Method and system for identifying sound signals

• US 8,725,829 B2
• Filed: 04/26/2004
• Issued: 05/13/2014
• Est. Priority Date: 07/31/2000
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Shazam Ivestments Ltd. (Apple Inc.)
• Inventors: Wang, Avery Li-Chun, Barton, Christopher Jacques Penrose, Mukherjee, Dheeraj Shankar, Inghelbrecht, Philip
• Primary Examiner(s): CHOUDHURY, AZIZUL Q
• Application Number:
  US10/831,945
• Publication Number:
  US 20040199387A1
• Time in Patent Office: 3,669 Days
• Field of Search: 709/217
• US Class Current: 709/217
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence

Abstract

A method and system is described which allows users to identify (pre-recorded) sounds such as music, radio broadcast, commercials, and other audio signals in almost any environment. The audio signal (or sound) must be a recording represented in a database of recordings. The service can quickly identify the signal from just a few seconds of excerption, while tolerating high noise and distortion. Once the signal is identified to the user, the user may perform transactions interactively in real-time or offline using the identification information.

Claims

1. A method for identifying recorded sound signals comprising:

receiving a sound stream including an unidentified recorded sound;

processing the received sound stream to determine an index set of values corresponding to characteristics of the unidentified recorded sound, wherein the index set of values comprises fingerprint and landmark pairs, wherein the landmark indicates a distinctive and reproducible location for determining the fingerprint for the unidentified recorded sound;

searching a library using fingerprints of the fingerprint and landmark pairs, the library having sets of values corresponding to characteristics of a plurality of library recorded sounds, wherein each of the sets of values in the library comprises fingerprint and landmark pairs, wherein the landmark indicates a distinctive and reproducible location for determining the fingerprint for each of the library recorded sounds;

identifying, via a processor, one or more landmarks in the library corresponding to fingerprints in the library that match any of the fingerprints of the index set of values; and

determining a library recorded sound matching the unidentified recorded sound based on an amount of the one or more landmarks in the library recorded sound having a matching time difference between landmarks of matching fingerprints of the index set of values.

2. The method according to claim 1, further including returning information relating to the library recorded sound to a client device.

3. The method according to claim 2, wherein the information is returned over a first delivery channel, the first delivery channel including an interface selected from the group consisting of a real-time reporting interface and an offline reporting interface.

4. The method according to claim 3, wherein the real-time reporting interface is an interactive voice response interface.

5. The method according to claim 3, wherein the information is provided to the client device as a voice report.

6. The method according to claim 3, wherein the real-time reporting interface is a WAP browser interface.

7. The method according to claim 3, wherein the offline reporting interface is an internet browser interface.

8. The method according to claim 1, wherein the unidentified recorded sound is provided to a client device over a transmission medium.

9. The method according to claim 8, wherein the transmission medium includes acoustic waves.

10. The method according to claim 8, wherein the transmission medium includes radio waves.

11. The method according to claim 9, wherein the transmission medium includes digital audio streams.

12. The method according to claim 8, wherein the transmission medium includes PCM streams.

13. The method according to claim 8, wherein the transmission medium includes internet streaming broadcasts.

14. The method according to claim 8, wherein the transmission medium includes a digital audio stream, and wherein the digital audio stream is compressed.

15. The method according to claim 14, wherein the compressed digital audio stream is a Dolby Digital or MP3 audio stream.

16. The method according to claim 1, wherein the sound stream is received over a delivery channel selected from the group consisting of POTS lines, wireless cellular, wireless PCM, GSM, internet, radio, satellite, and a network.

17. The method according to claim 16, wherein the network includes a local area network.

18. The method according to claim 16, wherein the network includes an Ethernet network.

19. The method according to claim 16, wherein the network includes one or more private networks.

20. The method according to claim 16, wherein the network includes a cable network.

21. The method according to claim 16, wherein the network is configured to operate according to a short-range wireless protocol.

22. The method according to claim 21, wherein short-range wireless protocol includes the Bluetooth wireless standard.

23. The method according to claim 1, wherein receiving the sound stream comprises receiving the sound stream from a capture device.

24. The method according to claim 23, wherein the capture device includes a telephone.

25. The method according to claim 23, wherein the capture device includes a mobile telephone.

26. The method according to claim 23, wherein the capture device includes a tape recorder.

27. The method according to claim 23, wherein the capture device includes a digital voice recorder.

28. The method according to claim 23, wherein the capture device includes an answering machine.

29. The method according to claim 23, wherein the capture device includes a radio receiver.

30. The method according to claim 23, wherein the capture device includes a walkie-talkie.

31. The method according to claim 23, wherein the capture device includes an internet streaming socket.

32. The method according to claim 23, wherein the capture device includes a voice-over-IP transceivers.

33. The method according to claim 1, further comprising determining a score associated with the temporal correspondence.

34. A method for detecting use of copyrighted audio media, the method comprising:

receiving a signal including a captured sample of an audio signal;

deriving from the signal a characteristic of the captured sample, wherein the characteristic comprises a fingerprint and a landmark indicating a distinctive and reproducible location for determining the fingerprint for the captured sample;

comparing, via a processor, the characteristic of the captured sample to a characteristic associated with a stored identity record of copyrighted audio media included in a database, wherein the characteristic associated with the stored identity record of copyrighted audio media comprises a fingerprint and a landmark indicating a distinctive and reproducible location for determining the fingerprint for the copyrighted audio media; and

determining a probability of a match between the audio signal and a stored identity record based on an amount of characteristics of the captured sample having a matching time difference between characteristics associated with the stored identity record of the copyrighted audio media, wherein the captured sample of the audio signal is captured at a location remote from the database.