System and method for localizing a talker using audio and video information
AssigneePolycom, Inc.
InventorJinwei Feng
Life of this patent
Estimating the term…
Abstract
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.
Claims20
A videoconferencing endpoint, the endpoint comprising:
- at least one processor,
- a predetermined number of microphones and at least one camera, each in signal communication with the processor;
- at least one non-transitory computer readable storage medium in signal communication with the processor;
- at least one program module, stored on the non-transitory computer readable storage medium and operable, upon execution of the processor to:
- receive audio information via the predetermined number of microphones for a predetermined period during a teleconferencing session, the audio information corresponding to one or more angles with respect to the microphones from within a location of the teleconferencing session;
- analyze the received audio information according to at least one algorithm to determine at least one candidate angle, the candidate angle corresponding to a possible location of an active talker, wherein the algorithm gives greater weight to lower frequency bands than to higher frequency bands from within the received audio information;
- receive motion information via at the least one camera;
- and
- analyze the candidate angle with respect to the received motion information to determine whether the candidate angle corresponds to an active talker.
A videoconferencing endpoint, the endpoint comprising:
- at least one processor,
- a predetermined number of microphones and at least one camera, each in signal communication with the processor;
- at least one non-transitory computer readable storage medium in signal communication with the processor;
- at least one program module, stored on the non-transitory computer readable storage medium and operable, upon execution of the processor to:
- receive audio information via the predetermined number of microphones for a predetermined period during a teleconferencing session, the audio information corresponding to one or more angles with respect to the microphones from within a location of the teleconferencing session;
- analyze the received audio information according to at least one algorithm to determine at least one candidate angle, the candidate angle corresponding to a possible location of an active talker;
- receive motion information via at the least one camera;
- and
- analyze the candidate angle with respect to the received motion information to determine whether the candidate angle corresponds to an active talker,
- wherein analyzing the candidate angle with respect to the received motion involves determining whether motion has been detected at the candidate angle within the predetermined period.
A non-transitory computer readable storage medium storing instructions executable by a processor, which upon execution are operable to cause the processor to:
- receive audio information via a predetermined number of microphones for a predetermined period during a teleconferencing session, the audio information corresponding to one or more angles with respect to the microphones from within a location of a teleconferencing session;
- analyze the received audio information according to at least one algorithm to determine at least one candidate angle, the candidate angle corresponding to a possible location of an active talker of the teleconferencing session, wherein the algorithm gives greater weight to lower frequency bands than to higher frequency bands from within the received audio information;
- receive motion information via at least one camera;
- and
- analyze the candidate angle with respect to the received motion information to determine whether the candidate angle corresponds to an active talker.
A non-transitory computer readable storage medium storing instructions executable by a processor, which upon execution are operable to cause the processor to:
- receive audio information via a predetermined number of microphones for a predetermined period during a teleconferencing session, the audio information corresponding to one or more angles with respect to the microphones from within a location of a teleconferencing session;
- analyze the received audio information according to at least one algorithm to determine at least one candidate angle, the candidate angle corresponding to a possible location of an active talker of the teleconferencing session;
- receive motion information via at least one camera;
- and
- analyze the candidate angle with respect to the received motion information to determine whether the candidate angle corresponds to an active talker,
- wherein analyzing the candidate angle with respect to the received motion involves determining whether motion has been detected at the candidate angle within the predetermined period.
Dependencies are inferred from the claim text.