Audio and depth based sound source localization

A method comprising:

• receiving multiple input microphone signals;
• analyzing one or more of the multiple input microphone signals to determine a first estimate of a source position of a sound produced by an object;
• capturing a depth image of an area that encompasses the first estimate of the source position of the sound;
• determining a position of the object based at least in part on the depth image;
• and
• determining a second estimate of the source position of the sound based at least in part on a weighted average of the first estimate of the source position of the sound and the position of the object, the weighted average based at least in part on a first confidence level associated with the first estimate of the source position of the sound and a second confidence level associated with the position of the object, the first confidence level based at least in part on a signal-to-noise ratio associated with the one or more of the multiple input microphone signals.

A method comprising:

• analyzing one or more input microphone signals to determine a first estimate of a source position of a sound emitted in an environment;
• capturing an image that encompasses the first estimate of the source position of the sound;
• analyzing the image to detect a position of a source of the sound in the image;
• and
• determining a second estimate of the source position of the sound based at least in part on a weighted average of the first estimate of the source position of the sound and the position of the source of the sound in the image, the weighted average based at least in part on a first confidence level associated with the first estimate of the source position of the sound and a second confidence level associated with the position of the source of the sound in the image, the first confidence level based at least in part on a signal-to-noise ratio associated with the one or more input microphone signals.