Method and apparatus of rejecting false hypotheses in automatic speech recognizer systems
作者： Lawrence G. Bahler , Alan L. Higgins
DOI:
关键词: Computer science 、 Artificial intelligence 、 Utterance 、 Natural language processing 、 Syntax (programming languages) 、 Interval (music) 、 Speech recognition 、 Automatic speech 、 Phrase
摘要: An automatic speech recognition system employs parallel syntaxes with a first syntax operative to compare keyword templates incoming over given time interval and second in the filler same interval. Based on best comparisons each likelihood probability ratio is computed compared against selected threshold for determining whether contains valid phrase or as an undesirable utterance.
lens.org 参考文章(7)
Visvaldis A. Vitols, James E. Paul, Keyword detection in continuous speech using continuous asynchronous correlation ,(1975)
Lawrence G. Bahler, Continuous speech recognition Journal of the Acoustical Society of America. ,vol. 80, pp. 1566- 1566 ,(1981) , 10.1121/1.394303
John W. Klovstad, Speech recognition method having noise immunity Journal of the Acoustical Society of America. ,vol. 88, pp. 593- 593 ,(1984) , 10.1121/1.399877
Lawrence G. Bahler, Stephen L. Moshier, Continuous speech recognition method for improving false alarm rates Journal of the Acoustical Society of America. ,vol. 76, pp. 1876- 1876 ,(1978) , 10.1121/1.391523
Periagaram K. Rajasekaran, George R. Doddington, Speaker-independent word recognizer Journal of the Acoustical Society of America. ,vol. 87, pp. 2802- 2802 ,(1983) , 10.1121/1.399008
Hiroshi Matsuura, Tsuneo Nitta, Monosyllable recognition apparatus ,(1983)
James K. Baker, Speech recognition method Journal of the Acoustical Society of America. ,vol. 87, pp. 1672- 1672 ,(1987) , 10.1121/1.399009