COMPARATIVE EVALUATION OF SEGMENTAL UNIT INPUT HMM AND CONDITIONAL DENSITY HMM

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 1615-1618

  Yamamoto, Kazumasa ^a   Nakagawa, Seiichi ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

COVARIANCE MATRIX; SPEECH COMMUNICATION;

COMPARATIVE EVALUATIONS; CONDITIONAL DENSITY; DYNAMIC CHANGES; DYNAMIC FEATURES; ESTIMATION OF COVARIANCE MATRIXES; MODIFIED QUADRATIC DISCRIMINANT FUNCTIONS; RECOGNITION METHODS; REGRESSION COEFFICIENT; TIME VARIANT FEATURES;

SPEECH RECOGNITION;

EID: 0011453543     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. E. Tsuboka, Y. Takada and H.Wakita: Neural predictive hidden Markov model, Proc. ICSLP, pp.l341-1344 (1990)
2. L. Deng, M. Aksmanoric, X. Sun and C. F. J. Wu: Speech recognition using hidden Markov models with polynomial regression functions as non stationary states, IEEE Trans. Speech & Audio Process., Vol.2, No.4, pp.507-520 (1994)
3. S.Nakagawa, Y.Hirata and Y. Ono: Syllable recognition by hidden Markov models using fixed-length segmental statistics, Trans. Inst. Elect. Inform. Comm., Vol. J75-DII, No.5, pp.843-851 (1992, in Japanese).
4. F. J. Smith, J. Ming, P.O'Boyle and A.D. Irvine: A hidden Markov model with optimized inter-frame dependence, Proc. ICASSP, pp.209-212 (1995)
5. K.Aikawa, H.Singer, H.Kawahara and Y.Tohkura: A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition. Proc. ICASSP, pp.II-668-II-671 (1993)
6. S. Nakagawa and Y.Enomoto: Speaker-independent phoneme and word recognition by statistical classification methods for time-sequential pattern. Trans. Inst. Elect. Inform. Comm., Vol. J71-D, No.lO, pp.1977-1983 (1988, in Japanese)
7. R. Haeb-Umbach and H. Ney: Linear discriminant analysis for improved large vocabulary continuous speech recognition, Proc. ICASSP, pp.I-13-I-16 (1992)
8. L. R. Bahl et al: Performance of the IBM large vocabulary continuous speech recognition system on the ARPA wall street journal task, Proc. ICASSP, pp.41-44 (1995)
9. J. He and H. Leich: A unified way in incorporating segmental feature and segmental model into HMM, Proc. ICASSP, pp.532-535 (1995)
10. W. J. Holmes and M. J. Russell: Experiment evaluation of segmental HMMs, Proc. ICASSP, pp.536-539 (1995)
11. F. Kimura, K. Takashina, S. Tsuruoka and Y. Miyake: Modified quadratic discriminant function and the application to Chinese character recognition, IEEE Trans, of Pattern Anal, k Mach. Intell., Vol. PAMI-9, No.l, pp.149-153 (1987)
12. C.J.Wellekens: Explicit correlation in hidden Markov model for speech recognition. Proc. ICASSP, pp.383-386 (1987).
13. P.F. Brown: The acoustic-modeling problem in automatic speech recognition, Ph.D. thesis, Carnegie-Mellon University (1987).
14. S.Takahashi, T.Matsuoka, Y.Minami and K.Shikano: Phoneme HMMs constrained by frame correlations, Proc. ICASSP, pp. 11-219-222 (1993).