摘要: A system is provided for allowing a user to add word models speech recognition system. In particular, the allows input number of renditions new and which generates from these sequence phonemes representative word. This stored in phoneme dictionary together with typed version subsequent use by
google.com.mx
harvard.edu参考文章(178)
Yui Mieko, Silence compression coding/decoding method and device ,(2000)
John Marland Garth, Paramesh Sampatrai Desai, Method, system, and program for extracting data from database records using dynamic code ,(2000)
Ben R. Breed, Kenneth A. Witzke, Allen K. Lo, Ronald A. Borrell, Mark D. Skinas, Signal processing incorporating signal tracking, estimation,and removal processes using a maximum a posteriori algorithm, and sequential signal detection ,(1993)
Dietrich Klakow, Method of estimating probabilities of occurrence of speech vocabulary elements ,(1999)
John Skilling, Classic Maximum Entropy Springer Netherlands. pp. 45- 52 ,(1989) , 10.1007/978-94-015-7860-8_3
Richard Vandervoort Cox, Anthony J. Accardi, Core estimator and adaptive gains from signal to noise ratio in a hybrid speech enhancement system ,(1998)
Victor W. Zue, Kenney Ng, Subword unit representations for spoken document retrieval. conference of the international speech communication association. ,(1997)
Barry S. Bronson, Method and apparatus for indexing and retrieving audio-video data ,(1990)
Chung T. Nguyen, Francis J. O'Brien, Bruce J. Bates, Model identification and characterization of error structures in signal processing ,(1997)
Pietro Laface, G. Micca, R. Pieraccini, Three dimensional DP for phonetic lattice matching international conference on digital signal processing. pp. 547- 551 ,(1987)