A hidden Markov model based visual speech synthesizer

Author

Williams, Jay J. ; Katsaggelos, Aggelos K. ; Randolph, Mark A.

Author_Institution

Dept. of Electr. & Comput. Eng., Northwestern Univ., Evanston, IL, USA

Volume

6

fYear

2000

fDate

2000

Firstpage

2393

Abstract

This paper describes a hidden Markov model (HMM) based visual synthesizer designed to assist persons with impaired hearing. This synthesizer builds on results in the area of audio-visual speech recognition. We describe how a correlation HMM can be used to integrate independent acoustic and visual HMMs for speech-to-visual synthesis. Our results show that an HMM correlating model can significantly improve synchronization errors versus techniques which compensate for rate differences through scaling

Keywords

audio-visual systems; correlation methods; error compensation; handicapped aids; hidden Markov models; speech recognition; speech synthesis; synchronisation; acoustic HMM; audio-visual speech recognition; correlation HMM; hidden Markov model based; impaired hearing; rate difference compensation; scaling; speech-to-visual synthesis; synchronization errors; visual HMM; visual speech synthesizer; Auditory system; Hidden Markov models; Narrowband; Neural networks; Signal synthesis; Speech analysis; Speech recognition; Speech synthesis; Synthesizers; Telephony;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.859323

Filename

859323