System for monitoring broadcast audio content

• US 6,574,594 B2
• Filed: 06/29/2001
• Issued: 06/03/2003
• Est. Priority Date: 11/03/2000
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Pitman, Michael C., Fitch, Blake G., Germain, Robert S., Abrams, Steven
• Primary Examiner(s): Knepper, David D.
• Application Number:
  US09/896,849
• Publication Number:
  US 20020099555A1
• Time in Patent Office: 704 Days
• Field of Search: 704/231, 704/236, 704/246, 704/270, 725/22, 702/73
• US Class Current: 704/236
• CPC Class Codes: G11B 20/00086 Circuits for prevention of unauthorised reproduction or copying, e.g. piracy indicating unauthorised use of record carriers in general G11B23/28; scrambling for television signal recording H04N5/913; network architectures or network protocols for network security H04L63/00; cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
• CPC Class Codes: G11B 20/10527 Audio or video recording; Data buffering arrangements G11B20/12 - G11B20/18 take precedence
• CPC Class Codes: G11B 2020/10546 specifically adapted for audio data
• CPC Class Codes: H04H 20/14 for monitoring programmes
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/4627 Rights management associated to the content security in data switching network management H04L41/28; security management or policies for network security H04L63/20; access security in wireless networks H04W12/08

Abstract

A broadcast datastream is received, and audio identifying information is generated for audio content from the broadcast datastream. It is determined whether the audio identifying information generated for the broadcast audio content matches audio identifying information in an audio content database. In one preferred embodiment, the audio identifying information is an audio feature signature that is based on audio content. Also provided is a system for monitoring broadcast audio content.

Claims

1. A method for monitoring broadcast audio content, said method comprising the steps of:

receiving a broadcast datastream;

generating audio identifying information for audio content from the broadcast datastream based on detected events in the audio content; and

determining whether the audio identifying information generated for the broadcast audio content matches audio identifying information in an audio content database,

wherein the generating step includes the sub-step of;

detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average,

wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and

the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content.

2. The method according to claim 1, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content.

3. The method according to claim 2, wherein the determining step includes the sub-step of comparing the audio feature signature generated for the broadcast audio content with the audio feature signatures stored in the audio content database.

4. The method according to claim 1, further comprising the steps of:

generating audio identifying information for predetermined audio content based on detected events in the predetermined audio content; and

storing the audio identifying information for the predetermined audio content in the audio content database.

5. The method according to claim 1, further comprising the step of:

if the audio identifying information generated for the broadcast audio content matches audio identifying information in the audio content database, recording information including identification of the audio content and a broadcast source from which the broadcast datastream was received.

6. The method according to claim 5, further comprising the steps of:

compiling at least one list from the recorded information, the list including all broadcasts of a plurality of pieces of audio content; and

dividing royalties based at least partially on the number of times each pieces of audio content is broadcast.

7. The method according to claim 5, further comprising the steps of:

compiling at least one list from the recorded information, the list including all of the audio content broadcast by at least one broadcast source; and

charging royalties to the broadcast source based on the list.

8. The method according to claim 5, further comprising the step of:

compiling at least one list from the recorded information, the list including all broadcasts of at least one piece of audio content; and

charging a fee for the list.

9. The method according to claim 1, wherein the generating step further includes the sub-steps of:

obtaining an audio signal characterized by a time dependent power spectrum;

analyzing the spectrum to obtain the time dependent frequency components; and

producing the audio identifying information for the audio content from the broadcast datastream based on the detected events.

10. The method according to claim 9, wherein the sub-step of analyzing the spectrum includes:

sampling the audio signal to obtain a plurality of audio signal samples;

taking a plurality of subsets from the plurality of audio signal samples; and

performing a Fourier transform on each of the plurality of subsets to obtain a set of Fourier frequency components.

11. The method according to claim 9, wherein the sub-step of detecting a plurality of events includes:

keeping the first running average over the first averaging period of the plurality of time dependent frequency components so as to obtain a first series of averages for the first averaging period;

keeping the second running average over the second averaging period of the plurality of time dependent frequency components so as to obtain a second series of averages for the first averaging period; and

recording a plurality of event times, each of the event times being a time at which there occurs one of the detected events of the first running average crossing the second running average.

12. The method according to claim 1, wherein the generating step further includes the sub-steps of:

performing a Fourier transformation of the audio signals of the portion into a time series of audio power dissipated over a first plurality of frequencies;

grouping the frequencies into a smaller second plurality of bands that each include a range of neighboring frequencies;

detecting power dissipation events in each of the bands; and

grouping together the power dissipation events from mutually adjacent bands at a selected moment so as to form the identifying feature.

13. A computer-readable medium encoded with a program for monitoring broadcast audio content, said program containing instructions for performing the steps of:

receiving a broadcast datastream;

generating audio identifying information for audio content from the broadcast datastream based on detected events in the audio content; and

determining whether the audio identifying information generated for the broadcast audio content matches audio identifying information in an audio content database,

wherein the generating step includes the sub-step of;

detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average,

wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and

the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content.

14. The computer-readable medium according to claim 13, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content.

15. The computer-readable medium according to claim 14, wherein the determining step includes the sub-step of comparing the audio feature signature generated for the broadcast audio content with the audio feature signatures stored in the audio content database.

16. The computer-readable medium according to claim 13, wherein said program further contains instructions for performing the steps of:

generating audio identifying information for predetermined audio content based on detected events in the predetermined audio content; and

storing the audio identifying information for the predetermined audio content in the audio content database.

17. The computer-readable medium according to claim 13, wherein said program further contains instructions for performing the step of:

if the audio identifying information generated for the broadcast audio content matches audio identifying information in the audio content database, billing a broadcast source from which the broadcast datastream was received.

18. The computer-readable medium according to claim 13, wherein said program further contains instructions for performing the steps of:

if the audio identifying information generated for the broadcast audio content matches audio identifying information in the audio content database, recording information including identification of the audio content and a broadcast source from which the broadcast datastream was received;

compiling at least one list from the recorded information, the list including all broadcasts of a plurality of pieces of audio content; and

dividing royalties based at least partially on the number of times each pieces of audio content is broadcast.

19. The computer-readable medium according to claim 13, wherein said program further contains instructions for performing the steps of:

if the audio identifying information generated for the broadcast audio content matches audio identifying information in the audio content database, recording information including identification of the audio content and a broadcast source from which the broadcast datastream was received;

compiling at least one list from the recorded information, the list including all broadcasts of at least one piece of audio content; and

charging a fee for the list.

20. The computer-readable medium according to claim 13, wherein the generating step further includes the sub-steps of:

obtaining an audio signal characterized by a time dependent power spectrum;

analyzing the spectrum to obtain the time dependent frequency components; and

producing the audio identifying information for the audio content from the broadcast datastream based on the detected events.

21. The computer-readable medium according to claim 20, wherein the sub-step of analyzing the spectrum includes:

sampling the audio signal to obtain a plurality of audio signal samples;

taking a plurality of subsets from the plurality of audio signal samples; and

performing a Fourier transform on each of the plurality of subsets to obtain a set of Fourier frequency components.

22. The computer-readable medium according to claim 20, wherein the sub-step of detecting a plurality of events includes:

keeping the first running average over the first averaging period of the plurality of time dependent frequency components so as to obtain a first series of averages for the first averaging period;

keeping the second running average over the second averaging period of the plurality of time dependent frequency components so as to obtain a second series of averages for the first averaging period; and

recording a plurality of event times, each of the event times being a time at which there occurs one of the detected events of the first running average crossing the second running average.

23. The computer-readable medium according to claim 14, wherein the generating step further includes the sub-steps of:

performing a Fourier transformation of the audio signals of the portion into a time series of audio power dissipated over a first plurality of frequencies;

grouping the frequencies into a smaller second plurality of bands that each include a range of neighboring frequencies;

detecting power dissipation events in each of the bands; and

grouping together the power dissipation events from mutually adjacent bands at a selected moment so as to form the identifying feature.

24. A system for monitoring broadcast audio content, said system comprising:

a receiver for receiving a broadcast datastream;

an identifying information generator for generating audio identifying information based on detected events in audio content from the broadcast datastream; and

a match detector for determining whether the audio identifying information generated for the broadcast audio content matches audio identifying information in an audio content database,

wherein the identifying information generator detects a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average,

the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and

the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content.

25. The system according to claim 24, wherein the audio identifying information is an audio feature signature that is based on the detected events in the audio content.

26. The system according to claim 24, wherein the audio content database stores audio identifying information for predetermined audio content.

27. The system according to claim 24, further comprising:

an invoicer for charging a fee to a broadcast source from which the broadcast datastream was received, if the audio identifying information generated for the broadcast audio content matches audio identifying information in the audio content database.

28. The system according to claim 24, further comprising:

an information collector for recording information including identification of the audio content and a broadcast source from which the broadcast datastream was received, if the audio identifying information generated for the audio content matches audio identifying information in the audio content database;

a list generator for compiling at least one list from the recorded information, the list including all broadcasts of a plurality of pieces of audio content; and

a royalty calculator for assigning royalties based at least partially on the number of times each pieces of audio content is broadcast.

29. The system according to claim 24, further comprising:

an information collector for recording information including identification of the audio content and a broadcast source from which the broadcast datastream was received, if the audio identifying information generated for the audio content matches audio identifying information in the audio content database;

a list generator for compiling at least one list from the recorded information, the list including all broadcasts of at least one piece of audio content; and

an invoicer for charging a fee for the list.

30. A method for charging royalties for usage of copyrighted audio content, said method comprising the steps of:

receiving a broadcast datastream;

generating audio identifying information for audio content from the broadcast datastream based on detected events in the audio content;

determining whether the audio identifying information generated for the broadcast audio content matches audio identifying information in a copyrighted audio content database; and

if the audio identifying information generated for the broadcast audio content matches audio identifying information in the copyrighted audio content database, billing a broadcast source from which the broadcast datastream was received,

wherein the generating step includes the sub-step of;

detecting a plurality of events in the audio content, each of the events being a crossing of the value of a first running average and the value of a second running average,

wherein the first running average is an average over a first averaging period of a plurality of time dependent frequency components of the audio content, and

the second running average is an average over a second averaging period, which is different than the first averaging period, of the time dependent frequency components of the audio content.