Active Speaker Indicator for Conference Participants

• US 20140118472A1
• Filed: 10/31/2012
• Published: 05/01/2014
• Est. Priority Date: 10/31/2012
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Raghurama Bhat
• Inventors: Liu, Yanghua, Chen, Weidong, Gandhi, Biren, Bhat, Raghurama, Khouri, Joseph Fouad, Houston, John Joseph, Toombs, Brian Thomas
• Granted Patent: US 9,210,269 B2
• Time in Patent Office: Days
• US Class Current: 348/14.09
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04M 3/563 User guidance or feature selection
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

In one embodiment, a method includes receiving requests to join a conference from a plurality of user devices proximate a first endpoint. The requests include a username. The method also includes receiving an audio signal for the conference from the first endpoint. The first endpoint is operable to capture audio proximate the first endpoint. The method also includes transmitting the audio signal to a second endpoint, remote from the first endpoint. The method also includes identifying, by a processor, an active speaker proximate the first endpoint based on information received from the plurality of user devices.

Claims

1. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium embodying software that is operable when executed by the processor to;

receive requests to join a conference from a plurality of user devices proximate a first endpoint, the requests comprising a username;

receive an audio signal for the conference from the first endpoint, the first endpoint operable to capture audio proximate the first endpoint;

transmit the audio signal to a second endpoint, remote from the first endpoint; and

identify an active speaker proximate the first endpoint based on information received from the plurality of user devices.

2. The system of claim 1, wherein:

the received information is a plurality of audio energy values; and

the software is further operable when executed to identify the active speaker proximate the first endpoint by comparing the plurality of audio energy values.

3. The system of claim 2, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by calibrating the plurality of user devices.

4. The system of claim 2, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by:

identifying a greatest audio energy value user device of the plurality of user devices; and

identifying the username transmitted by the greatest audio energy value user device as the active speaker.

5. The system of claim 1, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by:

receiving a first audio energy value from a first user device of the plurality of user devices;

receiving a second audio energy value from a second user device of the plurality of user devices; and

comparing the first audio energy value with the second audio energy value.

6. The system of claim 1, wherein:

the active speaker is a first active speaker; and

the software is further operable when executed to identify a second active speaker proximate the first endpoint based on information received from the plurality of user devices.

7. A method, comprising:

receiving requests to join a conference from a plurality of user devices proximate a first endpoint, the requests comprising a username;

receiving an audio signal for the conference from the first endpoint, the first endpoint operable to capture audio proximate the first endpoint;

transmitting the audio signal to a second endpoint, remote from the first endpoint; and

identifying, by a processor, an active speaker proximate the first endpoint based on information received from the plurality of user devices.

8. The method of claim 7, wherein:

the received information is a plurality of audio energy values; and

identifying the active speaker proximate the first endpoint based on information received from the plurality of user devices comprises comparing the plurality of audio energy values.

9. The method of claim 8, wherein identifying the active speaker proximate the first endpoint based on information received from the plurality of user devices further comprises calibrating the plurality of user devices.

10. The method of claim 8, wherein identifying the active speaker proximate the first endpoint based on information received from the plurality of user devices further comprises:

identifying a greatest audio energy value user device of the plurality of user devices; and

identifying the username transmitted by the greatest audio energy value user device as the active speaker.

11. The method of claim 7, wherein identifying the active speaker proximate the first endpoint based on information received from the plurality of user devices comprises:

receiving a first audio energy value from a first user device of the plurality of user devices;

receiving a second audio energy value from a second user device of the plurality of user devices; and

comparing the first audio energy value with the second audio energy value.

12. The method of claim 7, wherein the active speaker is a first active speaker, and further comprising identifying a second active speaker proximate the first endpoint based on information received from the plurality of user devices.

13. One or more non-transitory computer-readable storage media embodying software that is operable when executed by a processor to:

receive requests to join a conference from a plurality of user devices proximate a first endpoint, the requests comprising a username;

receive an audio signal for the conference from the first endpoint, the first endpoint operable to capture audio proximate the first endpoint;

transmit the audio signal to a second endpoint, remote from the first endpoint; and

identify an active speaker proximate the first endpoint based on information received from the plurality of user devices.

14. The media of claim 13, wherein:

the received information is a plurality of audio energy values; and

the software is further operable when executed to identify the active speaker proximate the first endpoint by comparing the plurality of audio energy values.

15. The media of claim 14, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by calibrating the plurality of user devices.

16. The media of claim 14, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by:

identifying a greatest audio energy value user device of the plurality of user devices; and

identifying the username transmitted by the greatest audio energy value user device as the active speaker.

17. The media of claim 13, wherein the software is further operable when executed to identify the active speaker proximate the first endpoint by:

receiving an first audio energy value from a first user device of the plurality of user devices;

receiving a second audio energy value from a second user device of the plurality of user devices; and

comparing the first audio energy value with the second audio energy value.

18. The media of claim 13, wherein:

the active speaker is a first active speaker; and

the software is further operable when executed to identify a second active speaker proximate the first endpoint based on information received from the plurality of user devices.

19. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium embodying software that is operable when executed by the processor to;

receive registration audio signals associated with a plurality of users;

generate voice identification information for the plurality of users based on the received registration audio signals;

store the voice identification information in a database;

receive an audio signal for a conference from a first endpoint, the first endpoint operable to capture audio proximate the first endpoint;

transmit the audio signal to a second endpoint, remote from the first endpoint; and

identify an active speaker proximate the first endpoint based on the audio signal and the voice identification information.

20. The system of claim 19, wherein the software is further operable when executed to:

select a subset of the plurality of users; and

identify the active speaker proximate the first endpoint based on the audio signal and the voice identification information for the subset of the plurality of users.

21. The system of claim 20, wherein the software is further operable when executed to:

receive requests to join the conference from a plurality of user devices proximate the first endpoint, the requests comprising a username; and

select the subset of the plurality of users based on the received requests to join the conference.

22. The system of claim 20, wherein:

the database further stores location information associated with the plurality of users; and

the software is further operable when executed to;

determine a location of the first endpoint; and

select the subset of the plurality of users based on the location information associated with the plurality of users.

23. The system of claim 19, wherein the software is further operable when executed to:

receive active speaker detection feedback, the feedback indicating the accuracy of the active speaker identification; and

update the voice identification information based on the active speaker detection feedback.

24. The system of claim 19, wherein the software is further operable when executed to:

receive a video signal for the conference from the first endpoint;

process the video signal to produce a processed video signal that includes active speaker identification information; and

transmit the processed video signal to the second endpoint.