realistic speech motions,
but maybe good enough for "fun and games" :-)

One of the main challenges with speech animation is defining what is to
happen between
phonemes/visemes. If you look at many automatic animations they don't look
natural
because of this.

Other challenges is finding ways to represent and implement real-time
animation that is
fast enough so you don't have to make a video to get good enough frame rate.

- else