MIT TechTV is an initiative of
Learn about MIT TechTV and check out our resource page for media makers at MIT.
MIT TechTV is an initiative of
You need Adobe Flash Player to watch videos on this site.
We describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she utters a pre-determined speech corpus. After processing the corpus automatically, a visual speech module is learned from the data that is capable of synthesizing the human subject's mouth uttering entirely novel utterances that were not recorded in the original video. The synthesized utterance is re-composited onto a background sequence which contains natural head and eye movement. The final output is videorealistic in the sense that it looks like a video camera recording of the subject. At run time, the input to the system can be either real audio sequences or synthetic audio produced by a text-to-speech system, as long as they have been phonetically aligned.
Click here for more information.
You need to log in, in order to post comments. If you don’t have an account yet, sign up now!
Added over 2 years ago | 00:03:25 | 1132 views
Added over 2 years ago | 01:37:07 | 895 views
Added 1 year ago | 00:04:07 | 1029 views
Added 1 year ago | 00:02:59 | 714 views
Added 5 months ago | 01:05:08 | 137 views | private
Added 5 months ago | 01:19:14 | 148 views | private
Amazing study ..Wey well done .
Posted 1 year by Anonymous User
Bravissimi Tony and Mary !!! Tony for fantastic ideas and hard tecnology works and Mary for perfect face and very realistic , expressive moviments of eyes and mouth. I hope all best future success for this project.
with compliment
walter conti
info@walterconti.it
Posted 1 year by Anonymous User
A tremendous opportunity exists for speech therapy in patients recovering from stroke. I cannot over state this. Often after a course of professional therapy administered by a speech pathologist, practice must be ongoing in order for progress to continue.
Is there software available that I can download and prototype with?
Does MIT have a medical technology program that could offer PCs with this kind of software installed?
My Uncle has had a severe stroke and further speech practice must be self administered due to Medicare restrictions.
Software like this could make a giant contribution for in-home therapy.
brad.n.ospam.eckrose@gmail.com
Posted 9 months by Anonymous