Method and apparatus for identification of broadcast source

• US 8,290,423 B2
• Filed: 06/20/2011
• Issued: 10/16/2012
• Est. Priority Date: 02/19/2004
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Shazam Ivestments Ltd. (Apple Inc.)
• Inventors: Wang, Avery Li-Chun
• Primary Examiner(s): Sobutka, Philip
• Application Number:
  US13/164,069
• Publication Number:
  US 20110244784A1
• Time in Patent Office: 484 Days
• Field of Search: None
• US Class Current: 455/2.01
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04B 17/23 Indication means, e.g. displays, alarms, audible means
• CPC Class Codes: H04H 20/71 Wireless systems
• CPC Class Codes: H04H 20/88 Stereophonic broadcast systems multiplex system in general H04J
• CPC Class Codes: H04H 2201/50 characterised by the use of watermarks
• CPC Class Codes: H04H 2201/90 characterised by the use of signatures
• CPC Class Codes: H04H 60/27 Arrangements for recording or accumulating broadcast information or broadcast-related information
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/43 for identifying broadcast channels
• CPC Class Codes: H04H 60/44 for identifying broadcast stations
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/63 for services of sales data processing systems or methods specially adapted for electronic commerce G06Q30/00

Abstract

A user (102) hears an audio program being broadcast and can record a sample of the audio. The sample is then conveyed to an analyzing means (106) to determine to which broadcast station the user is listening. The analyzing means monitors many broadcast channels. Thus, characteristics of the audio sample and samples taken from the broadcast channels can be compared to find a match. Broadcast information pertaining to the broadcast channel from which the match was found may then be reported back to the user, combined with an advertisement of a promotion, prize notification, discount offers, and other information specific for a certain radio station for example.

Claims

1. A method for identifying a broadcast source of content comprising:

receiving a sample of content that is a rendition of a segment of content from a source;

determining characteristics of the sample of content;

performing a comparison of relative locations, within the sample of content, of the characteristics of the sample of content with relative locations, within a source sample, of characteristics of the source sample, wherein the source sample is taken from content rendered by a known source; and

based on the comparison, determining that the known source rendered the segment of content.

2. The method of claim 1, wherein performing the comparison comprises:

comparing the characteristics of the sample of content with characteristics of the source sample at approximately temporally corresponding timepoints.

3. The method of claim 1, further comprising:

identifying an estimated time offset of the sample of content, the estimated time offset of the sample of content indicating a time position in the segment of content;

comparing the estimated time offset of the sample of content with a time offset of the source sample.

4. The method of claim 1, further comprising:

performing a plurality of comparisons of the relative locations, within the sample of content, of characteristics of the sample of content with relative locations, within a source sample, of characteristics of a plurality of source samples taken from content rendered by known sources; and

based on the comparisons, identifying one of the known sources as a source from which the segment of content was rendered.

5. The method of claim 4, further comprising:

identifying a sample from the plurality of source samples that has characteristics which most closely match the characteristics of the sample of content; and

identifying a known source from which the identified sample was taken as a source from which the sample of content was rendered.

6. The method of claim 1, further comprising comparing an identity of the sample of content with an identity of the source sample.

7. The method of claim 1, further comprising receiving from a client device the sample of content that is a rendition of a segment of content from a source.

8. The method of claim 7, further comprising sending information identifying the known source to the client device.

9. The method of claim 8, wherein the information includes an advertisement.

10. The method of claim 1, further comprising:

recording a plurality of source samples from content rendered by each of the known sources; and

recording a time at which each of the plurality of source samples was recorded.

11. The method of claim 1 further comprising:

wherein the sample of content is a rendition of a segment of content comprising a transition of programs on the source;

comparing the transition within the sample of content with transitions within source samples taken from content rendered by known sources; and

identifying a content alignment between the transition within the sample of content and at least one transition within a source sample.

12. The method of claim 1, further comprising:

identifying variations in the sample of content, the variations including non-music content superimposed upon audio content; and

comparing the variations in the sample of content with variations in the source sample.

13. The method of claim 1, further comprising:

identifying a change of identity of content within the sample of content;

comparing a first identity of the sample of content with an identity of the source sample; and

comparing a second identity of the sample of content with an identity of the source sample.

14. The method of claim 1, further comprising:

determining a stretch factor of the sample of content, the stretch factor indicating a difference between a speed at which the sample of content was rendered and a speed of an original playback of the segment of content; and

comparing the stretch factor of the sample of content with a stretch factor of the source sample.

27. The method of claim 1, wherein the sample of content that is a rendition of a segment of content from a source includes fingerprints determined at landmarks of the sample of content.

28. The method of claim 1, wherein the segment of content is broadcast from the source, and the method further comprises receiving the source sample at approximately the sampling time of the sample of content.

29. The method of claim 1, wherein the method is performed in real-time.

30. The method of claim 1, wherein determining the characteristics of the sample of content comprises determining fingerprints at landmarks of the sample of content.

33. The method of claim 1, wherein the source sample is taken from content previously rendered by a known source, and wherein the sample of content is a rendition of a segment of content from a source that is currently being rendered.

34. The method of claim 1, wherein determining the characteristics of the sample of content comprises:

determining one or more values that characterize one or more features in the sample of content; and

determining a hash value based on a hash function of the one or more values that characterize one or more features in the sample of content.

35. The method of claim 34, wherein performing the comparison comprises performing a search of characteristics of a source sample taken from content rendered by a known source using the determined hash value.

36. The method of claim 35, wherein performing the search of characteristics of the source sample taken from content rendered by the known source using the determined hash value comprises performing a symbolic search of the characteristics of the sample of content from a database index of characteristics of a source sample taken from content rendered by a known source.

37. The method of claim 36, wherein the database index includes a database of symbolic characteristics of source samples taken from content rendered by known sources.

38. The method of claim 34, wherein the hash value is a numeric value.

39. The method of claim 34, further comprising determining a match between the sample of content and the source sample based on determining a threshold number of matches between hash values of the sample of content and hash values of the source sample.

15. A non-transitory computer readable medium having stored therein instructions executable by a computing device to cause the computing device to perform operations comprising:

receiving a sample of content that is a rendition of a segment of content from a source;

determining characteristics of the sample of content;

performing a comparison of relative locations, within the sample of content, of the characteristics of the sample of content with relative locations, within a source sample, of characteristics of the source sample, wherein the source sample is taken from content rendered by a known source; and

based on the comparison, determining that the known source rendered the segment of content.

16. The non-transitory computer readable medium of claim 15, wherein performing the comparison comprises:

comparing the characteristics of the sample of content with characteristics of the source sample at approximately temporally corresponding timepoints.

17. The non-transitory computer readable medium of claim 15, further comprising instructions to cause the computing device to perform operations comprising:

performing a plurality of comparisons of the relative locations, within the sample of content, of characteristics of the sample of content with relative locations, within a source sample, of characteristics of a plurality of source samples taken from content rendered by known sources; and

based on the comparisons, identifying one of the known sources as a source from which the segment of content was rendered.

18. The non-transitory computer readable medium of claim 15, further comprising instructions to cause the computing device to perform operations comprising comparing an identity of the sample of content with an identity of the source sample.

19. The non-transitory computer readable medium of claim 15, further comprising instructions to cause the computing device to perform operations comprising receiving from a client device the sample of content that is a rendition of a segment of content from a source.

20. The non-transitory computer readable medium of claim 15, further comprising instructions to cause the computing device to perform operations comprising sending information identifying the known source to client device.

31. The non-transitory computer readable medium of claim 15, wherein the sample of content that is a rendition of a segment of content from a source includes fingerprints determined at landmarks of the sample of content.

32. The non-transitory computer readable medium of claim 15, wherein the segment of content is broadcast from the source, and the instructions further comprise instructions to cause the computing device to perform operations comprising receiving the source sample at approximately the sampling time of the sample of content.

21. A monitoring station comprising:

a broadcast channel sampler configured to receive source samples of content rendered by respective known sources; and

a processor configured to receive from a client device a sample of content that is a rendition of a segment of content from a source, to perform a comparison of relative locations, within the sample of content, of characteristics of the sample of content with relative locations, within a given source sample, of characteristics of the given source sample, and based on the comparison to identify a known source from which the segment of content was rendered.

22. The monitoring station of claim 21, wherein the broadcast channel sampler is configured to sample the content rendered by the respective known sources to generate the source samples.

23. The monitoring station of claim 22, wherein the broadcast channel sampler is configured to sample the content rendered by the respective known sources on a continual basis.

24. The monitoring station of claim 22, wherein the processor is further configured to compare an identity of the sample of content with identities of the source samples, and to identify the known source from which the segment of content was rendered based on matching identities between the sample of content and the source samples.

25. The monitoring station of claim 21, wherein the sample of content that is a rendition of a segment of content from a source includes fingerprints determined at landmarks of the sample of content.

26. The monitoring station of claim 21, wherein the segment of content is broadcast from the source, and wherein the processor is configured to receive the source samples at approximately a sampling time of the sample of content.