Paper Info
Title
Dynamic units of visual speech
Abstract
We present a new method for generating a dynamic, concatenative, unit of visual speech that can generate realistic visual speech animation. We redefine visemes as temporal units that describe distinctive speech movements of the visual speech articulators. Traditionally visemes have been surmized as the set of static mouth shapes representing clusters of contrastive phonemes (e.g. /p, b, m/, and /f, v/). In this work, the motion of the visual speech articulators are used to generate discrete, dynamic visual speech gestures. These gestures are clustered, providing a finite set of movements that describe visual speech, the visemes. Dynamic visemes are applied to speech animation by simply concatenating viseme units. We compare to static visemes using subjective evaluation. We find that dynamic visemes are able to produce more accurate and visually pleasing speech animation given phonetically annotated audio, reducing the amount of time that an animator needs to spend manually refining the animation.
Year
DOI
Venue
2012
10.2312/SCA/SCA12/275-284
Symposium on Computer Animation 2004
Keywords
Field
DocType
distinctive speech movement,visual speech,speech animation,realistic visual speech animation,static visemes,dynamic unit,pleasing speech animation,finite set,dynamic visual speech gesture,dynamic visemes,visual speech articulators,natural language processing,motion capture,applications,computer vision
Motion capture,Computer vision,Mesh animation,Scene analysis,Gesture,Computer science,Viseme,Motion transfer,Speech recognition,Artificial intelligence,Animation,Concatenation
Conference
ISBN
Citations 
PageRank 
978-3-905674-37-8
36
1.39
References 
Authors
22
4
Name
Order
Citations
PageRank
Sarah L. Taylor1674.77
Moshe Mahler233417.39
Barry-John Theobald333225.39
Iain Matthews44900253.61