Patent
1994-01-19
1997-04-15
MacDonald, Allen R.
395 266, 395759, G10L 506, G10L 900
Patent
active
056218591
ABSTRACT:
The invention provides a method of large vocabulary speech recognition that employs a single tree-structured phonetic hidden Markov model (HMM) at each frame of a time-synchronous process. A grammar probability is utilized upon recognition of each phoneme of a word, before recognition of the entire word is complete. Thus, grammar probabilities are exploited as early as possible during recognition of a word. At each frame of the recognition process, a grammar probability is determined for the transition from the most likely preceding grammar state to a set of words that share at least one common phoneme. The grammar probability is combined with accumulating phonetic evidence to provide a measure of the likelihood that a state in the HMM will lead to the word most likely to have been spoken. In a preferred embodiment, phonetic context information is exploited, even before the complete context of a phoneme is known. Instead of an exact triphone model, wherein the phonemes previous and subsequent to a phoneme are considered, a composite triphone model is used that exploits partial phonetic context information to provide a phonetic model that is more accurate than aphonetic model that ignores context. In another preferred embodiment, the single phonetic tree method is used as the forward pass of a forward/backward recognition process, wherein the backward pass employs a recognition process other than the single phonetic tree method.
REFERENCES:
patent: 4741036 (1988-04-01), Bahl et al.
patent: 4748670 (1988-05-01), Bahl et al.
patent: 4984178 (1991-01-01), Hemphill et al.
patent: 5075896 (1991-12-01), Wilcox et al.
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5349645 (1994-09-01), Zhao
patent: 5457768 (1995-10-01), Tsuboi et al.
Placeway et al., "The estimation of powerful language models from small and large corpora", 1993 IEEE international conference on Acoustics, Speech and Signal processinn (ICASSP 93); pp.33-36 vol. 2 Apr. 1993.
Schukat-Talamazzini et al., "Acoustic modelling of subword units in the lsadora speech recognizer", 1992 IEEE International conference on Acoustics, Speech and Signal processing, (ICASSP 92), pp. 577-580 Mar. 1992.
S. J. Young, "The general use of typing in phoneme-based HMM speech recognisers", 1992 IEEE international conference on Acoustics, Speech and Signal processing (ICASSP 92), pp. 569-572 vol. 1 Mar. 1992.
H. Ney et al., A Data-Driven Organization of the Dynamic Programming Beam Search for Continuous Speech Recognition, Proceedings: ICASSP 87, IEEE, vol. 2 of 4, pp. 833-836.
H. Ney et al., Improvements in Beam Search for 10000-Word Continuous Speech Recognition, Proceedings 1991 IEEE Workshop on Automatic Speech Recognition, IEEE, pp. 76-77.
H. Ney et al., Improvements in Beam Search for 10000-Word Continuous Speech Recognition, 1992 IEEE, pp. I-9--I-12.
P. Placeway et al., The Estimation of Powerful Language Models from Small and Large Corpora, IEEE International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, MN, Apr. 27-30, 1993, pp. II-33-36.
X.L. Aubert, A Fast Lexical Selection Strategy for Large Vocabulary Continuous Speech Recognition, Speech Recognition and Understanding. Recent Advances, Trends and Applications, NATO ASI Series, vol. F75, pp. 165-170.
Nguyen Long
Schwartz Richard M.
BBN Corporation
Dorvil Richemond
MacDonald Allen R.
LandOfFree
Single tree method for grammar directed, very large vocabulary s does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Single tree method for grammar directed, very large vocabulary s, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Single tree method for grammar directed, very large vocabulary s will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-368347