Tied posteriors: An approach for effective introduction of context dependency in hybrid NN/HMM LVCSR

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

Volumn 3, Issue , 2000, Pages 1241-1244

  Rottland, Jörg ^a   Rigoll, Gerhard ^a  

^a UNIVERSITY OF DUISBURG ESSEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

DEEP NEURAL NETWORKS; MIXTURES; NEURAL NETWORKS; SIGNAL PROCESSING; SPEECH PROCESSING; ESTIMATION; LEARNING SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY;

A-POSTERIORI PROBABILITIES; CLUSTERING TECHNIQUES; CONTEXT DEPENDENCY; CONTEXT-DEPENDENT MODELS; HYBRID APPROACH; HYBRID FRAMEWORK; SPEECH RECOGNITION SYSTEMS; WALL STREET JOURNAL;

SPEECH RECOGNITION;

CONTEXT DEPENDENCY; HIDDEN MARKOV MODEL; TIED POSTERIOR;

EID: 0033692963     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2000.861800     Document Type: Conference Paper

References (9)

1. H. Bourlard and N. Morgan. Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, 1994.
2. A. J. Robinson. An Application of Recurrent Nets to Phone Probability Estimation. IEEE Transactions on Neural Networks, 5(2):298-305, March 1994.
3. J. Fritsch, M. Finke, and A. Waibel. Contextdependent hybrid HME/speech recognition using polyphone clustering decision trees. In Proc. ICASSP, pages 1759-1762, 1997.
4. X. D. Huang and M. A. Jack. Semi-continuous hidden Markov models for speech signals. Computer Speech and Language, 3(3):239-251, May 1989.
5. H. P. Hutter. Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition. In Proc. ICASSP, pages 3311-3314, 1995.
6. D. B. Paul and J. M. Baker. The Design for the Wall Street Journal-based CSR Corpus. In Proc. of the DARPA Speech and Natural Language Workshop, pages 357-362, Pacific Grove, CA, 1992. Morgan Kaufmann.
7. D. Johnson. ftp://ftp.icsi.berkeley.edu/pub/real/davidj/quicknet-v0.96.tar.gz.
8. J. Wawrzynek, K. Asanović, B. Kingsbury, D. Johnson, J. Beck, and N. Morgan. Spert-II: A Vector Microprocessor System. Computer, 29(3):79-86, March 1996.
9. D. S. Pallett, J. G. Fiscus, W. M. Fisher, J. S. Garofolo, B. A. Lund, and M. A. Przybocki. 1993 Benchmark Tests for the ARPA Spoken Language Program. In Proc. of the Human Language Technology Workshop, pages 49-74, Plainsboro, New Jersey, March 1994.