Managing audio in a multi-source audio environment

• US 7,995,732 B2
• Filed: 10/04/2007
• Issued: 08/09/2011
• Est. Priority Date: 10/04/2007
• Status: Expired due to Fees

• 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
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Neway; Samuel G
• Application Number:
  US11/867,177
• Publication Number:
  US 20090094029A1
• Time in Patent Office: 1,405 Days
• Field of Search: 37920201-20501
• US Class Current: 379/204.01
• 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 computer-implemented method for managing real-time audio from a multi-source audio environment, the computer-implemented method comprising computer-implemented operations for:

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

identifying a plurality of speakers, each of which is associated with one of the plurality of audio sources;

detecting an audio source change from a first audio source of the plurality of audio sources to a second audio source of the plurality of audio sources;

in response to detecting the audio source change, providing an identification of a first speaker of the plurality of speakers, the first speaker being associated with the second audio source;

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

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

after recording of 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 to create a modified audio recording, 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.

2. The method of claim 1,

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

3. The method of claim 2, further comprising:

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

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

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

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

5. The method of claim 1, wherein identifying the plurality of speakers, each of which is associated with one of the plurality of audio sources comprises:

creating an unidentified voice print for each speaker of the plurality of speakers;

comparing the unidentified voice print for each speaker of the plurality of speakers to at least one identified voice print stored in the repository;

if a match between one of the unidentified voice prints and one of the plurality of speakers is discovered, identifying a particular speaker of the plurality of speakers associated with the match as corresponding to a matched unidentified voice print; and

if a match between one of the unidentified voice prints and one of the plurality of speakers is not discovered, assigning an identity to an unmatched unidentified voice print.

6. The method of claim 5, further comprising selecting a particular identified voice print of the at least one identified voice prints stored in the repository for comparison according to one of the following:

a telephone number and an Internet Protocol address associated with each unidentified voice print.

7. The method of claim 1, 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.

8. The method of claim 1, 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 the one of the plurality of audio sources.

9. The method of claim 1, wherein one of the plurality of audio sources is associated with a subset of the plurality of speakers, the subset of the plurality of speakers comprising at least two speakers, and wherein identifying the plurality of speakers, each of which is associated with one of the plurality of audio sources comprises distinguishing between individual speakers of the subset of the plurality of speakers associated with the one of the plurality of audio sources according to a position of each of the individual speakers of the subset of the plurality of speakers with respect to at least one microphone receiving the real-time audio.

10. The method of claim 9, wherein distinguishing between the individual speakers of the subset of the plurality of speakers associated with the one of the plurality of audio sources according to the position of each of the individual speakers of the subset of the plurality of speakers with respect to the at least one microphone receiving the real-time audio comprises:

detecting a sound wave at a position on each of the at least one microphone; and

assigning a speaker identification to a source of each sound wave according to the position on each of the at least one microphone in which the sound wave is detected.

11. A non-transitory computer-readable medium having computer-executable instructions stored thereon which, when executed by a computer, cause the computer at least to:

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

identify a plurality of speakers, each of which is associated with one of the plurality of audio sources;

detect an audio source change from a first audio source of the plurality of audio sources to a second audio source of the plurality of audio sources;

in response to detecting the audio source change, provide an identification of a first speaker of the plurality of speakers, the first speaker being associated with the second audio source;

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

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

after recording of the real-time audio has completed, determine 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, modify the audio recording according to the feedback to create a modified audio recording, 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, store the audio recording in the repository.

12. The computer-readable medium of claim 11, wherein the computer-executable instructions stored thereon which, when executed by the computer, cause the computer at least to

cause the computer to provide the identification of the first speaker associated with the second audio source comprise computer-executable instructions stored thereon which, when executed by the computer, cause the computer to cause the computer at least to insert a descriptor corresponding to the first speaker associated with the second audio source into the recording of the real-time audio.

13. The computer-readable medium of claim 12, further comprising computer-executable instructions stored thereon which, when executed by the computer, cause the computer to:

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

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

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

14. The computer-readable medium of claim 11, wherein the computer-executable instructions stored thereon which, when executed by the computer, cause the computer at least to identify the plurality of speakers, each of which is associated with one of the plurality of audio sources comprise computer-executable instructions stored thereon which, when executed by the computer, cause the computer to cause the computer at least to:

create an unidentified voice print for each speaker of the plurality of speakers;

compare the unidentified voice print for each speaker of the plurality of speakers to at least one identified voice print stored in the repository;

if a match between one of the unidentified voice prints and one of the plurality of speakers is discovered, identify a particular speaker of the plurality of speakers associated with the match as corresponding to a matched unidentified voice print; and

if a match between one of the unidentified voice prints and one of the plurality of speakers is not discovered, assign an identity to an unmatched unidentified voice print.

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

a repository; and

an audio management server computer, the audio management server computer comprising an audio management engine configured to;

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

identify a plurality of speakers, each of which is associated with one of the plurality of audio sources;

detect an audio source change from a first audio source of the plurality of audio sources to a second audio source of the plurality of audio sources;

in response to detecting the audio source change, provide an identification of a first speaker of the plurality of speakers, the first speaker being associated with the second audio source;

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

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

after recording of the real-time audio has completed, determine 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, modify the audio recording according to the feedback to create a modified audio recording, and storing the modified audio recording in the 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.

16. The system of claim 15, wherein one of the plurality of audio sources is associated with a subset of the plurality of speakers, the subset of the plurality of speakers comprising at least two speakers, and wherein in being configured to identify the plurality of speakers, each of which is associated with one of the plurality of audio sources, the audio management server computer is configured to utilize at least one microphone each of which is configured to determine a direction of an audio source of the plurality of audio sources 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.