Abstract: Disclosed herein is an audio processing apparatus for processing a plurality of pieces of audio data of sounds picked up by a plurality of microphones. The apparatus includes: a speaker identification section configured to identify a speaker based on the audio data; a simultaneous speech section identification section configured to, when at least first and second speakers have been identified, identify speech sections during which the first and second speakers have made speeches, and identify a section during which the first and second speakers have made the speeches at the same time as a simultaneous speech section; and an arranging section configured to separate audio data of the first speaker and audio data of the second speaker from the simultaneous speech section, and allow the audio data of the first speaker and the audio data of the second speaker to be outputted at mutually different timings.

Abstract: Disclosed herein is a sound source direction detecting apparatus including: a plurality of microphones configured to collect sounds from a sound source in order to form an audio frame; a frequency decomposition section configured to decompose the audio frame into frequency components; an error range determination section configured to determine the effects of noises collected together with the sounds as an error range relative to phases; a power level dispersion section configured to disperse power levels of the sounds for each of the frequency components decomposed by the frequency decomposition section, on the basis of the error range determined by the error range determination section; a power level addition section configured to add the power levels dispersed by the power level dispersion section; and a sound source direction detection section configured to detect the direction of the sound source based on the phase at which is located the highest of the power levels added by the power level addition sect

Abstract: An echo canceller used for hands-free communication systems in which hands-free communication is performed by using a speaker and a microphone is disclosed. The echo canceller includes a step size control unit calculating a step size value in an adaptive filter and an adaptive filter unit estimating an echo component of a feedback path from an input signal to the feedback path by adaptively identifying an impulse response of the feedback path formed by an acoustical coupling and the like of the speaker and the microphone, and subtracting the echo component from an output signal from the feedback path, in which the step size control unit calculates a step size value by using an echo reduction amount defined based on the ratio between the output signal from the feedback path and a residual signal and outputs the value to the adaptive filter unit.

Abstract: Disclosed herein is an echo canceller for use in a sound reinforcement communication system configured to carry out a sound reinforcement communication by utilizing a speaker and a microphone, the echo canceller including: an adaptive filter section configured to adaptively identify an impulse response of a feedback path formed by an acoustic coupling or the like between the speaker and the microphone to estimate an echo component in the feedback path from an input signal to the feedback path, and subtracting the echo component thus estimated from an output signal from the feedback path; and an echo suppressing section configured to execute echo suppressing processing for an output signal from the adaptive filter section.

Abstract: An audio processor of a loud speech communication system including a speaker and a microphone is provided. The audio processor includes: an adaptive filter wherein an amount of update in a learning event is set to an arbitrary value, and a filter coefficient is serially determined corresponding to the set amount of update; a semi-fixed filter adapted to an echo cancellation process of an audio input signal input from the microphone; adaptive filter assessment unit that calculates a length of an update vector based on the filter coefficient determined by the adaptive filter and a length of an update vector based on a filter coefficient set in the semi-fixed filter and that performs assessment of the filter coefficients in accordance with the update vectors; and coefficient specifying unit that sets an optimal filter coefficient among the filter coefficients into the semi-fixed filter in accordance with the result of the assessment of the filter coefficients performed by the adaptive filter assessment unit.

Abstract: An echo canceller for executing adaptive processing for canceling an echo component mixed with an audio input signal includes a volume ratio learner configured to compute a volume ratio between an audio output signal externally outputted and the audio input signal mixed with an echo component caused by reflection of the audio output signal to the audio input signal, thereby learning the volume ratio in a regular status in own apparatus, a double-talk detector configured to detect the double-talk status depending on whether a this-time volume ratio computed this time adapts to a double-talk status predicted by the learning of volume ratio and an echo cancel processor configured to control a learning operation of the echo component for the adaptive processing on the basis of a result of the double-talk status detection by the double-talk detector.

Abstract: A voice detecting apparatus includes a first determining unit to determine that human voice has been input if a signal component having a harmonic structure is detected from an input voice signal; a second determining unit to determine that human voice has been input if a frequency center-of-gravity of the input voice signal is within a predetermined range; a noise level storing unit to store a noise level; a third determining unit to determine that human voice has been input if the ratio of the power of the input voice signal to the noise level is above a predetermined threshold; a final determining unit configured to finally determine whether human voice has been input based on determination results of the first to third determining units; and a noise level updating unit configured to update the noise level if the final determining unit determines that human voice has not been input.