System and method for localizing a talker using audio and video information
A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The audio information is evaluated automatically to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session.
1. A videoconference system comprising:
a number of microphones;
a number of cameras;
a processor coupled to at least one of the microphones and to at least one of the cameras;
a memory storing instructions executable by the processor, the instructions comprising instructions to:
receive, using the at least one microphone, auditory data;
determine at least one candidate angle pertaining to at least some of the received auditory data based, at least in part, on application of an algorithm which gives greater weight to lower frequency bands than to higher frequency bands; and
identify the determined at least one candidate angle as indicating a possible location of an active talker;
detect motion using the at the least one camera; and
determine whether the candidate angle corresponds to a location of an active talker based, at least in part, on the detected motion,
wherein determining whether the candidate angle corresponds to a location of an active talker based on the detected motion involves determining whether motion has been detected at the candidate angle within a predetermined period and within a predetermined range of the candidate angle.
2. The videoconferencing system of claim 1 , wherein the number of microphones is at least three microphones, and the at least three microphones are arranged in a plane.
3. The videoconferencing system of claim 2 , wherein the at least three microphones are included in a teleconferencing device that includes at least one camera configured to receive visual data in a 360 degree plane.
4. The videoconferencing system of claim 1 , wherein the number of microphones is exactly three microphones.
5. The videoconferencing system of claim 1 , wherein determining the at least one candidate angle involves collecting audio data from a predetermined number of angles.
6. A non-transitory computer readable storage medium storing instructions, the instructions comprising instructions to:
receive, using at least one microphone from amongst a number of microphones, auditory data;
determine at least one candidate angle pertaining to at least some of received auditory data based, at least in part, on application of an algorithm weighting lower frequency bands more than higher frequency bands;
identify the determined at least one candidate angle as indicating a possible location of an active talker;
detect motion using at least one camera; and
determine whether the candidate angle corresponds to a location of an active talker based, at least in part, on the detected motion,
wherein determining whether the candidate angle corresponds to a location of an active talker based on the detected motion involves determining whether motion has been detected at the candidate angle within a predetermined period and within a predetermined range of the candidate angle.
7. The non-transitory computer readable storage medium of claim 6 , wherein the number of microphones is at least three microphones, and the at least three microphones are arranged in a plane.
8. The non-transitory computer readable storage medium of claim 7 , wherein the at least three microphones are included in a teleconferencing device that includes at least one camera configured to receive visual data in a 360 degree plane.
9. The non-transitory computer readable storage medium of claim 6 , wherein the number of microphones is exactly three microphones.
10. The non-transitory computer readable storage medium of claim 6 , wherein determining the at least one candidate angle involves collecting audio data from a predetermined number of angles.
11. A method comprising:
receiving, using at least one microphone from amongst a number of microphones, auditory data;
determining at least one candidate angle pertaining to at least some of the received auditory data, based at least in part, on application of an algorithm which gives greater weight to lower frequency bands than to higher frequency bands;
identifying the determined at least one candidate angle as indicating a possible location of an active talker;
detecting motion using at least one camera; and
determining whether the candidate angle corresponds to a location of an active talker based, at least in part, on the detected motion,
wherein determining whether the candidate angle corresponds to a location of an active talker based on the detected motion involves determining whether motion has been detected at the candidate angle within a predetermined period and within a predetermined range of the candidate angle.
12. The method of claim 11 , wherein the number of microphones is at least three microphones, and the at least three microphones are arranged in a plane.
13. The method of claim 12 , wherein the at least three microphones are included in a teleconferencing device that includes at least one camera configured to receive visual data in a 360 degree plane.
14. The method of claim 11 , wherein the number of microphones is exactly three microphones.