Method and system for speech recognition using continuous densit

Details Method and system for speech recognition using continuous densit Method and system for speech recognition using continuous densit

1996-05-01

1999-08-10

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704251, 704254, 704255, G10L 506

Patent

active

059373849

ABSTRACT:
A method and system for achieving an improved recognition accuracy in speech recognition systems which utilize continuous density hidden Markov models to represent phonetic units of speech present in spoken speech utterances is provided. An acoustic score which reflects the likelihood that a speech utterance matches a modeled linguistic expression is dependent on the output probability associated with the states of the hidden Markov model. Context-independent and context-dependent continuous density hidden Markov models are generated for each phonetic unit. The output probability associated with a state is determined by weighing the output probabilities of the context-dependent and context-independent states in accordance with a weighting factor. The weighting factor indicates the robustness of the output probability associated with each state of each model, especially in predicting unseen speech utterances.

REFERENCES:
patent: 4783803 (1988-11-01), Baker et al.
patent: 4817156 (1989-03-01), Bahl et al.
patent: 4829577 (1989-05-01), Kuroda et al.
patent: 4866778 (1989-09-01), Baker
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5267345 (1993-11-01), Brown et al.
patent: 5268990 (1993-12-01), Cohen et al.
patent: 5293584 (1994-03-01), Brown et al.
patent: 5333236 (1994-07-01), Bahl et al.
patent: 5444617 (1995-08-01), Merialdo
patent: 5581655 (1996-12-01), Cohen et al.
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5627939 (1997-05-01), Huang et al.
patent: 5642519 (1997-06-01), Martin
patent: 5710866 (1998-01-01), Alleva et al.
Bahl, et al., "A Maximum Likelihood Approach to Continuous Speech Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence; 1983; pp. 308-319.
Lee, Kai-Fu, "Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition," IEEE Transactions on Acoustics, Speech and Signal Processing; Apr. 1990; pp. 347-362.
Huang, Xuedong et al., "An Overview of the SPHINX-II Speech Recognition System," Proceedings of ARPA Human Language Technology Workshop; 1993; pp. 1-6.
Huang, X.D., and M. A. Jack, "Semi-continuous hidden Markov models for speech signals," Computer Speech and Language, vol. 3; 1989; pp. 239-251.
Baker, James K., "Stochastic Modeling for Automatic Speech Understanding," Speech Recognition, Editor P.R. Reddy; pp. 297-307.
"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing." ICASSP-93--Speech Processing Volume II of V, Minneapolis Convention Center; Apr. 27-30, 1993; pp. 311-314.
Gelsema et al. (Ed.), "Pattern Recognition in Practice," Proceedings of an International Workshop held in Amsterdam; May 21-23, 1980; pp. 381-402.
Rabiner, Lawrence, and Biing-Hwang Juang, "Fundamentals of Speech Recognition," Prentice Hall Publishers; 1993; Chapter 6; pp. 372-373.
Lee, Kai-Fu et al., "Automatic Speech Recognition--The Development of the SPHINX System," Kluwer Academic Publishers; 1989; pp. 51-62, and 118-126.
Huang, X.D. et al., "Hidden Markov Models for Speech Recognition," Edinburgh University Press; 1990; pp. 210-212.
"Developing NeXTSTEP.TM. Applications," SAMS Publishing; 1995; pp. 118-144.
Rabiner et al., "High Performance Connected Digit Recognition Using Hidden Markov Models," Proceedings of ICASSP-88, 1998; pp. 320-330.
Moulines, Eric, and Francis Charpentier, "Pitch-Synchronous Waveform Processing Techniques for Text-To-Speech Synthesis Using Diphones," Speech Communications 9; 1990; pp. 453-467.
Breckenridge Pierrehumbert, Janet, "The Pholology and Phonetics of English Intonation," Massachusetts Institute of Technology, Sep. 1980, pp. 1-401.

Affiliated with

Also associated with

Rating

Method and system for speech recognition using continuous densit does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and system for speech recognition using continuous densit, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for speech recognition using continuous densit will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1130821