Audio processing for video conferencing
Methods, systems, and computer program products for enhancing transmitted audio signals for a video conference call are disclosed. Facial recognition technology and audio processing techniques determine a position of a speaking member of a party on a video conference. Based on the determined position of the speaking member, the directionality of the received audio signals can be adjusted towards the speaking member. The video conference system can transmit the adjusted audio signals.
1. A method of transmitting audio for a video conference, comprising:
receiving audio signals from a microphone array during a video conference between a party and a third party;
receiving an image of the party;
determining a position of a speaking member of the party by analyzing the image;
adjusting a directionality of the received audio signals towards the speaking member using a beam forming strategy, based on the position determined by analyzing the image; and
transmitting adjusted audio signals to the third party during the video conference.
2. The method of claim 1 , wherein the determining step comprises determining the position of the speaking member of the party by analyzing facial movements in the image.
3. The method of claim 1 , wherein the determining step comprises determining the position of the speaking member of the party using audio processing techniques.
4. The method of claim 1 , wherein the determining step comprises determining the position of the speaking member of the party using facial recognition and audio processing techniques.
5. The method of claim 1 , wherein the transmitting step comprises transmitting adjusted audio signals to the third party during the video conference such that the adjusted audio signals are rendered according to the determined position.
6. The method of claim 1 , further comprising:
determining an identity of the speaking member of the party; and
transmitting a message representative of the determined identity of the speaking member of the party to the third party during the video conference.
7. The method of claim 1 , further comprising reinforcing the received audio signals according to the determined position and attenuating the received audio signals for known noise sources.
8. A video conferencing system, comprising:
a call control module, configured to initiate and maintain a video conference between a party controlling the video conferencing system and a third party;
a microphone array, configured to generate signals from sounds of the party controlling the video conferencing system;
a camera, configured to capture an image of the party controlling the video conferencing system;
a facial recognition module, configured to determine a position of a speaking member of the party controlling the video conferencing system by analyzing the image;
an audio processing module, configured to adjust a directionality of the generated signals towards the speaking member using a beam forming strategy, based on the position determined by analyzing the image; and
a video transport module, configured to transmit adjusted audio signals to the third party during the video conference.
9. The system of claim 8 , wherein the facial recognition module is further configured to determine the position of the speaking member of the party controlling the video conferencing system by analyzing facial movements in the image.
10. The system of claim 8 , wherein the facial recognition module is further configured to determine the position of the speaking member of the party controlling the video conferencing system using audio processing techniques.
11. The system of claim 8 , wherein the facial recognition module is further configured to determine the position of the speaking member of the party controlling the video conferencing system using facial recognition and audio processing techniques.
12. The system of claim 8 , wherein the video transport module is further configured to transmit adjusted audio signals to the third party during the video conference such that the adjusted audio signals are rendered according to the determined position.
13. The system of claim 8 , further comprising:
an identity module configured to determine an identity of the speaking member of the party controlling the video conferencing system;
wherein the video transport module is further configured to transmit a message representative of the determined identity of the speaking member of the party to the third party during the video conference.
14. The system of claim 8 , wherein the audio processing module is further configured to reinforce the generated signals according to the determined position and attenuate the generated signals for known noise sources using facial recognition.
15. A non-transitory computer readable storage medium comprising instructions stored thereon that, when executed by a processor, cause the processor to:
receive audio signals from a microphone array during a video conference between a party and a third party;
receive an image of the party;
determine a position of a speaking member of the party by analyzing the image;
adjust a directionality of the received audio signals towards the speaking member using a beam forming strategy, based on the position determined by analyzing the image; and
transmit adjusted audio signals to the third party during the video conference.
16. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to determine the position of the speaking member of the party by analyzing facial movement in the image.
17. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to determine the position of the speaking member of the party using audio processing techniques.
18. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to determine the position of the speaking member of the party using facial recognition and audio processing techniques.
19. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to transmit adjusted audio signals to the third party during the video conference such that the adjusted audio signals are rendered according to the determined position.
20. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to:
determine an identity of the speaking member of the party; and
transmit a message representative of the determined identity of the speaking member of the party to the third party during the video conference.
21. The non-transitory computer readable storage medium of claim 15 , further comprising instructions, that when executed by the processor, cause the processor to reinforce the received audio signals according to the determined position and attenuate the received audio signals for known noise sources using facial recognition.
22. A method of transmitting audio for a video conference, comprising:
receiving audio signals from a microphone array during a video conference from a party;
receiving an image of the party; and
adjusting a directionality of the received audio signals towards a speaking member of the party using a beam forming strategy, based on the image.
23. A method of transmitting audio for a video conference, comprising:
receiving audio signals from a microphone array during a video conference from a party;
receiving an image of the party; and
adjusting a directionality of the received audio signals towards a speaking member of the party using a beam forming strategy, based on facial motions detected in the image.