System and method for generating and using context dependent sub

Details System and method for generating and using context dependent sub System and method for generating and using context dependent sub

1995-01-26

1997-10-21

Zele, Krista M.

395 263, 395 265, G10L 506

Patent

active

056805101

ABSTRACT:
A speech recognition system for Mandarin Chinese comprises a preprocessor, HMM storage, speech identifier, and speech determinator. The speech identifier includes pseudo initials for representing glottal stops that precede syllables of lone finals. The HMM storage stores context dependent models of the initials, finals, and pseudo initials that make the syllables of Mandarin Chinese speech. The models may be dependent on associated initials or finals and on the tone of the syllable. The speech determinator joins the initials and finals and pseudo initials and finals according to the syllables of the speech identifier. The speech determinator then compares input signals of syllables to the joined models to determine the phonetic structure of the syllable and the tone of the syllable. The system also includes a smoother for smoothing models to make recognitions more robust. The smoother comprises an LDM generator and a detailed model modifier. The LDM generator generates less detailed models from the detailed models, and the detailed model modifier smoothes the models with the less detailed models. A method for recognizing Mandarin Chinese speech includes the steps of arranging context dependent, sub-syllable models; comparing an input signal to the arranged models; and selecting the arrangement of models that best matches the input signal to recognize the phonetic structure and tone of the input signal.

REFERENCES:
patent: 4803729 (1989-02-01), Baker
patent: 4831551 (1989-05-01), Schalk et al.
patent: 4985924 (1991-01-01), Matsuura
patent: 5027408 (1991-06-01), Kroeker et al.
patent: 5054084 (1991-10-01), Tanaka et al.
patent: 5164900 (1992-11-01), Bernath
patent: 5195167 (1993-03-01), Bahl et al.
patent: 5212638 (1993-05-01), Bernath
patent: 5220639 (1993-06-01), Lee
patent: 5329608 (1994-07-01), Bocchieri et al.
patent: 5450523 (1995-09-01), Zhao
patent: 5473728 (1995-12-01), Luginbuhl et al.
Lin, Chih-Heng et al., "A New Framework For Recognition Of Mandarin Syllables With Tones Using Sub-Syllabic Units" 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr. 27-30, 1993: Speech Processing/vol. II of V (pp. II-227-II 230).
Hon, Hsiao-Wuen et al.; "Towards Large Vocabulary Mandarin Chinese Speech Recognition", 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr. 19-22, 1994: Speech Processing 1/vol. 1 (I-545--I-548).
Giachin, E. et al., "Word Juncture Modeling Using Inter-Word Context-Dependent Phone-Like Units", Cselt Technical Reports, Mar. 1992: vol. XX -No. 1 (pp. 43-47).
Wang, Hsin-min et al., "An initial Study On Large Vocabulary Continuous Mandarin Speech Recognition With Limited Training Data Based On Sub-Syllabic Models", International Computer Symposium 1994., Dec. 12-15: vol. 2 (pp. 1140-1145).
Lawrence Rabiner & Bing-Hwang Juang, Fundamentals of Speech Recognition, pp. 461-464, date not provided.
W. Yang, et al., Hidden Markov Model for Mandarin Lexical Tone Recognition, Jul. 1988, IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 36, pp. 988-992.
L. Lee, et al., Golden Mandarin (II)--an improved single-chip real-time Mandarin dictation machine for Chinese language with very large vocabulary, Proceedings Int. Conf. Acoustics, Speech & Signal Processing, 1993, vol. II, pp. 503-506.
Schwartz & Chow, The N-Best Algorithm: An Efficient and Exact Procedure for Finding the N Most Likely Sentence Hypotheses, 1990, IEEE, pp. 81-84.
F. Jelinek & R. Mercer, Interpolated Estimation of Markov Source Parameters from Sparse Data, in Pattern Recognition in Practice, edited by E. Gelsema & L Kanal, 1980 pp. 381-397.
Y. Wang, S. Chen & J. Shieh, Tone Recognition of Continuous Mandarin Speech Based on Hidden Markov Model, 1994, International Journal of Pattern Recognition and Artificial Intelligence vol. 8, pp. 233-245.

Affiliated with

Also associated with

Rating

System and method for generating and using context dependent sub does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System and method for generating and using context dependent sub, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for generating and using context dependent sub will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1013624