Stochastic Lexicon Modeling for Speech Recognition

IEEE Signal Processing Letters

Volumn 6, Issue 2, 1999, Pages 28-30

  Yun, Seong Jin ^a   Oh, Yung Hwan ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

Continuous speech recognition; Hidden Markov model; Lexicon

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS;

HIDDEN MARKOV MODELS (HMM); STOCHASTIC LEXICON MODELING;

CONTINUOUS SPEECH RECOGNITION;

EID: 0033079465     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/97.739004     Document Type: Article

References (5)

1. H. Ney, D. Mergel, A. Noll, and A. Paeseler, "Data driven organization of the dynamic programming beam search for continuous speech recognition," IEEE Trans. Signal Processing, vol. 40, pp. 272-281, 1992.
2. L. R. Bahl et al., "A method for the construction of acoustic Markov models for words," IEEE Trans. Speech Audio Processing, vol. 1, pp. 443-452, Oct. 1993.
3. C. Woosters and A. Stolcke, "Multiple-pronunciation lexical modeling in a speaker independent speech understanding system," in Proc. ICSLP'94, Yokohama, Japan, pp. 1366-1368.
4. T. Svendsen, F. K. Soong, and H. Purnhagen, "Optimizing baseforms for HMM-based speech recognition," Proc. Eurospeech'95, Madrid, Spain, pp. 783-785.
5. S.-J. Yun, Y.-H. Oh, and G.-C. Shin, "Improved lexicon modeling for continuous speech recognition," Proc. ICASSP'97, Munich, Germany, pp. 1827-1830.