Crowd noise analysis

• US 8,457,768 B2
• Filed: 06/04/2007
• Issued: 06/04/2013
• Est. Priority Date: 06/04/2007
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Hammer, Stephen C., Holladay, Christopher E., Morgan, William D.
• Primary Examiner(s): Saunders, Jr., Joseph
• Application Number:
  US11/757,934
• Publication Number:
  US 20080300700A1
• Time in Patent Office: 2,192 Days
• Field of Search: 700/94, 704/224, 704/234, 381/57
• US Class Current: 700/94
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308

Abstract

The present invention generally provides a way to analyze crowd noise to identify “highlights” or the like. Specifically, an audio stream containing crowd noise from an event (e.g., sporting event, political rally, religious gathering, etc) is captured (e.g., using microphones) and time coded. The audio stream is normalized based on geography and processed to remove undesired artifacts and to identify a set (at least one) of highlights. Based on at least one threshold, at least one highlight is selected from the set of highlights.

Claims

1. A method for analyzing crowd noise, comprising:

receiving an audio stream for an event having a first participant and a second participant located at a venue, the audio stream containing crowd noise from a crowd that is distinct from the first participant and the second participant;

determining a geography for the event, the geography including geographic characteristics that include a geographic location of the venue of the event;

time coding the audio stream;

comparing a geographic characteristic of the first and second participants to the geographic characteristics of the event to identify one of the first participant or the second participant as a home participant of the event;

normalizing the audio stream based on the geography and the home participant; and

processing substantially an entirety of the audio stream with a computer device to remove undesired artifacts and to identify, from noise levels in the substantially the entirety of the audio stream, a set of highlights from the crowd noise.

2. The method of claim 1, further comprising selecting at least one highlight from the set of highlights based on at least one threshold.

3. The method of claim 2, the at least one threshold being selected from the group consisting of:

a level squelch threshold and a similarity squelch threshold.

4. The method of claim 1, the processing comprising:

identifying a target sound range;

removing frequencies that vary from the target sound range by more than a predetermined tolerance;

taking a level measurement of the audio stream over a predetermined time window to eliminate spikes;

generating a frequency-domain representation of the audio stream;

time averaging the audio stream to eliminate the spikes;

applying a squelch algorithm to eliminate the undesired artifacts; and

weighting the audio stream and the frequency-domain representation to produce a final response level measurement.

5. The method of claim 1, the event being selected from a group consisting of a sporting event, a political rally, and a religious gathering.

6. The method of claim 1, the audio stream being generated by a set of from participants and a set of attendees of the event.

7. The method of claim 1, further comprising capturing the audio stream using a set of microphones.

8. A system for analyzing crowd noise, comprising:

a computer system, having;

a module for receiving an audio stream for an event having a first participant and a second participant located at a venue, the audio stream containing crowd noise from a crowd that is distinct from the first participant and the second participant;

a module for time coding the audio stream;

a module for normalizing the audio stream configured to;

determine a geography for the event, the geography including geographic characteristics that include a geographic location of the venue of the event;

compare a geographic characteristic of the first and second participants to the geographic characteristics of the event to identify one of the first participant or the second participant as a home participant of the event; and

normalize the audio stream based on the geography and the home participant; and

a module for processing substantially an entirety of the audio stream to remove undesired artifacts and to identify, from noise levels in the substantially the entirety of the audio stream, a set of highlights from the crowd noise.

9. The system of claim 8, further comprising a module for selecting at least one highlight from the set of highlights based on at least one threshold.

10. The system of claim 9, the at least one threshold being selected from the group consisting of:

a level squelch threshold and a similarity squelch threshold.

11. The system of claim 8, the module for processing being configured to:

identify a target sound range;

remove frequencies that vary from the target sound range by more than a predetermined tolerance;

take a level measurement of the audio stream over a predetermined time window to eliminate spikes;

generate a frequency-domain representation of the audio stream;

time average the audio stream to eliminate the spikes;

apply a squelch algorithm to eliminate the undesired artifacts; and

weight the audio stream and the frequency-domain representation to produce a final response level measurement.

12. The system of claim 8, the event being selected from a group consisting of a sporting event, a political rally, and a religious gathering.

13. The system of claim 8, the audio stream being generated by a set of from participants and a set of attendees of the event.

14. The system of claim 8, the audio stream being captured using a set of microphones.

15. A computer readable storage device having a program product for analyzing crowd noise stored thereon, the computer readable storage device comprising program code for causing a computer system to:

receive an audio stream for an event having a first participant and a second participant located at a venue, the audio stream containing crowd noise from a crowd that is distinct from the first participant and the second participant;

determine a geography for the event, the geography including geographic characteristics that include a geographic location of the venue of the event;

time code the audio stream;

compare a geographic characteristic of the first and second participants to the geographic characteristics of the event to identify one of the first participant or the second participant as a home participant of the event;

normalize the audio stream based on the geography and the home participant; and

process substantially an entirety of the audio stream to remove undesired artifacts and to identify, from noise levels in the substantially the entirety of the audio stream, a set of highlights from the crowd noise.

16. The program product of claim 15, the computer readable storage device further comprising program code for causing the computer system to:

select at least one highlight from the set of highlights based on at least one threshold.

17. The program product of claim 16, the at least one threshold being selected from the group consisting of:

a level squelch threshold and a similarity squelch threshold.

18. The program product of claim 15, the computer readable storage device further comprising program code for causing the computer system to:

identify a target sound range;

remove frequencies that vary from the target sound range by more than a predetermined tolerance;

take a level measurement of the audio stream over a predetermined time window to eliminate spikes;

generate a frequency-domain representation of the audio stream;

time average the audio stream to eliminate the spikes;

apply a squelch algorithm to eliminate the undesired artifacts; and

weight the audio stream and the frequency-domain representation to produce a final response level measurement.

19. The program product of claim 15, the event being selected from a group consisting of a sporting event, a political rally, and a religious gathering.

20. The program product of claim 15, the audio stream being generated by a set of from participants and a set of attendees of the event.

21. The program product of claim 15, the audio stream being captured using a set of microphones.

22. A method for deploying a system for analyzing crowd noise, comprising:

providing a computer infrastructure having a computer device being operable to;

receive an audio stream for an event having a first participant and a second participant located at a venue, the audio stream containing crowd noise from a crowd that is distinct from the first participant and the second participant;

determine a geography for the event, the geography including geographic characteristics that include a geographic location of the venue of the event;

time code the audio stream;

compare a geographic characteristic of the first and second participants to the geographic characteristics of the event to identify one of the first participant or the second participant as a home participant of the event;

normalize the audio stream based on the geography and the home participant; and

process substantially an entirety of the audio stream to remove undesired artifacts and to identify, from noise levels in the substantially the entirety of the audio stream, a set of highlights from the crowd noise.