Continuous optical automatic speech recognition by lipreading

We describe a continuous optical automatic speech recognizer (OASR) that uses optical information from the oral-cavity shadow of a speaker. The system achieves a 25.3 percent recognition on sentences having a perplexity of 150 without using any syntactic, semantic, acoustic, or contextual guides. We...

Full description

Saved in:
Bibliographic Details
Published inProceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers Vol. 1; pp. 572 - 577 vol.1
Main Authors Goldschen, A.J., Garcia, O.N., Petajan, E.
Format Conference Proceeding
LanguageEnglish
Published IEEE Comput. Soc. Press 1994
Subjects
Automatic speech recognition
Cameras
Hidden Markov models
Image databases
Loudspeakers
Optical devices
Optical filters
Optical noise
Optical recording
Spatial databases
Online AccessGet full text
ISBN0818664053
9780818664052
ISSN1058-6393
DOI10.1109/ACSSC.1994.471517

Cover

More Information
Summary:We describe a continuous optical automatic speech recognizer (OASR) that uses optical information from the oral-cavity shadow of a speaker. The system achieves a 25.3 percent recognition on sentences having a perplexity of 150 without using any syntactic, semantic, acoustic, or contextual guides. We introduce 13, mostly dynamic, oral-cavity features used for optical recognition, present phones that appear optically similar (visemes) for our speaker, and present the recognition results for our hidden Markov models (HMMs) using visemes, trisemes, and generalized trisemes. We conclude that future research is warranted for optical recognition, especially when combined with other input modalities.< >
ISBN:0818664053
9780818664052
ISSN:1058-6393
DOI:10.1109/ACSSC.1994.471517