Locating an audio source

A method comprising the steps of:

• generating, at an image pickup device, image signal representative of an image;
• generating audio signals representative of sound from an audio source;
• processing the audio signals to determine a direction of the audio source relative to a reference point;
• processing the image signals to identify an object in the direction of the audio source;
• processing the image signals for pixels having flesh tone colors;
• and
• steering the image pickup device to frame the object in the direction of the audio source.

A method for validating a detected speaker, comprising the steps of:

• detecting audio signals representative of sound from an audio source;
• processing the detected audio signals to determine a direction of the audio source;
• comparing the processed audio signals with processed previous audio signals that were previously detected in a direction proximate to the direction of the processed audio signals;
• determining that the processed audio signals include speech;
• generating, at an image pickup device, image signals representative of a framed image obtained in the direction of the processed audio signals and including the detected speaker;
• determining movement of the detected speaker based on the framed image and motion pixels;
• and
• if a cross-correlation value between the processed audio signals and the processed previous audio signals is greater than a predetermined threshold value, verifying the detected speaker.