Sound source-separating device and sound source-separating method

摘要

A sound source-separating device includes a sound-collecting part, an imaging part, a sound signal-evaluating part, an image signal-evaluating part, a selection part that selects whether to estimate a sound source direction based on the first sound signal or the first image signal, a person position-estimating part that estimates a sound source direction using the first image signal, a sound source direction-estimating part that estimates a sound source direction, a sound source-separating part that extracts a second sound signal corresponding to the sound source direction from the first sound signal, an image-extracting part that extracts a second image signal of an area corresponding to the estimated sound source direction from the first image signal, and an image-combining part that changes a third image signal of an area other than the area for the second image signal and combines the third image signal with the second image signal.

主权项

1. A sound source-separating device comprising:
a sound-collecting part configured to collect sound and generate a first sound signal; an imaging part configured to capture an image and generate a first image signal; a sound signal-evaluating part configured to evaluate the first sound signal; an image signal-evaluating part configured to evaluate the first image signal; a selection part configured to select whether to estimate a sound source direction based on the first sound signal or whether to estimate a sound source direction based on the first image signal, based on an evaluation result of the first sound signal by the sound signal-evaluating part and an evaluation result of the first image signal by the image signal-evaluating part; a person position-estimating part configured to estimate a sound source direction indicating a direction of a speaker by using the first image signal when the selection part has selected that the sound source direction is estimated based on the first image signal; a sound source direction-estimating part configured to estimate a sound source direction by using the first sound signal when the selection part has selected that the sound source direction is estimated based on the first sound signal; a sound source-separating part configured to extract a second sound signal corresponding to the sound source direction from the first sound signal based on the estimated sound source direction estimated by the sound source direction-estimating part when the selection part has selected that sound source direction is estimated based on the first sound signal; an image-extracting part configured to extract a second image signal of an area corresponding to the estimated sound source direction from the first image signal, the estimated sound source direction being estimated by the person position-estimating part when the selection part has selected that sound source direction is estimated based on the first image signal; and an image-combining part configured to change a third image signal of an area other than the area for the second image signal and to combine the third image signal with the second image signal.