Large vocabulary continuous speech recognition using HTK

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

Volumn 2, Issue , 1994, Pages II125-III128

  Woodland, P C ^a   Odell, J J ^a   Valtchev, V ^a   Young, S J ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DECISION TREES; SIGNAL PROCESSING;

CAMBRIDGE UNIVERSITY; CONTINUOUS DENSITY HIDDEN MARKOV MODELS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MIXTURE DENSITY; PORTABLE SOFTWARE; SPEECH RECOGNITION SYSTEMS; STATE CLUSTERING; WALL STREET JOURNAL;

HIDDEN MARKOV MODELS;

EID: 84926060821     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389562     Document Type: Conference Paper

References (7)

1. Hwang M-Y., Huang X. & Alleva F. (1993). Predicting Unseen Triphones with Senones. Proc. ICASSP'93, Vol II, pp. 311-314, Minneapolis.
2. Ney H., Haeb-Umbach R, Tran B-H. & Oerder M. (1992). Improvements in Beam Search for 10000-Word Continuous Speech Recognition. Proc. ICASSP'92, Vol I, pp. 9-12. San Francisco.
3. Woodland P.C. & Young S.J. (1992) Benchmark DARPA RM Results with the HTK Portable HMM Toolkit. Proc. DARPA Continuous Speech Recognition Workshop, September 1992, Stanford.
4. Woodland P.C. & Young S.J. (1993) The HTK Tied-State Continuous Speech Recogniser. Proc. Eu-rospeech'93, Berlin.
5. Young S.J. (1992). The General Use of Tying in Phoneme-Based HMM Speech Recognisers. Proc. ICASSP'92, Vol I, pp. 569-572. San Francisco.
6. Young, S.J., Woodland P.C. & Byrne W.J. (1993). HTK Version 1.5: User, Reference & Programmer Manual. Cambridge University Engineering Department & En-tropic Research Laboratories Inc., September 1993.
7. Young S.J. & Woodland P.C. (1993). The Use of State Tying in Continuous Speech Recognition. Proc. Eu-rospeech'93, Berlin.