Method and apparatus for sound processing

A sound processing method for processing environmental sound in which an operation noise of a device and other voices are mixed, the sound processing method comprising:

• collecting a sound signal through a plurality of channels using a plurality of microphones;
• removing noise from the sound signal;
• performing multi-channel blind source separation so as to separate sound sources in the noise-removed sound signal based on an independent vector analysis;
• and
• extracting a desired voice signal from a channel having the smallest sum of off-diagonal values of a separation adaptive filter when the intensity of the desired voice is larger than the intensity of the other voices.

A sound processing apparatus for extracting a desired voice signal from a sound signal in which an operation noise of a device and other voices are mixed, the sound processing apparatus comprising:

• a plurality of microphones configured to allow a sound signal to be collected through a plurality of channels;
• a noise filter configured to remove noise from the sound signal;
• and
• a sound source separator configured to performing multi-channel blind source separation so as to separate sound sources in the noise-removed sound signal based on independent vector analysis,
• wherein the sound source separator extracts a desired voice signal from the channel having the smallest sum of the off-diagonal values of the separation adaptive filter when the intensity of the desired voice is larger than the intensity of the other voices.