Genones: Optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 1994, Pages I537-I540

  Digalakis, V ^a   Murveit, H ^a  

^a SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLUSTER ANALYSIS; MIXTURES; SIGNAL PROCESSING;

AGGLOMERATIVE CLUSTERING; ERROR RATE; LARGE VOCABULARY; MIXTURE COMPONENTS; OUTPUT DISTRIBUTION; SPEECH RECOGNIZER; TIED-MIXTURES; WALL STREET JOURNAL;

HIDDEN MARKOV MODELS;

EID: 33646934294     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389212     Document Type: Conference Paper

References (17)

1. L. R. Rabiner, B. H. Juang, S. E. Levinson. and M. M. Sondhi, "Recognition of Isolated Digits Using Hidden Markov Models with Continuous Mixture Densities," Bell Systems Tech Journal, Vol. 64(6), pp. 1211-34, 1985.
2. X. D. Huang, and M. A. Jack, "Performance Comparison Between Semi-continuous and Discrete Hidden Markov Models," IEEElecrronics Letrers, Vol. 24 no. 3, pp. 149-150.
3. I. R. Bellegarda and D. Nahamoo, "Tied Mixture Continuous Parameter Modeling for Speech Recognition," IEEE Truns. ASSP, Vol. 38(12), pp 2033-2045, Dec. 1990.
4. C. Lee, L. Rabiner, R. Pieraccini and J. Wilpon, "Acoustic Modeling for Large Vocabulary Speech Recognition," ComputerSpeech undLangge, April. 1990, pp. 127-165.
5. D. Pallett, "Results for the Sept. 1992 Resource Management Benchmark," DARPA Workshop on Artijiciul Neurul Networks and CSR, Sept. 1992.
6. O. Kimball and M. Ostendorf. "On the Use of Tied-Mixture Distributions," Pmc. ARPA HLT Workshop, March 1993.
7. D. B. Paul and E. A. Martin, "Speaker Stress-resistant Continuous Speech Recognition." Proc. ICASSP, pp. 283-286, April 1988.
8. K. F. Lee, "Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speec.h Recognition," IEEE Tram. ASSE pp. 599-609, April 1990.
9. L. R. Bahl, P. V. de Souza, P. S. Gopdakrishnan, D. Nahamoo and M. A. Picheny, "Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees," DARPA Workshop on Speech and Natural Language. pp, 264-269, February 1991.
10. M.-Y. Hwang and X. D. Huang, "Subphonetic Modeling with Markov States-Senone," Proc. ICASSP, pp. 1-33-36, March 1992.
11. H. Murveif J. Butzberger, V. Digalakis and M. Weintraub, "Large Vocabulary Dictation using SRI's DECIPHERTM Speech Recognition System: Progressive Search Techniques," Pmc. ICASSP, pp. 11.319-E-322, April 1993.
12. S. J. Young, "The General Use of ping in Phoneme-Based HMM Speech Recognizers," Proc. ICASSP. pp. 1.569-I-512, March 1992.
13. R. Haeb-Umbach and H. Ney, "Linear Discriminant Analysis for Improved Large Vocabulary Continuous Speech Recognition," Proc. ICASSP, pp. 1-13-1-16, March 1992.
14. J. L. Gauvain and C. H. Lee, "Bayesian Learning of Gaussian Mixture Densities for Hidden Markov Models," Proc. DARPA Speech und Nuturul Lunguage Workshop. Feb. 1991.
15. V. Digalakis, P. Monaco and H. Murveit, "Acoustic Calibration and Search in SRI's Large Vocabulary HMM-based Speech Recognition System." Proc. IEEE ASR Workshop, Snowbird, Dec. 1993.
16. K. E Lee and H. W. Hon. "Speaker Independent Phone Recognition Using Hidden Markov Models." IEEE Truns. ASSR pp. 1641-1648,1989
17. D. Pallet, I. G. Fiscus, W. M. Fisher, and J. S. Garofolo, "Benchmark Tests for the DARPA Spoken Language Program," HLT Workshop, Princeton, March 1993.