Class-based word clustering for speech recognition using a three

Details Class-based word clustering for speech recognition using a three Class-based word clustering for speech recognition using a three

1996-04-18

1998-11-10

MacDonald, Allen R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704 9, 704 10, 704256, G10L 300

Patent

active

058358935

ABSTRACT:
In a word clustering apparatus for clustering words, a plurality of words is clustered to obtain a total tree diagram of a word dictionary representing a word clustering result, where the total tree diagram includes tree diagrams of an upper layer, a middle layer and a lower layer. In a speech recognition apparatus, a microphone converts an input utterance speech composed of a plurality of words into a speech signal, and a feature extractor extracts predetermined acoustic feature parameters from the converted speech signal. Then, a speech recognition controller executes a speech recognition process on the extracted acoustic feature parameters with reference to a predetermined Hidden Markov Model and the obtained total tree diagram of the word dictionary, and outputs a result of the speech recognition.

REFERENCES:
patent: 5040127 (1991-08-01), Gerson
Lalit R. Bahl, Peter F. Brown, Peter V. deSouza, and Robert L. Mercer, "A Tree-Based Statistical Language Model for Natural Language Speech Recognition", IEEE Trans. on ASSP, vol. 37, No. 7, pp. 1001-1008, Jul. 1989.
Ave Wrigley, "Parse Tree N-Grams for Spoken Language Modeling," IEE Colloquium No. 092, Grammatical Inference: Theory, Application and Alternatives, 1993.
Masafumi Tamoto and Takeshi Kawabata, "Clustering Word Category Based in Binomial Posteriori Co-Occurrence Distribution", Proc. IEEE ICASSP 95, pp. 165-168, May 1995.
Klaus Ries, Finn Dag Buo, and Ye-Yi Wang, "Improved Langauge Modeling by Unsupervised Acquisition of Structure," IEEE ICASSP 95, pp. 193-196, May 1995.
Sven Martin, Jorg Liermann, and Hermann Ney, "Algorithms for Bigram and Trigram Word Clustering," Proc. 4th European Conf. on Speech Comm. and Technology (Eurospeech 95), pp. 1253-1256, Sep. 1995.
Joerg P. Ueberla, "More Efficient Clustering of N-Grams for Statistical Language Modeling", Proc. 4th European Conf. on Speech Comm. and Technology (Eurospeech 95), pp. 1257-1260, Sep. 1995.
Michele Jardino, "Multilingual Stochastic N-Gram Class Language Models," Proc. IEEE ICASSP 96, pp. 161-163, May 1996.
Jerome R. Bellegarda, John W. Butzberger, Yen-Lu Chow, Noah B. Coccaro, and Devang Naik, "A Novel Word Clustering Algorithm Based on Latent Semantic Analysis," Proc. IEEE ICASSP 96, pp. 172-175, May 1996.
Azarshid Farhat, Jean-Francois Isabelle, and Douglas O'Shaughnessy, "Clustering Words for Statistical Language Models Based on Contextual Word Similarity," IEEE ICASSP 96, pp. 180-183, May 1996.
John W. Miller and Fil Alleva, "Evaluation of a Language Model using a Clustered Model Backoff," 4th Intl. Conf. on Spoken Language Processing (ICSLP 96), Oct. 1996.
"Mutual Information-Based Word Clustering", Proceedings on the Symposium of the Training in Natural Language Processing, the Institute of Electronics, Information and Communication Engineers in Japan pp. 104-111, Dec. 30, 1994 by Hideki Kashioka, et al.
"Class-Based n-gram Models of Natural Language", by Peter F. Brown et al, Computational Linguistics vol. 18, No. 4, pp. 467-479, 1992.
"Automatically Acquiring Phrase Structure Using Distributional Analysis", Darpa Workshop on Speech and Natural Language, Harriman, NY pp. 155-159, Feb., 1992 by Eric Brill, et al.
"Improved Clustering Techniques for Class-Based Statistical Language Modelling", Proceedings of European Conference on Speech Communication and Technology, vol., 2, pp. 973-976, Sep. 21, 1993 by Reinhard Kreser and Hermann Ney Missing pp. 973-974.

Affiliated with

Also associated with

Rating

Class-based word clustering for speech recognition using a three does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Class-based word clustering for speech recognition using a three, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Class-based word clustering for speech recognition using a three will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1528804