Generation of a media content database by correlating repeating media content in media streams

• US 20050193016A1
• Filed: 02/17/2005
• Published: 09/01/2005
• Est. Priority Date: 02/17/2004
• Status: Abandoned Application

• Current Assignee: Auditude.com Incorporated
• Original Assignee: Auditude.com Incorporated
• Inventors: Zapf, Vivien, Seet, Nicholas
• Application Number:
  US11/061,770
• Publication Number:
  US 20050193016A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content

Abstract

A media content database is created and maintained by comparing the media items from two related media streams. Segments of media items from the streams are sampled and stored. Samples from one stream are matched against samples from the other stream to identify any repeating content in the streams. A reviewer observes the matched samples representing the repeating content and provides identifying meta-data for that content. The identified media content is then added to the media content database, where it can be used at a later time in an application that requires media content recognition.

Claims

1. A method for creating and maintaining a media content database, the method comprising:

sampling a first media stream to obtain a first set of samples, each sample including characteristic information for a segment of the first media stream;

sampling a second media stream to obtain a second set of samples, each sample including characteristic information for a segment of the second media stream;

matching at least some of the second set of samples against the first set of samples;

receiving identifying information for the matched samples; and

storing the matched samples and their corresponding identifying information in the media content database.

2. The method of claim 1, wherein the first media stream is an earlier portion of a media broadcast and the second media stream is a later portion of the media broadcast.

3. The method of claim 1, wherein the first and second media streams are audio broadcasts.

4. The method of claim 1, wherein at least some of the matched samples are of advertisements.

5. The method of claim 1, further comprising:

combining a group of matched samples into a single unit representing a single media item in the second media stream; and

presenting the group of matched samples together for receiving identifying information therefor.

6. The method of claim 1, further comprising:

inferring a match for an unmatched sample of the second set of samples based on the temporal location of the unmatched sample with respect to other matched samples in the second set.

7. The method of claim 1, wherein receiving identifying information is performed using a web-based user interface.

8. The method of claim 1, wherein the received identifying information for a sample comprises meta-data for a media item associated with the sample.

9. A method for generating entries for a media content database, the method comprising:

receiving a first media stream;

receiving a second media stream;

matching at least some portions of the second media stream to the first media stream to determine repeating content between the streams; and

presenting the repeating content to a reviewer for identification.

10. The method of claim 9, further comprising:

receiving identifying information about the repeating content from a reviewer.

11. The method of claim 10, further comprising:

creating a set of entries for the media content database, each entry including a portion of the repeating content and the identifying information received from the reviewer.

12. The method of claim 9, wherein the first and second media streams comprise a media broadcast, and the repeating content includes advertisements transmitted in the radio broadcast.

13. The method of claim 9, wherein the matching comprises:

dividing each of the first and second media streams into a plurality of segments;

generating fingerprints of the segments of each media stream;

determining whether at least some of the fingerprints of the segments of the first media stream are within a predetermined tolerance of any fingerprints of the segments of the second media stream.

14. The method of claim 9, wherein the repeating content is presented to a reviewer over a web-based interface.

15. A computer program product for creating and maintaining a media content database, the computer program product comprising a computer-readable medium containing computer program code for performing the operations:

sampling a first media stream to obtain a first set of samples, each sample including characteristic information for a segment of the first media stream;

sampling a second media stream to obtain a second set of samples, each sample including characteristic information for a segment of the second media stream;

matching at least some of the second set of samples against the first set of samples;

receiving identifying information for the matched samples; and

storing the matched samples and their corresponding identifying information in the media content database.

16. The computer program product of claim 15, wherein the first media stream is an earlier portion of a media broadcast and the second media stream is a later portion of the media broadcast.

17. The computer program product of claim 15, wherein the first and second media streams are audio broadcasts.

18. The computer program product of claim 15, wherein at least some of the matched samples are of advertisements.

19. The computer program product of claim 15, the computer-readable medium further containing computer program code for performing the operations:

combining a group of matched samples into a single unit representing a single media item in the second media stream; and

presenting the group of matched samples together for receiving identifying information therefor.

20. The computer program product of claim 15, the computer-readable medium further containing computer program code for performing the operations:

inferring a match for an unmatched sample of the second set of samples based on the temporal location of the unmatched sample with respect to other matched samples in the second set.

21. The computer program product of claim 15, wherein receiving identifying information is performed using a web-based user interface.

22. The computer program product of claim 15, wherein the received identifying information for a sample comprises meta-data for a media item associated with the sample.