Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1996-06-18
1998-09-22
Hudspeth, David R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704245, 704255, 704236, 704244, 704243, G10L 506
Patent
active
058129758
ABSTRACT:
A method of designing a state transition model capable of high speed voice recognition and a voice recognition method and apparatus using the state transition model is provided. The methods provide a state transition model in which a state shared structure of the state transition model is designed. The method includes a step of setting the states of a triphone state transition model in an acoustic space as initial clusters, a clustering step of generating a cluster containing the initial clusters by top-down clustering, a step of determining a state shared structure by assigning a short distance cluster among clusters generated by the clustering step, to the state transition model, and a step of learning a state shared model by analyzing the states of the triphones in accordance with the determined state shared structure.
REFERENCES:
patent: 4156868 (1979-05-01), Levinson
patent: 4817156 (1989-03-01), Bahl et al.
patent: 4918731 (1990-04-01), Muroi
patent: 5050215 (1991-09-01), Nishimura
patent: 5073939 (1991-12-01), Vensko et al.
patent: 5165007 (1992-11-01), Bahl et al.
patent: 5220629 (1993-06-01), Kosaka et al.
patent: 5307444 (1994-04-01), Tsuboka
patent: 5381514 (1995-01-01), Aso et al.
patent: 5444817 (1995-08-01), Takizawa
patent: 5506933 (1996-04-01), Nitta
patent: 5515475 (1996-05-01), Gupta et al.
patent: 5535305 (1996-07-01), Acero et al.
patent: 5608841 (1997-03-01), Tsuboka
patent: 5615286 (1997-03-01), Patel
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5638489 (1997-06-01), Tsuboka
S.J. Young & P.C. Woodland, "The Use of State Tying in Continuous Speech Recognition," Eurospeech 93, pp. 2203-2206.
J. Takami & S. Sagayama, "Automatic Generation of Hidden Markov Networks by a Successive State Splitting Algorithm," Institute of Electronics, Information and Communication Engineers, vol. J76-D11, No. 10, pp. 2155-2164, 1993 (Japanese language), together with English equivalent, A successive State Splitting Algorithm for Efficient Allophone Modeling, IEEE, 992, pp. I573-576.
S. Takahashi & Sagayama, "Phoneme HMMs Four-Level Tied-Structure," Institute of Electronics, Information and Communication Engineers, SP94-73, pp. 25-32, 1994 (Japanese language, together with English equivalent, Four-Level Tied-Structure for Efficient Representation of Acoustic Modeling, IEEE 1995, pp. 520-523.
J. Takami, "Improvement in Representing Efficiency of Hidden Markov Networks by a State Splitting Merging Algorithm," Acoustic Society of Japan, 1-8-4, pp. 7-8, 1994 (Japanese language only).
ICASSP 88 vol. I, Apr. 11-14, 1988, Large-Vocabulary Speaker-Independent Continuous Speech Recognition Using HMM, Lee, et al. (pp. 123-126).
ICASSP 92, vol. I, Mar. 23-26, 1992, Subphonetic Modeling with Markov States--Senone, Hwang, et al., (pp. I33-I36).
ICASSP 89 vol. I, May 23-26, 1989, "Tied Mixture Continuous Parameter Models for Large Vocabulary Isolated Speech Recognition", Bellegarda, et al. (pp. 13-16).
ICASSP 89, "The Lincoln Robust Continuous Speech Recognizer" Douglas B. Paul, (pp. 449-451).
Van Trees ("detection, Estimation, and Modulation Thoery", Part I, John Wiley &Sons, Jan.1968, pp. 26-29, 126-127).
Komori Yasuhiro
Ohora Yasunori
Canon Kabushiki Kaisha
Chawan Vijay B.
Hudspeth David R.
LandOfFree
State transition model design method and voice recognition metho does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with State transition model design method and voice recognition metho, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and State transition model design method and voice recognition metho will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1635070