Managing Audio in a Multi-Source Audio Environment

• US 20090094029A1
• Filed: 10/04/2007
• Published: 04/09/2009
• Est. Priority Date: 10/04/2007
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Tischer, Steven, Starr, Robert, Koch, Robert
• Granted Patent: US 7,995,732 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15
• CPC Class Codes: H04M 3/568 audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30

Abstract

Methods, systems, and computer-readable media provide for the management of an audio environment with multiple audio sources. According to various embodiments described herein, real-time audio from multiple sources is received. A speaker is identified for each of the audio sources. Upon detecting a change from a first audio source to a second audio source, an identification of the speaker associated with the second audio source is provided. According to various embodiments, a recording of the real-time audio may be made and descriptors inserted to identify each speaker as the audio source changes. Real-time feedback from the speakers regarding characteristics of the audio may be received and corresponding adjustments to the audio made.

Claims

1. A method for managing real-time audio from a multi-source audio environment, comprising:

receiving the real-time audio comprising a plurality of audio sources;

identifying a speaker associated with each of the plurality of audio sources;

detecting an audio source change from a first audio source to a second audio source; and

in response to detecting the audio source change, providing an identification of the speaker associated with the second audio source.

2. The method of claim 1, further comprising:

creating a recording of the real-time audio; and

wherein providing the identification of the speaker associated with the second audio source comprises inserting a descriptor corresponding to the speaker associated with the second audio source into the recording of the real-time audio.

3. The method of claim 2, further comprising:

storing the recording of the real-time audio in a repository;

receiving a request to search the repository for audio recordings comprising the descriptor corresponding to the speaker associated with the second audio source;

searching the repository for the descriptor corresponding to the speaker associated with the second audio source; and

providing a list comprising an identification of any audio recording stored within the repository comprising the descriptor corresponding to the speaker associated with the second audio source.

4. The method of claim 1, wherein providing the identification of the speaker associated with the second audio source comprises providing the identification to a speaker associated with one of the plurality of audio sources other than the speaker associated with the second audio source.

5. The method of claim 1, wherein identifying the speaker associated with each of the plurality of audio sources comprises:

creating an unidentified voice print for each speaker corresponding to the plurality of audio sources;

comparing each unknown voice print to one or more stored identified voice prints;

if a match is discovered, identifying a speaker associated with a matched unknown voice print as a speaker associated with a matching identified voice print; and

if a match is not discovered, assigning an identity to an unmatched unknown voice print.

6. The method of claim 5, further comprising selecting the one or more stored identified voice prints for comparison according to a telephone number or Internet Protocol (IP) address associated with each unknown voice print.

7. The method of claim 1, further comprising:

receiving feedback corresponding to one of the plurality of audio sources from a speaker associated with one of the plurality of audio sources; and

modifying the real-time audio according to the feedback.

8. The method of claim 7, wherein the feedback comprises an identification of a key press on a communications device corresponding to a request for increasing a volume of the one of the plurality of audio sources.

9. The method of claim 7, wherein the feedback comprises an identification of a key press on a communications device corresponding to a request for an improvement of audio quality of one of the plurality of audio sources.

10. The method of claim 1, further comprising:

receiving feedback corresponding to one of the plurality of audio sources from a speaker associated with one of the plurality of audio sources;

recording the real-time audio to create an audio recording;

after the real-time audio has completed, determining whether a threshold quantity of feedback was received during the recording of the real-time audio;

if the threshold quantity of feedback was received during the recording of the real-time audio, modifying the audio recording according to the feedback and storing the modified audio recording in a repository; and

if the threshold quantity of feedback was not received during the recording of the real-time audio, storing the audio recording in the repository.

11. The method of claim 1, wherein one of the plurality of audio sources comprises a plurality of speakers, and wherein identifying the speaker associated with each of the plurality of audio sources comprises distinguishing between the plurality of speakers at the one of the plurality of audio sources according to a position of each of the plurality of speakers with respect to one or more microphones receiving the real-time audio.

12. The method of claim 11, wherein distinguishing between the plurality of speakers at the one of the plurality of audio sources according to the position of each of the plurality of speakers with respect to the one or more microphones receiving the real-time audio comprises:

detecting a sound wave at a position on each of the one or more microphones; and

assigning a speaker identification to a source of each sound wave according to the position on each of the one or more microphones in which the sound wave is detected.

13. A computer-readable medium having computer-executable instructions stored thereon which, when executed by a computer, cause the computer to:

receive real-time audio comprising a plurality of audio sources;

identify a speaker associated with each of the plurality of audio sources;

detect an audio source change from a first audio source to a second audio source; and

in response to detecting the audio source change, provide an identification of the speaker associated with the second audio source.

14. The computer-readable medium of claim 13, further comprising computer-executable instructions stored thereon which, when executed by a computer, cause the computer to:

create a recording of the real-time audio; and

wherein causing the computer to provide the identification of the speaker associated with the second audio source comprises causing the computer to insert a descriptor corresponding to the speaker associated with the second audio source into the recording of the real-time audio.

15. The computer-readable medium of claim 14, further comprising computer-executable instructions stored thereon which, when executed by a computer, cause the computer to:

store the recording of the real-time audio in a repository;

receive a request to search the repository for audio recordings comprising the descriptor corresponding to the speaker associated with the second audio source;

search the repository for the descriptor corresponding to the speaker associated with the second audio source; and

provide a list comprising an identification of any audio recording stored within the repository comprising the descriptor corresponding to the speaker associated with the second audio source.

16. The computer-readable medium of claim 13, wherein causing the computer to identify the speaker associated with each of the plurality of audio sources comprises causing the computer to:

create an unidentified voice print for each speaker corresponding to the plurality of audio sources;

compare each unknown voice print to one or more stored identified voice prints;

if a match is discovered, identify a speaker associated with a matched unknown voice print as a speaker associated with a matching identified voice print; and

if a match is not discovered, assign an identity to an unmatched unknown voice print.

17. The computer-readable medium of claim 13, further comprising computer-executable instructions stored thereon which, when executed by a computer, cause the computer to:

receive feedback corresponding to one of the plurality of audio sources from a speaker associated with one of the plurality of audio sources; and

modify the real-time audio according to the feedback.

18. A system for managing real-time audio from a multi-source audio environment, comprising:

means for receiving the real-time audio comprising a plurality of audio sources;

means for identifying a speaker associated with each of the plurality of audio sources;

means for detecting an audio source change from a first audio source to a second audio source; and

means for providing an identification of the speaker associated with the second audio source in response to detecting the audio source change.

19. The system of claim 18, wherein one of the plurality of audio sources comprises a plurality of speakers, and wherein the means for identifying the speaker associated with each of the plurality of audio sources comprises one or more microphones, each microphone operative to determine a direction of an audio source with respect to the microphone by detecting a direction of a sound wave associated with the audio source according to a portion of the microphone first exposed to the sound wave.

20. The system of claim 18, further comprising:

means for receiving feedback corresponding to one of the plurality of audio sources from a speaker associated with one of the plurality of audio sources;

means for recording the real-time audio to create an audio recording;

means for determining whether a threshold quantity of feedback was received during the recording of the real-time audio;

means for modifying the audio recording according to the feedback and storing the modified audio recording in a repository if the threshold quantity of feedback was received during the recording of the real-time audio; and

means for storing the audio recording in the repository if the threshold quantity of feedback was not received during the recording of the real-time audio.