Abstract: In a speech recognition method, at least two standard feature vector series having different signal-to-noise ratios (SNRs) are prepared in advance for each category. Then, an SNR is calculated from an input speech signal, and a noise adaptive standard feature vector series is calculated by a linear interpolation method between the prepared standard feature vector series using the calculated SNR. Finally, a dynamic programming matching operation is performed upon the feature vectors of the noise adaptive standard feature vector series and the feature vectors of the input speech signal.

Abstract: In a speech recognition method, at least two standard feature vector series having different signal-to-noise ratios (SNRs) are prepared in advance for each category. Then, an SNR is calculated from an input speech signal, and a noise adaptive standard feature vector series is calculated by a linear interpolation method between the prepared standard feature vector series using the calculated SNR. Finally, a nonlinear expansion and reduction matching operation is performed upon the feature vectors of the noise adaptive standard feature vector series and the feature vectors of the input speech signal.

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.

Abstract: A single-input spectral subtraction section 13 removes ambient noise around the caller from received signals. A characteristic correction section 14 estimates transmission characteristics from received and transmitted signals and corrects the transmitted signals to coincide with the received signals. And finally, a dual-input subtraction section 15 removes an automated voice by subtracting the output of the characteristic correction section 14 from the output of the single-input spectral subtraction section 13.

Abstract: A speech recognition apparatus includes a feature extraction section, and a recognition section. The feature extraction section extracts the feature vectors of input speech. The feature extraction section includes at least a pitch intensity extraction section. The pitch intensity extraction section extracts the intensities of the fundamental frequency components of the input speech. The recognition section performs speech recognition by using the feature vectors from the feature extraction section.

Abstract: An analyzing unit 1 converts an input speech into a feature vector time series. A reference pattern storing unit 3 stores the feature vector time series obtained by the same manner as in the analyzing unit. A matching unit 2 correlates for time axis the input speech feature vector time series and the reference patterns to one another. An environmental adapting unit 4 performs the environmental adaptation between the input speech feature vector time series and the reference patterns according to the result of matching in the matching unit 2. A speaker adapting unit 6 performs the adaptation concerning the speaker between the environmentally adapted reference patterns from the environmental adapting unit 4 and the input speech feature vector time series.

Abstract: A speech adaptation device comprises a vocabulary independent reference pattern memory for memorizing a plurality of vocabulary independent reference patterns having one or more categories. Each category has one or more acoustic units, and has such a connection relation of the acoustic units that allows reception of any sequence of the acoustic units appearing in the input speech. A preliminary matching unit is for use in making time-alignment between the time series of the feature vectors of the input speech obtained from the analysis unit and the vocabulary independent reference pattern to obtain mean vectors for individual categories of the input speech and the vocabulary independent reference pattern from the aligned portion for the individual categories of the feature vectors of the input speech and the vocabulary independent reference pattern.

Abstract: A speech recognition apparatus includes an average vector calculating portion 5, a compensating portion 6, and a matching portion 8. The average vector calculating portion 5 calculates an average vector for each of the noise region and the speech region of the input speech and those of a reference pattern received from a spectrum converting portion 4 corresponding to matching information received from a preliminary matching portion 2.

Abstract: Each time a matching unit 22 finishes a matching at a time "i" between feature vectors of input speech which have been converted by an analyzer 1 and feature vectors of reference patterns stored in a reference pattern memory 2, and goes to a matching at a next time "i+1", a feature vector integrator 24 multiplies the feature vectors of the input speech or the reference patterns by a weight w1 in each of acoustic categories, successively integrates products, stores integrated values in respective frames of the reference patterns in feature vector accumulating buffers 26, and integrates and stores weights w1 in feature vector weight counters 27 corresponding to the respective acoustic categories.