Speech recognition by acoustic/phonetic system and technique

Details Speech recognition by acoustic/phonetic system and technique Speech recognition by acoustic/phonetic system and technique

1987-04-03

1989-07-25

Harkcom, Gary V.

Electrical audio signal processing systems and devices

One-way audio signal program distribution

Public address system

G10L 708

Patent

active

048521809

ABSTRACT:
A speech recognition system and technique of the acoustic/phonetic type is made speaker-independent and capable of continuous speech recognition during fluent discourse by a combination of techniques which include, inter alia, using a so-called continuously-variable-duration hidden Markov vodel in identifying word segments, i.e., phonetic units, and developing proposed phonetic sequences by a durationally-responsive recursion before any lexical access is attempted. Lexical access is facilitated by the phonetic transcriptions provided by the durationally-responsive recursion; and the resulting array of word candidates facilitates the subsequent alignment of the word candidates with the acoustic feature signals. A separate step is used for aligning the members of the candidate word arrays with the acoustic feature signals representative of the corresponding portion of the utterance. Any residual work selection ambiguities are then more readily resolved, regardless of the ultimate sentence selection technique employed.

REFERENCES:
patent: 4277644 (1981-07-01), Levinson et al.
patent: 4587670 (1986-05-01), Levinson et al.
patent: 4718094 (1988-01-01), Bahl et al.
patent: 4761815 (1988-08-01), Hitchcock
patent: 4783804 (1988-11-01), Juang et al.
Bourlard et al., "Speaker Dependent Connected Speech Recognition Via Phonemic Markov Models", IEEE ICASSP 85, pp. 1213-1216.
Speech and Speaker Recognition, "A Task-Oriented Conversational Mode Speech Understanding System", S. E. Levinson et al, pp. 149-196 (1985).
IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-23, No. 1, Feb. 1975, "Motivation and Overview of SPEECHLIS: An Experimental Prototype for Speech Understanding Research", pp. 2-10, W. A. Woods.
IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-23, No. 1, Feb. 1975, "Minimum Prediction Residual Principle Applied to Speech Recognition", pp. 67-72, F. Itakura.
Computer Speech and Language, vol 1, 1986, "Continuously Variable Duration Hidden Markov Models for Automatic Speech Recognition", S. E. Levinson, pp. 29-45.
The Art of Computer Programming, D. E. Knuth, vol. 1 (pp. 230-231) and vol. 3 (pp. 506-542).

Affiliated with

Also associated with

Rating

Speech recognition by acoustic/phonetic system and technique does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition by acoustic/phonetic system and technique, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition by acoustic/phonetic system and technique will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2364781