THE USE OF STATE TYING IN CONTINUOUS SPEECH RECOGNITION

3rd European Conference on Speech Communication and Technology, EUROSPEECH 1993

Volumn , Issue , 1993, Pages 2203-2206

  Young, S J ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

HMM state clustering phone recognition TIMIT HTK

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION;

BALANCE MODEL; CLUSTERINGS; CONTEXT DEPENDENT; GAUSSIAN-MIXTURES; HMM STATE CLUSTERING PHONE RECOGNITION TIMIT HTK; MODELING COMPLEXITY; OPERATIONAL PROPERTIES; PHONE RECOGNITION; POSTERIORI; STATE CLUSTERING;

TELEPHONE SETS;

EID: 85135369802     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Bahl LR, de Souza PV, Gopalakrishnan PS, Nahamoo D, Picheny MA. Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees. Proc DARPA Speech and Natural Language Processing Workshop, pp264-270, Pacific Grove, Calif, Feb, 1991
2. Gauvain L, Lee C-H. Bayesian Learning for Hidden Markov Model with Gaussian Mixture State Observation Densities. Speech Communication, Volume 11, Nos 2-3, (Eurospeech '91), pp205-214, 1992
3. Hwang M-Y, Huang X. Subphonetic Modeling with Markov States - Senone. Proc ICASSP, Vol 1, pp33-36, San Francisco, 1992
4. Lee K-F. Context-Dependent Phonetic Hidden Markov Models for Speaker Independent Continuous Speech Recognition. IEEE Irans ASSP, Vol 38, No 4, pp599-609, 1990
5. Lee K-F, Hon H-W. Speaker Independent Phone Recognition Using Hidden Markov Models. IEEE Trans ASSP, Vol 37, No 11, ppl641-1648, 1989
6. Rabiner LR, Juang B-H, Levinson SE, Sondhi MM. Recognition of Isolated Digits Using HMMs with Continuous Mixture Densities. AT&T Technical J, Vol 64, No 6, ppl211-1233, 1985
7. Robinson AJ. Several Improvements to a Recurrent Error Propagation Network Phone Recognition System. Cambridge University Engineering Dept, Technical Report, C U E D/F - I N F E N G/T R. 8 2, 1991
8. Woodland PC, Young SJ. Benchmark DARPA RM Results with the HTK Portable HMM Toolkit. Proc DARPA Continuous Speech Recognition Workshop, Stanford, Sept, 1992
9. Woodland PC, Young SJ. The HTK Tied State Continuous Speech Recogniser. Proc Eurospeech, Berlin, Sept, 1993
10. Young SJ. The General Use of Tying in Phoneme-Based HMM Speech Recognisers. Proc ICASSP, S66.5, San Francisco, March, 1992
11. Young SJ. HTK Version l.j.: User, Reference and Programmer Manual. Cambridge University Engineering Dept, Speech Group, August, 1992