DocumentCode
1951818
Title
Prototyping and transforming visemes for animated speech
Author
Tiddeman, Bernard ; Perrett, David
Author_Institution
Sch. of Comput. Sci., Univ. of St Andrews, Fife, UK
fYear
2002
fDate
2002
Firstpage
248
Lastpage
251
Abstract
Animated talking faces can be generated from a set of predefined face and mouth shapes (visemes) by either concatenation or morphing. Each facial image corresponds to one or more phonemes, which are generated in synchrony with the visual changes. Existing implementations require a full set of facial visemes to be captured or created by an artist before the images can be animated. In this work we generate new, photo-realistic visemes from a single neutral face image by transformation using a set of prototype visemes. This allows us to generate visual speech from photographs and portraits where a full set of visemes is not available
Keywords
computer animation; face recognition; image morphing; software prototyping; speech recognition; animated speech; animated talking faces; concatenation; facial animation; facial image; facial visemes; image transformation; morphing; mouth shapes; neutral face image; predefined face; synchrony; Computer graphics; Computer science; Facial animation; Mouth; Prototypes; Psychology; Shape; Solid modeling; Speech synthesis; Tongue;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Animation, 2002. Proceedings of
Conference_Location
Geneva
ISSN
1087-4844
Print_ISBN
0-7695-1594-0
Type
conf
DOI
10.1109/CA.2002.1017545
Filename
1017545
Link To Document