Playlist generation method and apparatus

• US 8,972,481 B2
• Filed: 07/20/2001
• Issued: 03/03/2015
• Est. Priority Date: 07/20/2001
• Status: Active Grant

• Current Assignee: Audible Magic Corporation
• Original Assignee: Audible Magic Corporation
• Inventors: Schrempp, James B., Ikezoye, Vance, Wold, Erling H., Blum, Thomas L., Keislar, Douglas F., Wheaton, James A.
• Primary Examiner(s): Patel, Dhairya A
• Application Number:
  US09/910,680
• Publication Number:
  US 20030018709A1
• Time in Patent Office: 4,974 Days
• Field of Search: 704/270, 704/235, 709/203, 709/223, 707/1, 714/38, 705/51, 705/55, 705/310, 705/58
• US Class Current: 709/203
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 16/275 Synchronous replication
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• 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: 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

Abstract

A method and system for playlist generation is disclosed. In one aspect, the system may include at least one analysis module for receiving and analyzing an unknown work and generating a corresponding representation thereof, and at least one identification (ID) server for receiving the representation from the analysis modules and determining the identity of the unknown work.

Claims

1. A system comprising:

a memory;

a processor coupled to the memory; and

at least one analysis module executed from the memory by the processor to;

receive a portion of audio data of a broadcast signal, wherein the portion of audio data comprises a plurality of unknown works,

generate a segment representation of each of a plurality of segments from the portion of audio data, wherein the plurality of segments comprise portions of the plurality of unknown works,

transmit the segment representations over a network to an identification (ID) server, wherein the ID server is to identify the plurality of unknown works based on identifying one or more of the segment representations that correspond to one or more segments of a plurality of reference works, to generate separate playlists for two or more of the identified works, the separate playlists each identifying broadcast instances of a single identified work, and to output identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying the one or more segment representations that correspond to the one or more segments of the plurality of reference works, and

purge the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to receiving the identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works.

2. The system of claim 1, wherein the at least one analysis module further comprises an input port configured to receive the portion of audio data of the broadcast signal from a networked source.

3. The system of claim 1, wherein the at least one analysis module further comprises an input port configured to receive the portion of audio data of the broadcast signal from a broadcast source.

4. The system of claim 1, wherein the segment representations comprise feature vectors.

5. The system of claim 1, wherein the segment representations comprise spectral representations.

6. The system of claim 1, wherein the segment representations comprise text output of a speech recognition system.

7. The system of claim 1, wherein the segment representations comprise a musical score output of a music transcription system.

8. The system of claim 1, wherein the segment representations comprise bit calculated keys.

9. The system of claim 1, wherein said ID server is configured to identify the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works using feature vectors.

10. The system of claim 1, wherein each of the segment representations comprise a spectral representation of a corresponding segment of the portion of audio data, and the ID server is configured to identify the one or more of the segment representations that correspond to one or more segments of the plurality of reference works using the spectral representations.

11. The system of claim 1, wherein the ID server is configured to identify the one or more of the segment representations that correspond to one or more segments of the plurality of reference works using bit calculated keys.

12. The system of claim 1, wherein the at least one analysis module is further configured to receive a plurality of portions of audio data of at least one broadcast signal for analysis at a single location.

13. The system of claim 1, wherein the at least one analysis module is further configured to receive a plurality of portions of audio data of at least one broadcast signal for analysis at a plurality of different access points of the network.

14. The system of claim 1, wherein the at least one analysis module is configured to transmit the segment representations to the ID server at a predetermined time interval.

15. The system of claim 1, wherein the at least one analysis module is configured to transmit the segment representations to the ID server responsive to receiving the portion of audio data of the broadcast signal and generating the segment representations.

16. The system of claim 1, wherein the at least one analysis module is configured to transmit the segment representations to the ID server based on an out-of-band event.

17. The system of claim 1, wherein the ID server is further configured to update one playlist of the separate playlists with the identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying a broadcast instance of the single identified work that is associated with the one playlist.

18. The system of claim 1, wherein the broadcast signal comprises an analog broadcast signal, and the at least one analysis module is further to digitize the received portion of audio data.

19. The system of claim 1, wherein the portion of audio data comprises unknown portions of the plurality of unknown works with unknown boundaries between the plurality of unknown works.

20. A method comprising:

receiving, by a processor, a portion of audio data of a broadcast signal, wherein the portion of audio data comprises one or more unknown works;

generating, by the processor, a segment representation of each of a plurality of segments from the portion of audio data, wherein the plurality of segments comprise portions of the one or more unknown works;

sending, by the processor, the segment representations to an identification server over a network, wherein the identification server identifies the one or more unknown works based on identifying one or more segment representations that correspond to one or more segments of a plurality of reference works, generates separate playlists for each of the one or more identified works, the separate playlists each identifying broadcast instances of a different identified work, and outputs identification of the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying the one or more segment representations that correspond to the one or more segments of the plurality of reference works; and

purging at least one file associated with the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to receiving the identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works.

21. The method of claim 20, further comprising:

storing the identification of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works in a playlist database.

22. The method of claim 20, further comprising:

sending, by the identification server, the identification of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works to the processor.

23. The method of claim 20, wherein the network is the Internet.

24. The method of claim 20, wherein generating the representations comprises:

generating feature vectors of each of the plurality of segments from the portion of audio data.

25. The method of claim 20, wherein generating the segment representations comprises:

generating a spectral representation of each of the plurality of segments from the portion of audio data.

26. The method of claim 20, wherein generating the segment representations comprises:

generating a text output of each of the plurality of segments of the portion of audio data using a speech recognition system.

27. The method of claim 20, wherein the segment representations comprise a musical score output for each of the plurality of segments of the portion of audio data using a music transcription system.

28. The method of claim 20, wherein the segment representations comprise a bit calculated key for each of the plurality of segments of the portion of audio data.

29. The method of claim 20, wherein the identification server identifying the one or more unknown works comprises:

determining the identity of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works using feature vectors in the segment representations.

30. The method of claim 20, wherein the identification server identifying the one or more unknown works comprises:

determining the identity of the one or more segment representations that correspond to one or more segments of the plurality of reference works using a spectral representation in each of the segment representations.

31. The method of claim 20, wherein the identification server identifying the one or more unknown works comprises:

determining the identity of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works using a text output, in each of the segment representations, from a speech recognition system.

32. The method of claim 20, wherein the identification server identifying the one or more unknown works comprises:

determining the identity of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works using a musical score output, in each of the segment representations, from a music transcription system.

33. The method of claim 20, wherein the identification server identifying the one or more unknown works comprises:

determining the identity of the one or more segment representations that correspond to one or more segments of the plurality of reference works using a bit calculated key in the segment representations.

34. The method of claim 20, wherein receiving the portion of audio data comprises:

receiving a plurality of portions of audio data of at least one broadcast signal for analysis at a single location.

35. The method of claim 20, wherein receiving the portion of audio data comprises:

receiving a plurality of portions of audio data of at least one broadcast signal for analysis at different access points of the network.

36. The method of claim 20, wherein sending the segment representations to the identification server comprises:

sending the segment representations responsive to generating the segment representations.

37. The method of claim 20, wherein the portion of audio data comprises unknown portions of the one or more unknown works with unknown boundaries.

38. The method of claim 20, wherein the broadcast signal comprises an analog broadcast signal, the method further comprising:

digitizing the received portion of the audio data.

39. A method comprising:

receiving a plurality of segment representations generated from a plurality of segments of a portion of audio data of a broadcast signal over a network, wherein the portion of audio data comprises a plurality of unknown works, and wherein the plurality of segments comprise portions of the plurality of unknown works;

identifying the plurality of unknown works based on identifying one or more of the segment representations that correspond to one or more segments of a plurality of reference works;

updating separate playlists for two or more of the identified works, the separate playlists each identifying broadcast instances of an associated identified work; and

outputting identification of the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying the one or more segment representations that correspond to the one or more segments of the plurality of reference works to enable a remote device to purge the one or more segment representations that correspond to the one or more segments of the plurality of reference works.

40. The method of claim 39, wherein the portion of audio data comprises unknown portions of the plurality of unknown works with unknown boundaries between the plurality of unknown works.

41. A system comprising:

a memory; and

a processor coupled to the memory, the processor comprising;

means for receiving a portion of audio data of a broadcast signal over a network, wherein the portion of audio data comprises a plurality of unknown works;

means for generating a representation of each of a plurality of segments from the portion of audio data, wherein the plurality of segments comprise portions of the plurality of unknown works; and

means for sending the segment representations to an identification server over a network, wherein the identification server identifies the plurality of unknown works based on identifying one or more of the segment representations that correspond to one or more segments of a plurality of reference works, generates separate playlists for two or more of the identified works, the separate playlists each identifying broadcast instances of an associated identified work, and provides identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying the one or more segment representations that correspond to the one or more segments of the plurality of reference works; and

means for purging the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to receiving the identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works.

42. The system of claim 41, further comprising:

means for storing the identification of the one or more of the segment representations that correspond to one or more segments of the plurality of reference works in a playlist database.

43. The system of claim 41, further comprising:

means for generating at least one of the separate playlists responsive to the identification of the one or more of the segment representations that correspond to one or more segments of a particular reference work.

44. The system of claim 41, further comprising:

means for updating at least one of the separate playlists responsive to the identification of the one or more of the segment representations that correspond to one or more segments of a particular reference work.

45. The system of claim 41, wherein the portion of audio data comprises unknown portions of the plurality of unknown works with unknown boundaries between the plurality of unknown works.

46. The system of claim 41, wherein the broadcast signal comprises an analog broadcast signal, the system further comprising:

means for digitizing the received portion of audio data.

47. A system comprising:

a memory; and

a processor coupled to the memory, the processor comprising;

means for receiving a portion of audio data of a broadcast signal, wherein the portion of the audio data comprises a plurality of unknown works;

means for generating a segment representation of each of a plurality of segments from the portion of audio data;

means for sending the segment representations to an identification server over a network, wherein the identification server identifies the plurality of unknown works based on identifying one or more of the segment representations that correspond to one or more segments of a plurality of reference works, generates separate playlists for two or more of the identified works, the separate playlists each identifying broadcast instances of an associated identified work, and provides identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works responsive to identifying the one or more segment representations that correspond to the one or more segments of the plurality of reference works;

means for purging the one or more segment representations that correspond to the one or more segments of the plurality of reference works responsive to receiving the identification of the one or more of the segment representations that correspond to the one or more segments of the plurality of reference works; and

means for sending an indication of the at least one of the identified works to at least one other computer system over the network.