Word hypothesizer for continuous speech decoding using stressed-

Details Word hypothesizer for continuous speech decoding using stressed- Word hypothesizer for continuous speech decoding using stressed-

1991-12-31

1994-09-20

MacDonald, Allen R.

395 264, G10L 900

Patent

active

053496450

ABSTRACT:
A word hypothesis module for speech decoding consists of four submodules: vowel center detection, bidirectional tree searches around each vowel center, forward-backward pruning, and additional short words hypotheses. By detecting the strong energy vowel centers, a vowel-centered lexicon tree can be placed at each vowel center and searches can be performed in both the left and right directions, where only simple phone models are used for fast acoustic match. A stage-wise forward-backward technique computes the word-beginning and word-ending likelihood scores over the generated half-word lattice for further pruning of the lattice. To avoid potential miss of short words with weak energy vowel centers, a lexicon tree is compiled for these words and tree searches are performed between each pair of adjacent vowel centers. The integration of the word hypothesizer with a top-down Viterbi beam search in continuous speech decoding provides two-pass decoding which significantly reduces computation time.

REFERENCES:
patent: 4882759 (1989-11-01), Bahl et al.
"A Fast Approximate Acoustic Match for Large Vocabulary Speech Recognition" by L. R. Bahl et al., pp. 156-158, Dec. 1990.
"Continuous Speech Recognition with Vowel-Context-Independent Hidden-Markov-Models for Demisyllables" by Walter Weigel, pp. 701-703, Dec. 1990.
"The Foward-Backward Search Algorithm" by Steve Austin et al., pp. 697-700, IEEE, 1991.
"Fast Look-Ahead Pruning Strategies in Continuous Speech Recognition" by Xavier L. Aubert, pp. 659-662, IEEE, 1989.
"Interaction Between Fast Lexical Access and Word Verification in Large Vocabulary Continuous Speech Recognition" by L. Fissore et al. pp. 279-282, IEEE, 1988.
"Experiments with a Speaker-Independent Continuous Speech Recognition Sytstem on the Timit Database" by Yunxin Zhao et al. pp. 697-700, Jan. 1989.
"An HMM Based Speaker-Independent Continuous Speech Recognition System with Experiments on the TIMIT Database" by Yunxin Zhao et al., pp. 333-336, Nov. 1991, IEEE.

Affiliated with

Also associated with

Rating

Word hypothesizer for continuous speech decoding using stressed- does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Word hypothesizer for continuous speech decoding using stressed-, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Word hypothesizer for continuous speech decoding using stressed- will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2430568