Abstract: A sound signal processor includes first and second framing sections, first and second frequency analyzing sections, and a cross-spectrum calculating sections, for detecting the phase of a cross-spectrum between the sound signals input to first and second microphones, a phase extracting sections, a phase unwrap processing sections, a frequency band dividing section, and first through N-th inclination calculating sections, for detecting the inclinations of the phase of the cross-spectrum detected by the cross-spectrum calculating section with respect to the frequency, and a histogram calculating section and a voiced/voiceless determining section, for detecting a speech section in the sound received by the first and second microphones based on the inclination with respect to the frequency detected by the first through N-th inclination calculating sections.

Abstract: FFT section 102 transforms a windowed input noise signal into a frequency spectrum. Spectral model storing section 103 stores model information on spectral models. Spectral model series calculating section 104 calculates spectral model number series corresponding to amplitude spectral series of the input noise signal, using the model information stored in spectral model storing section 103. Duration model/transition probability calculating section 105 outputs model parameters using the spectral model number series calculated in spectral model series calculating section 104. It is thereby possible to synthesize a background noise with perceptual high quality.

Abstract: A speaker verification apparatus and method input an identity claim, select voice information of a registered speaker corresponding to the input identity claim, input a voice of the speaker, analyze the input voice so as to extract a feature parameter, calculate a verification distance between a feature parameter of the input voice and that of the voice of the registered speaker and the speaker distances between a feature parameter of the input voice and those of the voices of other speakers; and determine whether or not the input voice matches that of the registered speaker. A false acceptance error rate, is input as a threshold, and a probability distribution of interspeaker distances is functions to determine that the input voice is the voice of the registered person specified by the identity claim.

Abstract: FFT section 102 transforms a windowed input noise signal into a frequency spectrum. Spectral model storing section 103 stores model information on spectral models. Spectral model series calculating section 104 calculates spectral model number series corresponding to amplitude spectral series of the input noise signal, using the model information stored in spectral model storing section 103. Duration model/transition probability calculating section 105 outputs model parameters using the spectral model number series calculated in spectral model series calculating section 104. It is thereby possible to synthesize a background noise with perceptual high quality.

Abstract: An adaptive predictive coding (APC) and adaptive kit allocation (ABA) system which splits a speech signal into a plurality of bands, subjecting each signal to adaptive predictive coding and adaptively changes quantization characteristics in the adaptive predictive coding so that quantization noise may become small. An average amplitude (not average power) of the signal of each band is detected for each temporal sub-interval, and a quantization bit number and a quantization step size are adaptively determined from the average amplitude for each sub-interval, thereby permitting reduction of the quantity of hardware used.

Abstract: The spectral envelope of speech signals are characterized by LSP (line spectral pair) parameters, termed w.sub.i and .theta..sub.i. In a speech synthesizer the control parameters for the filter may be a.sub.i =-2 cos w.sub.i and b.sub.i =-2 cos .theta..sub.i. The synthesizer filter is essentially an all pole filter consisting of two feedback paths each of which has a transfer function having zeroes on a unit circle in the complex plane.