Towards a low bandwidth talking face using appearance models

BJ Theobald; SM Kruse; JA Bangham; GC Cawley

doi:10.1016/j.imavis.2003.08.015

Towards a low bandwidth talking face using appearance models

BJ Theobald, SM Kruse, JA Bangham, GC Cawley

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

This paper is motivated by the need to develop low bandwidth virtual humans capable of delivering audio-visual speech and sign language at a quality comparable to high bandwidth video. Using an appearance model combined with parameter compression significantly reduces the number of bits required for animating the face of a virtual human. A perceptual method is used to evaluate the quality of the synthesised sequences and it appears that 3.6 kb s^-1 can yield acceptable quality.

Original language	English
Pages (from-to)	1117-1124
Number of pages	8
Journal	Image and Vision Computing
Volume	21
Issue number	13-14
DOIs	https://doi.org/10.1016/j.imavis.2003.08.015
Publication status	Published - 1 Dec 2003

Access to Document

10.1016/j.imavis.2003.08.015

Cite this

@article{89d0019ba41342f2b05f1cba8c3bea72,

title = "Towards a low bandwidth talking face using appearance models",

abstract = "This paper is motivated by the need to develop low bandwidth virtual humans capable of delivering audio-visual speech and sign language at a quality comparable to high bandwidth video. Using an appearance model combined with parameter compression significantly reduces the number of bits required for animating the face of a virtual human. A perceptual method is used to evaluate the quality of the synthesised sequences and it appears that 3.6 kb s-1 can yield acceptable quality.",

author = "BJ Theobald and SM Kruse and JA Bangham and GC Cawley",

year = "2003",

month = dec,

day = "1",

doi = "10.1016/j.imavis.2003.08.015",

language = "English",

volume = "21",

pages = "1117--1124",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier",

number = "13-14",

}

TY - JOUR

T1 - Towards a low bandwidth talking face using appearance models

AU - Theobald, BJ

AU - Kruse, SM

AU - Bangham, JA

AU - Cawley, GC

PY - 2003/12/1

Y1 - 2003/12/1

N2 - This paper is motivated by the need to develop low bandwidth virtual humans capable of delivering audio-visual speech and sign language at a quality comparable to high bandwidth video. Using an appearance model combined with parameter compression significantly reduces the number of bits required for animating the face of a virtual human. A perceptual method is used to evaluate the quality of the synthesised sequences and it appears that 3.6 kb s-1 can yield acceptable quality.

AB - This paper is motivated by the need to develop low bandwidth virtual humans capable of delivering audio-visual speech and sign language at a quality comparable to high bandwidth video. Using an appearance model combined with parameter compression significantly reduces the number of bits required for animating the face of a virtual human. A perceptual method is used to evaluate the quality of the synthesised sequences and it appears that 3.6 kb s-1 can yield acceptable quality.

U2 - 10.1016/j.imavis.2003.08.015

DO - 10.1016/j.imavis.2003.08.015

M3 - Article

SN - 0262-8856

VL - 21

SP - 1117

EP - 1124

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 13-14

ER -