AUDIO PROCESSING DEVICE, VOICE RECOGNITION DEVICE, AUDIO PROCESSING METHOD, VOICE RECOGNITION METHOD, AUDIO PROCESSING PROGRAM AND VOICE RECOGNITION PROGRAM

摘要

To make it possible to easily set a target area according to the environment in which a device is placed, and selectively collect only phonation from inside of the target area.SOLUTION: A sound processing apparatus according to the embodiment: arranges a plurality of first microphones at mutually different positions in a space where there is an area outside the target area; extracts feature quantities of voice uttered outside the target area from the sounds collected by the plurality of first microphones respectively; generates a determination model for determining whether a voice uttering position in the space is outside the target area or not on the basis of the feature quantities of the voice uttered outside the target area by learning; arranges a second microphone in the space; removes the voice uttered outside the target area from the collected voice by the second microphone on the basis of the feature quantities and the determination model; and detects and outputs the remaining voice.SELECTED DRAWING: Figure 1