A speech driven talking head system based on a single face image

I-Chen Lin; Cheng Sheng Hung; Tzong Jer Yang; Ming Ouhyoung

doi:10.1109/PCCGA.1999.803347

A speech driven talking head system based on a single face image

I-Chen Lin, Cheng Sheng Hung, Tzong Jer Yang, Ming Ouhyoung

Institute of Multimedia Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

In this paper, a lifelike talking head system is proposed. The talking head, which is driven by speaker independent speech recognition, requires only one single face image to synthesize lifelike facial expression. The proposed system uses speech recognition engines to get utterances and corresponding time stamps in the speech data. Associated facial expressions can be fetched from an expression pool and the synthetic facial expression can then be synchronized with speech. When applied to Internet, our web-enabled talking head system can be a vivid merchandise narrator, and only requires 50 K bytes/minute with an additional face image (about 40 Kbytes in CIF format, 24 bit-color, JPEG compression). The system can synthesize facial animation more than 30 frames/sec on a Pentium II 266 MHz PC.

Original language	English
Title of host publication	Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	50-58
Number of pages	9
ISBN (Print)	0769502938, 9780769502939
DOIs	https://doi.org/10.1109/PCCGA.1999.803347
State	Published - 1999
Event	7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999 - Seoul, Korea, Republic of Duration: 5 Oct 1999 → 7 Oct 1999

Publication series

Name	Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999

Conference

Conference	7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999
Country/Territory	Korea, Republic of
City	Seoul
Period	5/10/99 → 7/10/99

Access to Document

10.1109/PCCGA.1999.803347

Cite this

Lin, I.-C., Hung, C. S., Yang, T. J., & Ouhyoung, M. (1999). A speech driven talking head system based on a single face image. In Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999 (pp. 50-58). Article 803347 (Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCCGA.1999.803347

Lin, I-Chen ; Hung, Cheng Sheng ; Yang, Tzong Jer et al. / A speech driven talking head system based on a single face image. Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999. Institute of Electrical and Electronics Engineers Inc., 1999. pp. 50-58 (Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999).

@inproceedings{784e0628146948ba950fed175d12a0cb,

title = "A speech driven talking head system based on a single face image",

abstract = "In this paper, a lifelike talking head system is proposed. The talking head, which is driven by speaker independent speech recognition, requires only one single face image to synthesize lifelike facial expression. The proposed system uses speech recognition engines to get utterances and corresponding time stamps in the speech data. Associated facial expressions can be fetched from an expression pool and the synthetic facial expression can then be synchronized with speech. When applied to Internet, our web-enabled talking head system can be a vivid merchandise narrator, and only requires 50 K bytes/minute with an additional face image (about 40 Kbytes in CIF format, 24 bit-color, JPEG compression). The system can synthesize facial animation more than 30 frames/sec on a Pentium II 266 MHz PC.",

author = "I-Chen Lin and Hung, {Cheng Sheng} and Yang, {Tzong Jer} and Ming Ouhyoung",

note = "Publisher Copyright: {\textcopyright} 1999 IEEE.; 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999 ; Conference date: 05-10-1999 Through 07-10-1999",

year = "1999",

doi = "10.1109/PCCGA.1999.803347",

language = "English",

isbn = "0769502938",

series = "Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "50--58",

booktitle = "Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999",

address = "美國",

}

Lin, I-C, Hung, CS, Yang, TJ & Ouhyoung, M 1999, A speech driven talking head system based on a single face image. in Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999., 803347, Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999, Institute of Electrical and Electronics Engineers Inc., pp. 50-58, 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999, Seoul, Korea, Republic of, 5/10/99. https://doi.org/10.1109/PCCGA.1999.803347

A speech driven talking head system based on a single face image. / Lin, I-Chen; Hung, Cheng Sheng; Yang, Tzong Jer et al.
Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999. Institute of Electrical and Electronics Engineers Inc., 1999. p. 50-58 803347 (Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A speech driven talking head system based on a single face image

AU - Lin, I-Chen

AU - Hung, Cheng Sheng

AU - Yang, Tzong Jer

AU - Ouhyoung, Ming

PY - 1999

Y1 - 1999

N2 - In this paper, a lifelike talking head system is proposed. The talking head, which is driven by speaker independent speech recognition, requires only one single face image to synthesize lifelike facial expression. The proposed system uses speech recognition engines to get utterances and corresponding time stamps in the speech data. Associated facial expressions can be fetched from an expression pool and the synthetic facial expression can then be synchronized with speech. When applied to Internet, our web-enabled talking head system can be a vivid merchandise narrator, and only requires 50 K bytes/minute with an additional face image (about 40 Kbytes in CIF format, 24 bit-color, JPEG compression). The system can synthesize facial animation more than 30 frames/sec on a Pentium II 266 MHz PC.

AB - In this paper, a lifelike talking head system is proposed. The talking head, which is driven by speaker independent speech recognition, requires only one single face image to synthesize lifelike facial expression. The proposed system uses speech recognition engines to get utterances and corresponding time stamps in the speech data. Associated facial expressions can be fetched from an expression pool and the synthetic facial expression can then be synchronized with speech. When applied to Internet, our web-enabled talking head system can be a vivid merchandise narrator, and only requires 50 K bytes/minute with an additional face image (about 40 Kbytes in CIF format, 24 bit-color, JPEG compression). The system can synthesize facial animation more than 30 frames/sec on a Pentium II 266 MHz PC.

UR - http://www.scopus.com/inward/record.url?scp=0005517541&partnerID=8YFLogxK

U2 - 10.1109/PCCGA.1999.803347

DO - 10.1109/PCCGA.1999.803347

M3 - Conference contribution

AN - SCOPUS:0005517541

SN - 0769502938

SN - 9780769502939

T3 - Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999

SP - 50

EP - 58

BT - Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999

Y2 - 5 October 1999 through 7 October 1999

ER -

Lin IC, Hung CS, Yang TJ, Ouhyoung M. A speech driven talking head system based on a single face image. In Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999. Institute of Electrical and Electronics Engineers Inc. 1999. p. 50-58. 803347. (Proceedings - 7th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 1999). doi: 10.1109/PCCGA.1999.803347

A speech driven talking head system based on a single face image

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this