MULTI-PHONE STRINGS AS SUBWORD UNITS FOR SPEECH RECOGNITION

5th International Conference on Spoken Language Processing, ICSLP 1998

Volumn , Issue , 1998, Pages

  O'Neill, P ^a   Vaseghi, S ^a   Doherty, B ^a   Tan, W H ^a   McCourt, P ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNITION;

CONTEXT DEPENDENT; CONTEXTUAL INFORMATION; ENVIRONMENTAL VARIATIONS; EXPANDABILITY; LONG DURATION; MODEL-BASED OPC; MONOPHONES; SPEAKER VARIATION; SUBWORD MODELING; SUBWORD UNITS;

TELEPHONE SETS;

EID: 33645777455     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. S. Young (1996), "A Review of Large-Vocabulary Continuous-Speech Recognition", IEEE Signal Processing Magazine, Vol. 13, No. 5, pp. 45-57.
2. Lee K-F. (1990)”Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition”, IEEE Trans. ASSP, Vol. 38, No. 4, Pages 599-609.
3. Jershaw D. J., Phonetic Context-Dependency in a Hybrid ANN/HMM Speech recognition System, PhD Thesis Cambridge University 1997.
4. Odell J. J. The Use of Context in Large Vocabulary Speech Recognition, PhD Thesis, Cambridge University 1995.
5. Linguistic Data Consortium, http://www.ldc.upenn.edu