Method and apparatus for identifying new media content

• US 7,877,438 B2
• Filed: 10/23/2001
• Issued: 01/25/2011
• Est. Priority Date: 07/20/2001
• Status: Active Grant

• Current Assignee: Audible Magic Corporation
• Original Assignee: Audible Magic Corporation
• Inventors: Ikezoye, Vance, Schrempp, James B., Kvitek, Louis, Wold, Erling H.
• Primary Examiner(s): Follansbee; John
• Assistant Examiner(s): Patel; Dhairya A
• Application Number:
  US09/999,763
• Publication Number:
  US 20030033321A1
• Time in Patent Office: 3,381 Days
• Field of Search: 709/104, 709/203, 700/94, 713/193, 713/194
• US Class Current: 709/203
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04H 20/14 for monitoring programmes
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: H04N 21/2407 Monitoring of transmitted content, e.g. distribution time, number of downloads arrangements for monitoring programmes for broadcast or for distribution combined with broadcast H04H20/14
• CPC Class Codes: H04N 21/254 Management at additional data server, e.g. shopping server, rights management server arrangements for maintenance or administration in data networks H04L41/00; network services using third party service providers H04L67/53
• CPC Class Codes: H04N 7/16 Analogue secrecy systems; Analogue subscription systems
• CPC Class Codes: H04W 24/00 Supervisory, monitoring or testing arrangements
• CPC Class Codes: H04W 4/00 Services specially adapted for wireless communication networks; Facilities therefor

Abstract

A new media identification system is disclosed. In one aspect, a system may comprise at least one analysis module for receiving and analyzing an received work and generating a corresponding representation thereof; at least one identification (ID) server for receiving the representation from the at least one analysis module and generating a list of unidentifiable received works. A method for identifying new media is also disclosed. In one aspect, a method may comprise receiving an unidentified segment; determining whether the unidentified segment is similar to previously received unidentified segments; and sequentially arranging similar unidentified segments in a single super segment.

Claims

1. A new media identification system comprising:

at least one analysis module, including a first processor and a first memory, for receiving transmission of signals from at least one source, the signals including data from a portion of a master recording, dividing said data into a plurality of segments, generating a segment representation of each of the plurality of segments, and transmitting said segment representation to an identification server; and

at least one identification server, including a second processor and a second memory, for receiving said segment representation from said at least one analysis module, comparing said segment representation to a plurality of reference segment representations, determining that said segment representation is not identified, and adding said segment representation to a list for holding a plurality of unidentified segment representations;

wherein one of said at least one analysis module and said identification server is configured to compare segment representations of unidentified segments to segment representations of other unidentified segments, wherein the comparison comprises;

dividing a first unidentified segment representation into first sub-segments and a second unidentified segment representation into second sub-segments;

comparing the first sub-segments to the second sub-segments;

identifying a first subset of the first sub-segments that matches a second subset of the second sub-segments, wherein the first subset is a sequential run of the first sub-segments and the second subset is a sequential run of the second sub-segments; and

determining that the first subset and the second subset are associated with a performance of the same master recording;

wherein one of said at least one analysis module and said identification server is configured to create a representation of a super segment by combining the sequential run of sub-segments of at least one of the first subset or the second subset.

2. The system of claim 1, wherein said at least one analysis module further includes an input port configured to receive said transmission of signals from at least one networked source.

3. The system of claim 1, wherein said at least one analysis module further includes an input port configured to receive said transmission of signals from at least one broadcast source.

4. The system of claim 1, wherein said at least one analysis module further includes an input port configured to receive said transmission of signals in the form of a pre-broadcast digital form.

5. The system of claim 1, wherein said at least one analysis module and said at least one identification server may be coupled over a network.

6. The system of claim 5, wherein said network comprises the Internet.

7. The system of claim 1, wherein said segment representation comprises feature vectors.

8. The system of claim 1, wherein said segment representation comprises a spectral representation of said received master recording.

9. The system of claim 1, wherein said segment representation comprises the text output of a speech recognition system.

10. The system of claim 1, wherein said segment representation comprises the musical score output of a music transcription system.

11. The system of claim 1, wherein said segment representation comprises a bit calculated key.

12. The system of claim 1, wherein said segment representation includes an indication of significance of changes in media signal content.

13. The system of claim 1, wherein said at least one analysis modules are further configured to receive transmissions of signals from a plurality of streaming sources for analysis at a single location.

14. The system of claim 1, wherein said at least one analysis modules are further configured to receive transmissions of signals from a plurality of streaming sources for analysis at a plurality of different access points of the network.

15. The system of claim 1, wherein said at least one analysis module is configured to provide said segment representations to said at least one identification server at a predetermined time interval.

16. The system of claim 15, wherein said predetermined time interval comprises at least once a day.

17. The system of claim 15, wherein said predetermined time interval comprises approximately once an hour.

18. The system of claim 15, wherein said at least one analysis module is configured to provide said segment representations to said at least one identification server responsive to receiving said transmission.

19. The system of claim 15, wherein said at least one analysis module is configured to provide said segment representations to said at least one identification server when a predetermined threshold of resource utilization is crossed.

20. The system of claim 15, wherein said at least one analysis module is configured to provide said segment representations to said at least one identification server based on an out-of-band event.

21. The system of claim 1, wherein said identification server is further configured to generate a playlist of identified master recordings.

22. The system of claim 1, wherein said identification server is further configured to generate a playlist of identified master recordings received from different access points of the network responsive to receiving said transmission.

23. The system of claim 1, wherein said system is further configured to create groups of representations of super segments comprising repeat performances of the same master recording.

24. The system of claim 1, wherein said data is collected from a plurality of media streams.

25. The system of claim 1, wherein said system is further configured to report representations of super segments based on length.

26. The system of claim 25, wherein any repeating super segments less than 63 seconds in length are reported as advertisements.

27. The system of claim 25, wherein any repeating super segments between 2 and 15 minutes are reported as a song.

28. The system of claim 25, wherein any repeating super segments exceeding 5 seconds are reported as a repeated broadcast.

29. The system of claim 28, wherein said repeated broadcast comprises a radio talk show.

30. The system of claim 28, wherein said repeated broadcast comprises a TV show.

31. The system of claim 25, wherein any repeating super segments between 5 and 15 seconds are reported as station identification.

32. The system of claim 1, wherein said representation of the super segment represents an unidentifiable master recording, and is used to construct a new media playlist database.

33. The system of claim 32 wherein said new media playlist is stored on said identification server.

34. The system of claim 32, wherein said new media playlist is stored on a distant server.

35. The system of claim 32, wherein repeating segment representations are merged into a playlist report of identified media.

36. The system of claim 32, wherein said representation of the super segment is provided to the identification server responsive to receiving said transmission, and said new media playlist is generated responsive to receiving said representation of the super segment.

37. The system of claim 1, further configured to implement a Least Recently Used (LRU) algorithm to remove reference samples from a reference database that have not been identified in a predetermined amount of time.

38. The system of claim 1, further configured to provide an electronic notification to third parties of new media detections made by said system.

39. A method for identifying new media, implemented by a computing system programmed to perform the following, comprising:

receiving a media stream;

dividing said media stream into a plurality of segments;

determining that at least one of said plurality of segments is an unidentified segment by an identification server;

dividing the unidentified segment into first sub-segments and a previously received unidentified segment into second sub-segments;

comparing the first sub-segments to the second sub-segments;

identifying a first subset of the first sub-segments that matches a second subset of the second sub-segments, wherein the first subset is a sequential run of the first sub-segments and the second subset is a sequential run of the second sub-segments;

determining that the first subset and the second subset are associated with a performance of a single master recording; and

arranging the sequential run of sub-segments in at least one of the first subset or the second subset into a single super segment.

40. The method of claim 39, further comprising:

decomposing said super segment into overlapping sub-segments;

comparing each of the overlapping sub-segments to additional overlapping sub-segments of additional super segments; and

identifying a repeat performance of a master recording if at least one of the overlapping sub-segments matches one of the additional overlapping sub-segments.

41. The method of claim 40, where the overlapping sub-segments are approximately 5 seconds in length.

42. The method of claim 40, further including the act of adding a newly received segment to said super segment if said newly received segment is determined to be similar to any of said segments which constitute said super segment.

43. The method of claim 39, further including the act of reporting super segments by length.

44. The method of claim 43 wherein a super segment of less than 63 seconds is reported as an advertisement.

45. The method of claim 43, wherein a super segment of less than approximately 63 seconds in length is reported as a news segment.

46. The method of claim 43, wherein a super segment of less than 63 seconds is reported as a station promotion.

47. The method of claim 43, wherein a super segment between approximately 2 and 15 minutes in length is reported as a song.

48. The method of claim 43, wherein a super segment between approximately 5 and 15 seconds is reported as a station identification.

49. The method of claim 43, wherein a super segment longer than approximately 23 minutes in length is reported as an entire broadcast.

50. The method of claim 39 wherein super segments that are repeat performances of the same master recording are grouped together.

51. The method of claim 50, wherein said super segments are further reported on based on their length.

52. A method for processing media where segments of unknown content are presented for analysis comprising:

receiving a transmission;

dividing said transmission into a plurality of segments;

determining whether each of said plurality of segments is an unidentified segment by an identification server;

dividing each of the unidentified segments into a plurality of sub-segments;

comparing each of a first plurality of sub-segments from a first unidentified segment to a second plurality of sub-segments from a second unidentified segment;

identifying a first subset of the first plurality of sub-segments that matches a second subset of the second plurality of sub-segments, wherein the first subset is a sequential run of the first plurality of sub-segments and the second subset is a sequential run of the second plurality of sub-segments;

recognizing that the first subset and the second subset are both associated with a performance of a single master recording;

creating a super segment by combining the sequential run of sub-segments in at least one of the first subset and the second subset; and

analyzing said super segment, wherein said analysis comprises an identification of the super segment.

53. The method of claim 52, wherein said analysis comprises a statistical analysis of the super segment.

54. The method of claim 52, wherein said analysis provides input to the generation of a playlist.

55. The method of claim 52, wherein said analysis is performed by an automated system.

56. The method of claim 52, wherein said analysis is performed by a human.

57. The method of claim 52, where the analysis provides identification of the single master recording.

58. The method of claim 52, where the analysis is correlated back to an original media stream.

59. A system for identifying new media comprising:

a memory, to store instructions for identifying the new media; and

a processor, connected with the memory, to execute the instructions, wherein the instructions cause the processor to;

receive a media stream;

divide said media stream into a plurality of segments;

determine that at least one of said plurality of segments is an unidentified segment;

divide the unidentified segment into first sub-segments and a previously received unidentified segment into second sub-segments;

compare the first sub-segments to the second sub-segments;

identify a first subset of the first sub-segments that matches a second subset of the second sub-segments, wherein the first subset is a sequential run of the first sub-segments and the second subset is a sequential run of the second sub-segments;

determine that the first subset and the second subset are associated with a performance of a single master recording; and

arrange the sequential run of sub-segments of at least one of the first subset or the second subset into a single super segment.

60. The system of claim 59, wherein the instructions further to cause the processor to:

decompose said super segment into overlapping sub-segments;

compare each of the overlapping sub-segments to additional overlapping sub-segments of additional super segments; and

identify a repeat performance of a master recording if at least one of the overlapping sub-segments matches one of the additional overlapping sub-segments.

61. The system of claim 60, wherein the instructions further to cause the processor to add newly received segments to said super segment if said newly received segments are determined to be similar to any of said segments which constitute said super segment.

62. The system of claim 59, wherein the instructions further to cause the processor to report super segments by length.

63. The system of claim 62 wherein a super segment of less than 63 seconds are reported as an advertisement.

64. The system of claim 62, wherein a super segment of less than approximately 63 seconds in length are reported as a news segment.

65. The system of claim 62, wherein a super segment of less than 63 seconds are reported as a station promotion.

66. The system of claim 62, wherein a super segment between approximately 2 and 15 minutes in length are reported as a song.

67. The system of claim 62, wherein a super segment longer than approximately 23 minutes in length is reported as an entire broadcast.

68. The system of claim 59, wherein the instructions further to cause the processor to group super segments together that are repeat performances of the same master recording.

69. The system of claim 68, wherein said super segments are further reported on based on their length.

70. A system of processing media where segments of unknown content are presented for analysis comprising:

a memory, to store instructions for processing the media; and

a processor, connected with the memory, to execute the instructions, wherein the instructions cause the processor to;

receive a transmission;

divide said transmission into a plurality of segments;

determine whether each of said plurality of segments is an unidentified segment;

divide each of the unidentified segments into a plurality of sub-segments;

compare each of a first plurality of sub-segments from a first unidentified segment to a second plurality of sub-segments from a second unidentified segment;

identify a first subset of the first plurality of sub-segments that matches a second subset of the second plurality of sub-segments, wherein the first subset is a sequential run of the first plurality of sub-segments and the second subset is a sequential run of the second plurality of sub-segments;

recognize that the first subset and the second subset are both associated with a performance of a single master recording;

create a super segment by combining the sequential run of sub-segments in at least one of the first subset and the second subset; and

analyze said super segment, wherein said analysis comprises an identification of the super segment.

71. The system of claim 70, wherein said analysis comprises a statistical analysis of the super segment.

72. The system of claim 70, wherein said analysis provides input to the generation of a playlist.

73. The system of claim 70, wherein said analysis is performed by an automated system.

74. The system of claim 70, wherein said analysis is performed by a human.

75. The system of claim 70, where said analysis provides identification of new master recordings.

76. The system of claim 70, where said analysis includes correlating analysis results back to an original media stream.

78. The non-transitory program storage device of claim 71, the method further comprising:

decomposing said super segment into overlapping sub-segments;

comparing each of the overlapping sub-segments to additional overlapping sub-segments of additional super segments; and

identifying a repeat performance of a master recording if at least one of the overlapping sub-segments matches one of the additional overlapping sub-segments.

79. The non-transitory program storage device of claim 78, where the overlapping sub-segments are approximately 5 seconds in length.

77. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method for identifying new media, said method comprising:

receiving a media stream;

dividing said media stream into a plurality of segments;

determining that at least one of said plurality of segments is an unidentified segment by an identification server;

dividing the unidentified segment into first sub-segments and a previously received unidentified segment into second sub-segments;

comparing the first sub-segments to the second sub-segments;

identifying a first subset of the first sub-segments that matches a second subset of the second sub-segments, wherein the first subset is a sequential run of the first sub-segments and the second subset is a sequential run of the second sub-segments;

determining that the first subset and the second subset are associated with a performance of a single master recording; and

arranging the sequential run of sub-segments of at least one of the first subset or the second subset into a single super segment.

80. The non-transitory program storage device of claim 77, further including the act of adding newly received segments to said super segment if said newly received segments are determined to be similar to any of said segments which constitute said super segment.

81. The non-transitory program storage device of claim 77, further including the act of reporting super segments by length.

82. The non-transitory program storage device of claim 81 wherein a super segment of less than 63 seconds are reported as an advertisement.

83. The non-transitory program storage device of claim 81, wherein a super segment of less than approximately 63 seconds in length are reported as a news segment.

84. The non-transitory program storage device of claim 81, wherein a super segment of less than 63 seconds are reported as a station promotion.

85. The non-transitory program storage device of claim 81, wherein a super segment between approximately 2 and 15 minutes in length are reported as a song.

86. The non-transitory program storage device of claim 81, wherein a super segment between approximately 5 and 15 seconds in length are reported as a station identification.

87. The non-transitory program storage device of claim 81, wherein a super segment longer than approximately 23 minutes in length is reported as an entire broadcast.

88. The non-transitory program storage device of claim 77 wherein super segments that are repeat performances of the same master recording are grouped together.

89. The non-transitory program storage device of claim 77, wherein said super segments are further reported on based on their length.

90. A non-transitory program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method for processing media where repeated segments of unknown content are presented for analysis comprising:

receiving a transmission;

dividing said transmission into a plurality of segments;

determining whether each of said plurality of segments is an unidentified segment by an identification server;

dividing each of the unidentified segments into a plurality of sub-segments;

comparing each of a first plurality of sub-segments from a first unidentified segment to a second plurality of sub-segments from a second unidentified segment;

identifying a first subset of the first plurality of sub-segments that matches a second subset of the second plurality of sub-segments, wherein the first subset is a sequential run of the first plurality of sub-segments and the second subset is a sequential run of the second plurality of sub-segments;

recognizing that the first subset and the second subset are both associated with a performance of a single master recording;

creating a super segment by combining the sequential run of sub-segments in at least one of the first subset and the second subset; and

analyzing said super segment, wherein said analysis comprises an identification of the super segment.

91. The non-transitory program storage device of claim 90, wherein said analysis comprises a statistical analysis of the super segment.

92. The non-transitory program storage device of claim 90, wherein said analysis provides input to the generation of a playlist.

93. The non-transitory program storage device of claim 90, wherein said analysis is performed by an automated system.

94. The non-transitory program storage device of claim 90, wherein said analysis is performed by a human.

95. The non-transitory program storage device of claim 90, where the analysis provides identification of new master recordings.

96. The non-transitory program storage device of claim 90, where the analysis is correlated back to an original media stream.