Near-videorealistic synthetic visual speech using non-rigid appearance models

BJ Theobald; GC Cawley; I Matthews; JA Bangham

doi:10.1109/ICASSP.2003.1200092

Near-videorealistic synthetic visual speech using non-rigid appearance models

BJ Theobald, GC Cawley, I Matthews, JA Bangham

Research output: Contribution to conference › Paper

3 Citations (Scopus)

Abstract

We present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we explore the effect on the synthesiser output of blending several synthesis units considered similar to the desired unit. We present preliminary subjective and objective results used to judge the realism of the system.

Original language	English
Pages	800-803
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2003.1200092
Publication status	Published - 2003
Event	IEEE International Conference on Acoustics, Speech and Signal Processing - Hong Kong, China Duration: 6 Apr 2003 → 10 Apr 2003

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP '03
Country/Territory	China
City	Hong Kong
Period	6/04/03 → 10/04/03

Access to Document

10.1109/ICASSP.2003.1200092

Cite this

@conference{79867f5654544a629d92247dfeb5bffb,

title = "Near-videorealistic synthetic visual speech using non-rigid appearance models",

abstract = "We present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we explore the effect on the synthesiser output of blending several synthesis units considered similar to the desired unit. We present preliminary subjective and objective results used to judge the realism of the system.",

author = "BJ Theobald and GC Cawley and I Matthews and JA Bangham",

year = "2003",

doi = "10.1109/ICASSP.2003.1200092",

language = "English",

pages = "800--803",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '03 ; Conference date: 06-04-2003 Through 10-04-2003",

}

TY - CONF

T1 - Near-videorealistic synthetic visual speech using non-rigid appearance models

AU - Theobald, BJ

AU - Cawley, GC

AU - Matthews, I

AU - Bangham, JA

PY - 2003

Y1 - 2003

N2 - We present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we explore the effect on the synthesiser output of blending several synthesis units considered similar to the desired unit. We present preliminary subjective and objective results used to judge the realism of the system.

AB - We present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we explore the effect on the synthesiser output of blending several synthesis units considered similar to the desired unit. We present preliminary subjective and objective results used to judge the realism of the system.

U2 - 10.1109/ICASSP.2003.1200092

DO - 10.1109/ICASSP.2003.1200092

M3 - Paper

SP - 800

EP - 803

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

Y2 - 6 April 2003 through 10 April 2003

ER -