Patent
1993-03-15
1996-11-26
Knepper, David D.
395 265, 395 245, G10L 504, G10L 506
Patent
active
055794360
ABSTRACT:
A system pattern-based speech recognition, e.g., a hidden Markov model (HMM) based speech recognizer using Viterbi scoring. The principle of minimum recognition error rate is applied by the present invention using discriminative training. Various issues related to the special structure of HMMs are presented. Parameter update expressions for HMMs are provided.
REFERENCES:
patent: 4817156 (1989-03-01), Bahl et al.
patent: 5280563 (1994-01-01), Ganong
patent: 5315689 (1994-05-01), Kanazawa et al.
Chou Wu
Juang Biing-Hwang
Brown Kenneth M.
Knepper David D.
Lucent Technologies - Inc.
Restaino Thomas A.
LandOfFree
Recognition unit model training based on competing word and word does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Recognition unit model training based on competing word and word, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Recognition unit model training based on competing word and word will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1979915