Prototyping and Transforming Visemes for Animated Speech

Bernard Paul Tiddeman; David Ian Perrett

doi:10.1109/CA.2002.1017545

Prototyping and Transforming Visemes for Animated Speech

Bernard Paul Tiddeman, David Ian Perrett

Research output: Contribution to conference › Paper

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.

Original language	English
Pages	248-51
DOIs	https://doi.org/10.1109/CA.2002.1017545
Publication status	Published - 2002

Keywords

visual speech
facial animation
image transformation
MODELS
IMAGES
SHAPE

Access to Document

10.1109/CA.2002.1017545

Cite this

@conference{fa09d154f62144db871fd4edd9b16652,

title = "Prototyping and Transforming Visemes for Animated Speech",

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 = "visual speech, facial animation, image transformation, MODELS, IMAGES, SHAPE",

author = "Tiddeman, {Bernard Paul} and Perrett, {David Ian}",

note = "Proc. Computer Animation 2002, Geneva, Switzerland, 19-21 June 2002",

year = "2002",

doi = "10.1109/CA.2002.1017545",

language = "English",

pages = "248--51",

}

TY - CONF

T1 - Prototyping and Transforming Visemes for Animated Speech

AU - Tiddeman, Bernard Paul

AU - Perrett, David Ian

N1 - Proc. Computer Animation 2002, Geneva, Switzerland, 19-21 June 2002

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

KW - visual speech

KW - facial animation

KW - image transformation

KW - MODELS

KW - IMAGES

KW - SHAPE

UR - http://ieeexplore.ieee.org/Xplore/login.jsp?url=/iel5/7936/21886/01017545.pdf?arnumber=1017545

U2 - 10.1109/CA.2002.1017545

DO - 10.1109/CA.2002.1017545

M3 - Paper

SP - 248

EP - 251

ER -

Prototyping and Transforming Visemes for Animated Speech

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this