Speech recognition using distance between feature vector of one

Details Speech recognition using distance between feature vector of one Speech recognition using distance between feature vector of one

Filed on

1997-10-28

Date issued

1999-09-14

Examiner

Hudspeth, David R.

Patent Class

Data processing: speech signal processing, linguistics, language

SubClass

Speech signal processing

SubSubClass

Recognition

Other Related Categories

704239, 704243, G01L 302

Type

Patent

Status

active

Patent number

059536993

Description

ABSTRACT:
A speech recognition apparatus has an analysis section that outputs features of input speech as a time sequence of feature vectors defined for discrete time points corresponding to a processed speech frame. Reference paradigm utterances are converted into a time sequence of standard (reference) feature vectors. The possible continuous variation of standard feature vectors at each point in time is expressed by a line segment, or set of line segments, connecting the feature vectors for the two end points of the "movable" range within which the feature can change, rather than using a larger set of reference vectors as in a conventional multitemplate approach to speech recognition. For example, the continuous range of possible background noise levels in input speech defines a line segment connecting the two feature vectors at the two SNR value limits. A matching apparatus calculates the distance between the input speech feature vector at each time point and the reference line segment endpoints and the perpendicular distance to the reference line segment (where meaningful), for each reference line segment corresponding to that particular time. The distance between each input feature and each standard (reference) feature sequence, represented by its line segment at a given time, is defined as the smallest of these three (or two) computed distance values.

REFERENCES:
patent: 4181821 (1980-01-01), Pirz et al.
patent: 4571697 (1986-02-01), Watanabe
patent: 4608708 (1986-08-01), Watanabe
patent: 4737976 (1988-04-01), Borth et al.
patent: 4783802 (1988-11-01), Takebayashi et al.
patent: 4933973 (1990-06-01), Porter
Berouti et al., "Enhancement of Speech Corrupted by Acoutistic Noise", Bolt Baranek and Newman Inc., Cambridge, Mass., IEEE, 208-211 (1979).
Ohno et al., "Utterance Normalization Using Vowel Features in a Spoken Word Recognition System for Multiple Speakers," IEEE Speech Processing, Apr. 27, 1993, pp. II-578 to II-581.

Affiliated with

Also associated with

Rating

Speech recognition using distance between feature vector of one 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 using distance between feature vector of one , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using distance between feature vector of one will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1520487