Towards video realistic synthetic visual speech

Barry J. Theobald; J. Andrew Bangham; Iain A. Matthews; Gavin C. Cawley

doi:10.1109/ICASSP.2002.5745507

Towards video realistic synthetic visual speech

Barry J. Theobald, J. Andrew Bangham, Iain A. Matthews, Gavin C. Cawley

Research output: Contribution to conference › Paper

2 Citations (Scopus)

Abstract

In this paper we present initial work towards a video-realistic visual speech synthesiser based on statistical models of shape and appearance. A synthesised image sequence corresponding to an utterance is formed by concatenation of synthesis units (in this case phonemes) from a pre-recorded corpus of training data. A smoothing spline is applied to the concatenated parameters to ensure smooth transitions between frames and the resultant parameters applied to the model—early results look promising.

Original language	English
Pages	3892-3895
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2002.5745507
Publication status	Published - May 2002
Event	IEEE International Conference on Acoustics, Speech and Signal Processing - Orlando, United States Duration: 13 May 2002 → 17 May 2002

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP- 2002
Country/Territory	United States
City	Orlando
Period	13/05/02 → 17/05/02

Access to Document

10.1109/ICASSP.2002.5745507

Cite this

@conference{7847d534ab5f4b06badd1855f7c02ee0,

title = "Towards video realistic synthetic visual speech",

abstract = "In this paper we present initial work towards a video-realistic visual speech synthesiser based on statistical models of shape and appearance. A synthesised image sequence corresponding to an utterance is formed by concatenation of synthesis units (in this case phonemes) from a pre-recorded corpus of training data. A smoothing spline is applied to the concatenated parameters to ensure smooth transitions between frames and the resultant parameters applied to the model—early results look promising.",

author = "Theobald, {Barry J.} and Bangham, {J. Andrew} and Matthews, {Iain A.} and Cawley, {Gavin C.}",

year = "2002",

month = may,

doi = "10.1109/ICASSP.2002.5745507",

language = "English",

pages = "3892--3895",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP- 2002 ; Conference date: 13-05-2002 Through 17-05-2002",

}

TY - CONF

T1 - Towards video realistic synthetic visual speech

AU - Theobald, Barry J.

AU - Bangham, J. Andrew

AU - Matthews, Iain A.

AU - Cawley, Gavin C.

PY - 2002/5

Y1 - 2002/5

N2 - In this paper we present initial work towards a video-realistic visual speech synthesiser based on statistical models of shape and appearance. A synthesised image sequence corresponding to an utterance is formed by concatenation of synthesis units (in this case phonemes) from a pre-recorded corpus of training data. A smoothing spline is applied to the concatenated parameters to ensure smooth transitions between frames and the resultant parameters applied to the model—early results look promising.

AB - In this paper we present initial work towards a video-realistic visual speech synthesiser based on statistical models of shape and appearance. A synthesised image sequence corresponding to an utterance is formed by concatenation of synthesis units (in this case phonemes) from a pre-recorded corpus of training data. A smoothing spline is applied to the concatenated parameters to ensure smooth transitions between frames and the resultant parameters applied to the model—early results look promising.

U2 - 10.1109/ICASSP.2002.5745507

DO - 10.1109/ICASSP.2002.5745507

M3 - Paper

SP - 3892

EP - 3895

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 13 May 2002 through 17 May 2002

ER -