@inproceedings{5ef0623d16c04cacb0b7de3856234bed,
title = "An improved automatic lipreading system to enhance speech recognition",
abstract = "Current acoustic speech recognition technology performs well with very small vocabularies in noise or with large vocabularies in very low noise. Accurate acoustic speech recognition in noise with vocabularies over 100 words has yet to be achieved. Humans frequently lipread the visible facial speech articulations to enhance speech recognition, especially when the acoustic signal is degraded by noise or hearing impairment. Automatic lipreading has been found to improve significantly acoustic speech recognition and could be advantageous in noisy environments such as offices, aircraft and factories. An improved version of a previously described automatic lipreading system has been developed which uses vector quantization. dynamic time warping, and a new heuristic distance measure. This paper presents visual speech recognition results from multiple speakers under optimal conditions. Results from combined acoustic and visual speech recognition are also presented which show significantly improved performance compared to the acoustic recognition system alone.",
keywords = "Lipreading, Speech recognition, Vision",
author = "Eric Petajan and Bradford Bischoff and David Bodoff and Brooke, {N. Michael}",
year = "1988",
month = may,
day = "1",
doi = "10.1145/57167.57170",
language = "English",
series = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",
pages = "19--25",
editor = "J.J. O'Hare",
booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI 1988",
note = "1988 SIGCHI Conference on Human Factors in Computing Systems, CHI 1988 ; Conference date: 15-05-1988 Through 19-05-1988",
}