Devices and methods for speech recognition of vocabulary words w

Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

704231, 704251, G10L 708

Patent

active

058324305

ABSTRACT:
Devices and methods for speech recognition enable simultaneous word hypothesis detection and verification in a one-pass procedure that provides for different segmentations of the speech input. A confidence measure of a target hypothesis for a known word is determined according to a recursion formula that operates on parameters of a target models and alternate models of known words, a language model and a lexicon, and feature vectors of the speech input in a likelihood ratio decoder. The confidence measure is processed to determine an accept/reject signal for the target hypothesis that is output with a target hypothesis signal. The recursion formula is based on hidden Markov models with a single optimum state sequence and may take the form of a modified Viterbi algorithm.

REFERENCES:
patent: 4489434 (1984-12-01), Moshier
patent: 4783804 (1988-11-01), Juang et al.
patent: 4827521 (1989-05-01), Bahl et al.
patent: 5033087 (1991-07-01), Bahl et al.
patent: 5271088 (1993-12-01), Bahler
patent: 5349645 (1994-09-01), Zhao
patent: 5579436 (1996-11-01), Chou et al.
patent: 5606644 (1997-02-01), Chou et al.
patent: 5617488 (1997-04-01), Hong et al.
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5638425 (1997-06-01), Meador, III et al.
"A training procedure for verifying string hypotheses in continuous speech recognition", ICASSP, Apr. 1995.
"A Hidden Markov Model Keyword Recognition System", ICASSP 1990.
"A minimax classification approach with application to roubst speech recognition", IEEE Transactions on Speech and Audio Processing, Jan. 1993.
"A Bayesian Classification approach with application to speech recognition", IEEE Transactions on Signal Processing, Jan. 1991.
Young et al., Recognition Confidence Measures for Spontaneous Spoken Dialog, "Proc. European Conf./on Speech Communications", Sep. 1993, pp. 1177-1179.
Jeanrenaud et al., Phonetic-Based Word Spotter: Various Configurations and Application to Event Spotting, "Proc. European Conf. on Speech Communications", Sep. 1993, pp. 1057-1060.
Rose et al., Techniques for Robust Word Spotting in Continuous Speech Messages, "Proc. Int. Conf. on Acoust., Speech, and Sig. Processing", Mar. 1992.
Rose et al., A Training Procedure for Verifying String Hypotheses in Continuous Speech Recognition, "Proc. Int. Conf. on Acoust., Speech, and Sig. Processing", Apr. 1995, pp. 281-284.
Chen et al., AN N-Best Candidates-Based Discriminative Training for Speech Recognition Applications, "IEEE Trans on Speech and Audio" Jan. 1994, pp. 206-216.
Chou et al., Segmental GPD Training of HMM Based Speech Recognizer, "Proc. Int. Conf. on Acoust., Speech, and Sig. Processing", Apr. 1992, pp. 473-476.
Sukkar et al., A Two Pass Classifier for Utterance Rejection in Keyword Spotting, IEEE, "Proc. Int. Conf. on Acoust., Speech, and Sig. Processing", Apr. 1993, pp. II451-II454.
Rahim et al., Robust Utterance Verification for Connected Digits Recognition, IEEE, "Proc. Int. Conf. on Acoust., Speech, and Sig. Processing", May 1995, pp. 285-288.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Devices and methods for speech recognition of vocabulary words w does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Devices and methods for speech recognition of vocabulary words w, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Devices and methods for speech recognition of vocabulary words w will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-703549

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.