Error corrective mechanisms for consensus decoding of speech

Details Error corrective mechanisms for consensus decoding of speech Error corrective mechanisms for consensus decoding of speech

2005-02-22

2005-02-22

McFadden, Susan (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S251000

Reexamination Certificate

active

06859774

ABSTRACT:
Techniques are described for decreasing the number of errors when consensus decoding is used during speech recognition. A number of corrective rules are applied to confusion sets that are extracted during real-time speech recognition. The corrective rules are determined during training of the speech recognition system, which entails using many training confusion sets. A learning process is used that generates a number of possible rules, called template rules, that can be applied to the training confusion sets. The learning process also determines the corrective rules from the template rules. The corrective rules operate on the real-time confusion sets to select hypothesis words from the confusion sets, where the hypothesis words are not necessarily the words having the highest score.

REFERENCES:
patent: 5263117 (1993-11-01), Nadas et al.
patent: 5485372 (1996-01-01), Golding et al.
patent: 5638425 (1997-06-01), Meador et al.
patent: 5659771 (1997-08-01), Golding
patent: 5907839 (1999-05-01), Roth
patent: 5956739 (1999-09-01), Golding et al.
patent: 6584180 (2003-06-01), Nemoto
patent: 6684201 (2004-01-01), Brill
patent: 20020123876 (2002-09-01), Pokhariyal et al.
L.R. Bahl et al., “Constructing groups of acoustically confusable words,” ICASSP '90, vol. 1, pp. 85-88, Apr. 1990.*
M. Weintraub et al., “Neural-network based measures of confidence for word recognition,” IEEE Proc. ICASSP '97, vol. 2, pp. 887-890, 1997.*
L.R. Bahl et al., “A fast approximate acoustic match for large vocabulary speech recognition,” IEEE Trans. on Speech and Audio Processing, vol. 1, No. 1, pp. 59-67, Jan. 1993.*
A.R. Golding et al., “Combining Trigram-based and feature-based methods for context-sensitive spelling correction,” Proc. 34th Annual Meeting of the Association for Computational Linguistics, pp. 71-78, 1996.*
Mangu et al.,“Automatic rule acquisition for spelling correction, ” Proc. 14th International Conference on Machine Learning, pp. 187-193, 1997.*
Mangu et al.,“Finding consensus in speech recognition: word error minimization and other applications of confusion networks,” Computer Speech and Language 14(4), 373-400, Oct. 2000.*
Brill, Eric, “Transformation-based error-driven learning and natural language processing: A case study in part of speech tagging,” Computational Linguistics, vol. 21, pp. 543-565, 1995.*
Stolcke et al., “Combining words and speech prosody for automatic topic segmentation,” Proc. of DARPA Broadcast News Transcription and Understanding Workshop, 1999.*
Mangu et al., “Finding consensus among words: latticed based word error minimization,” Proc. of EUROSPEECH'99.*
Golding, Andrew R., “A Bayesian hybrid method for context-sensitive spelling corrections,” Proceedings of the Third Workshop on Very Large Corpora 1995.*
Bahl et al., “A Maximum Likelihood Approach to Continuous Speech Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, 179-190 (Mar. 1983).
Eric Brill, “Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part of Speech Tagging,” Computational Linguistics, vol. 21, No. 4, 1-37 (1995).
Ted Dunning, “Accurate Methods for the Statistics of Surprise and Coincidence,” Computational Linguistics, vol. 19, No. 1, 61-74 (1993).
Mangu et al., “Automatic Rule Acquisition for Spelling Correction” Computer Science Dept., Johns Hopkins University.
Mangu et al., “Finding Consensus Among Words: Lattice-Based Word Error Minimization,” Department of Computer Science, Johns Hopkins University, Baltimore, MD, Speech Technology and Research Laboratory, SRI International, Menlo Park, CA.
Mangu et al., “Finding Consensus in Speech Recognition: Word Error Minimization and Other Applications of Confusion Networks,” Computer Speech and Language 14, 373-400 (2000).
Ratnaparkhi et al., “A Maximum Entropy Model for Prepositional Phrase Attachment,” IBM Research Division, T. J. Watson Research Center, Yorktown Heights, NY.

Affiliated with

Also associated with

Rating

Error corrective mechanisms for consensus decoding of speech does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Error corrective mechanisms for consensus decoding of speech, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Error corrective mechanisms for consensus decoding of speech will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3498675