Systems and methods for providing online fast speaker adaptation in speech recognition
作者： Daben Liu
DOI: 10.1121/1.3074484
关键词:
摘要: A system ( 230 ) performs speaker adaptation when performing speech recognition. The receives an audio segment and identifies the as a first or subsequent associated with turn. then decodes to generate transcription is estimates transformation matrix based on segment. using
lens.org 参考文章(114)
Nobuo Hataoka, Haru Ando, Editing support system including an interactive interface ,(1995)
Elizabeth D. Liddy, Edmund S. Yu, Woojin Paik, Ming Li, Multilingual document retrieval system and method using semantic vector matching ,(1996)
Davis Pan, Jean-Manuel Van Thong, Apparatus and method for controlling rate of playback of audio data ,(2001)
Jacqueline Anne Lapstun, Paul Lapstun, Kia Silverbrook, Method and system for searching information using sensor with identifier ,(2002)
Frederick S. M. Herz, System for customized electronic identification of desirable objects ,(1996)
Ralph Lipe, Philipp Heinz Schmid, Speech-related event notification system ,(2004)
Hisashi Nakatsuyama, Go Uchida, Yo Okumura, Document database management apparatus capable of conversion between retrieval formulae for different schemata ,(1995)
J. Chris Lauwers, Lester F. Ludwig, Video conferencing on existing UTP infrastructure ,(1998)
Colin W. Wightman, Joan Bachenko, Speech-recognition-assisted selective suppression of silent and filled speech pauses during playback of an audio recording Journal of the Acoustical Society of America. ,vol. 110, pp. 25- ,(1998)
Boris Katz, Patrick H. Winston, Method and apparatus for utilizing annotations to facilitate computer retrieval of database material ,(1994)