Method of speaker adaptive speech recognition

Electrical audio signal processing systems and devices – One-way audio signal program distribution – Public address system

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

381 41, G10L 506, G10L 500

Patent

active

051704323

ABSTRACT:
A method for recognizing spoken words of a speech includes extracting feature vectors from a speech signal which corresponds to a spoken phrase, and segmenting and classifying the successive extracted feature vectors into syllable oriented word subunits by means of a stored supply of word subunits to form a set of hypotheses. The set of hypotheses is used to generate, by three dimensional time dynamic comparision, a set of word hypotheses by comparing the segmented and classified word subunits with standard pronunciations and pronunciation variants of a plurality of words stored in a reference pattern vocabulary. The generated set of word hypotheses are then subjected to syntactic analysis to determine the spoken phrase.

REFERENCES:
patent: 4748670 (1988-05-01), Bahl et al.
patent: 4780906 (1988-10-01), Rajasekaran et al.
patent: 4866778 (1989-09-01), Baker
patent: 4882757 (1989-11-01), Fisher et al.
patent: 4941178 (1990-07-01), Chuang
Speech Technology, vol. 4, No. 4 Apr./May 1989, "Progress in Large Vocabulary Speech Recognition," by F. Fallside, pp. 14-15.
Lexical Access And Verification In A Broad Phonetic Approach To Continuous Digit Recognition, F. R. Chen pp. 21.7.1-21.7.4, IEEE ICASSP (1986).
A Coarse Phonetic Knowledge Source for Template Independent Large Vocabulary Word Recognition, H. La-ger & A. Waibel pp. 23.6.1-23.6.3, IEEE ICASSP (2), (1985).
"Fast Feature-Based Preclassification of Segments In Continuous Digit Recognition" D. Lubensky & W. Feix, pp. 21.6.1-21.6.4, IEEE ICASSP, (1986).
Int. Conf. on Dig. Signal Proc., "Three-Dimensional DP for Phonetic Lattice Matching", G. Micca, R. Pieraccini & P. Laface, (1987), Fierence, Italy.
Fesseler et al., "Automatic Vocabulary Extension for a Speaker-Adaptive Speech Recognition System based on CVC Units", Eurospeech 89, Stuttgart, Germany, Sep. 1989, pp. 075-078.
Su, "Acoustic-Phonetic Recognition of Continuous Speech Using Vector Quantization; Adaptation of the Dictionary to a Speaker", Signal Processing, No. 4, Jun. 1988, pp. 388-389.
Togawa et al., "Voice-Activated Word Processor with Automatic Learning for Dynamic Optimization of Syllable-Templates", ICASSP 86 Proceedings, Apr. 1986, Tokyo, Japan, pp. 1121-1124.

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

Method of speaker adaptive speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method of speaker adaptive speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of speaker adaptive speech recognition will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-965706

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