Speech recognition using distance between feature vector of one sequence

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.