Method for processing multichannel acoustic signal, system thereof, and program

摘要

A method for processing multichannel acoustic signals, whereby input signals of a plurality of channels including the voices of a plurality of speaking persons are processed. The method is characterized by comprising: calculating the first feature quantity of the input signals of the multichannels for each channel; calculating similarity of the first feature quantity of each channel between the channels; selecting channels having high similarity; separating signals using the input signals of the selected channels; inputting the input signals of the channels having low similarity and the signals after the signal separation; and detecting a voice section of each speaking person or each channel.

主权项

1. A multichannel acoustic signal processing method of processing input signals of a plurality of channels including voices of a plurality of talkers, comprising:
calculating, by at least one processor, a first feature for each channel from the input signals of a multichannel; calculating, by at least one processor, an inter-channel similarity of said by-channel first feature; grouping by at least one processor, a plurality of the channels of which said similarity is higher than a threshold; separating, by at least one processor, the signals for each group for input signals of the grouped channels; and detecting, by at least one processor, voice section of each said talkers or voice section of said each of the channels using the input signals of channels unsubjected to the grouping and the signals subjected to said signal separation, respectively.