STATE TYING OF TRIPHONE HMM'S FOR THE 1994 AT&T ARPA ATIS RECOGNIZER

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

Volumn , Issue , 1995, Pages 1499-1502

  Bocchieri, Enrico ^a   Riccardi, Giuseppe ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; SPEECH COMMUNICATION;

CONTROLLED EXPERIMENT; HIDDEN-MARKOV MODELS; MERGING ALGORITHMS; MODEL RESOLUTION; MODEL STATE; OBJECTIVE CRITERIA; ROBUST ESTIMATE; SPOKEN LANGUAGES; TOTAL DISTORTION; TRIPHONES;

MERGING;

EID: 0001567771     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Bocchieri, E. L., Riccardi, G., Anantharaman, J., "The 1994 AT & TATIS CHRONÜS recognizer", Proceedings of the ARPA Spoken language Systems Technology Workshop, Austin, Jan 95, pp 265-268, Morgan-kaufman Publishers.
2. M. Y. Hwang and X.Huang, "Shared-Distribution Hidden Markov Models for Speech Recognition, " IEEE Proc. on Speech and Audio Processing, Vol 1, NO. 4, Oct 1993 pp 414-420.
3. Young, S. J., Woodland, P.O. "The Use of State Tying in Continuous Speech Recognition," Proc. Eurospeech-93 pp 2203-2206.
4. Young S. J., Odell J. J, and Woodland P.O., "Tree-Based State Tying For High Accuracy Acoustic Modelling," Proc Arpa Human Language Technology Workshop, March 1994, pp. 307-312, Morgan Kaufman.
5. Riccardi, G., Bocchieri, E. L., Pieraccini, R., "Non deterministic Stochastic Language Models for Speech Recognition " Proc. of IEEE ICASSP-95, Vol 1, pp 237-240.