Hitachi, Ltd.

Nippon Telegraph and Telephone Public Corporation

Kazuo Nakata

Akira Ichikawa

Kazuhiro Umemura

Akira Nakajima

Takanori Miyamoto

Hirokazu Sato

Akihiro Asada

Yoshihiro Ohta

Tohru Sampei

Akio Suehiro

Kazuhito Hirose

Kenya Murakami

Kiyoshi Into

Kiyoshi Intoh

Murakami Kenya

A method and apparatus for speech signal detection and classification in which a partial auto-correlation and residual power analyzation circuit extracts a normalized first-order partial auto-correlation coefficient and K.sub.1 a normalized zero-order residual power E.sub.N from an input signal, and a sound source analyzation circuit extracts a normalized residual correlation .phi. from the input signal, and in which on the basis of these extracted parameters, speech signals are detected, and, when so detected, the detected speech signals are classified into a voiced sound V, an unvoiced sound U and silence S. The classification of the respective voiced sound, unvoiced sound and silence is determined on the basis of preset threshold values that are mutually considered and which correspond to values of these extracted K.sub.1, E.sub.N and .phi. parameters for establishing boundary values for classifying the input signals into a voiced sound, an unvoiced sound or silence.

Method and apparatus for speech signal detection and classification of

A plurality of pitch period candidates are selected from a peak of correlation of a speech waveform in a current frame from which a pitch period is to be extracted, and a speech pitch is selected from the candidates by referring to a guide index which is precalculated based on pitch periods extracted in past frames. The guide index is an average of the pitch periods in the past frames.

Method and apparatus for extracting speech pitch

Speech synthesizer

This PARCOR-type speech synthesizer replaces a ten-stage lattice type filter with a pipeline multiplier and feedback loop, and provides a loss circuit (for bandwidth broadening) using subtraction circuits for multiplication.

Computation of the partial correlation coefficients (PARCOR K.sub.i) of a signal, using less cascaded hardware, is implemented by first deriving a sequence of auto-correlation coefficients (v.sub.j) which are then transformed into a sequence of K.sub.i using a single section digital filter plus recirculating circuitry for data iteration.

Speech analysing device

Signal-to-noise is enhanced by including the upper sideband of a sampled-speech signal with the original baseband signal for further signal processing. The invention features shifting both bands to form a continuum from 0 Hz to the sampling frequency. Application in a speech recognition is shown.

Preprocessing method and device for speech recognition device

A multifrequency signal receiving system comprising a filter for whitening a received signal, a correlator for extracting partial autocorrelation coefficients from the output of the whitening filter, a prediction error analyzer for judging the presence or absence of the multifrequency signal by analyzing prediction analysis errors from the output of the whitening filter, and a control unit responsive to the output of the analyzer indicative of the presence of the multifrequency signal for determining the frequency included in the received signal using the partial autocorrelation coefficients thereby identifying that the received signal is the multifrequency signal.

Multifrequency signal receiving system

Improvements in a push button signal receiving device for use in a voice response system, wherein in order to permit a push button signal from a user's telephone terminal to be received even during the period when a responding voice signal is being transmitted through the system, an analyzer for the parameter analysis of the responding voice signal and an inverse filter responsive to the analyzer for flattening the spectrum of the responding voice signal which is mixed into the push button signal are provided, whereby the influence of the responding voice signal mixing into the signal to be applied to a push button signal detector is erased, and the push button signal, which may be feeble in comparison to the responding voice signal, is detected and recognized nevertheless.

Growing community of inventors

Kodaira, Japan

Kazuo Nakata