METHODS AND APPARATUS TO GENERATE AND USE CONTENT-AWARE WATERMARKS

• US 20090256972A1
• Filed: 04/11/2008
• Published: 10/15/2009
• Est. Priority Date: 04/11/2008
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Ramaswamy, Arun, Luff, Robert A.
• Granted Patent: US 8,805,689 B2
• Time in Patent Office: Days
• US Class Current: 348/738
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06T 1/0021 Image watermarking
• CPC Class Codes: H04H 20/31 using in-band signals, e.g. subsonic or cue signal
• CPC Class Codes: H04H 2201/50 characterised by the use of watermarks
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/48 for recognising items expressed in broadcast information
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00

Abstract

Methods and apparatus to generate and use content-aware watermarks are disclosed herein. In a disclosed example method, media composition data is received and at least one word present in an audio track of the media composition data is selected. The word is then located in a watermark.

Claims

1. A method, comprising:

receiving media composition data;

selecting at least one word present in an audio track of the media composition data; and

locating the word in a watermark.

2. A method as defined in claim 1, further comprising associating the watermark with the media composition data.

3. A method as defined in claim 1, wherein the media composition data includes at least one of audio data or video data.

4. A method as defined in claim 1, wherein the at least one word is indicative of a product name or a product type mentioned in the audio track.

5. A method as defined in claim 1, wherein selecting the at least one word comprises:

retrieving closed caption text from the media composition data; and

selecting the at least one word from the closed caption text.

6. A method as defined in claim 1, wherein selecting the at least one word comprises selecting the at least one word based on a weighted value associated with the at least one word.

7. A method as defined in claim 1, wherein selecting the at least one word comprises:

retrieving at least a portion of the audio track from the media composition data;

performing a speech-to-text conversion to generate a textual representation of the at least the portion of the audio track; and

selecting the at least one word from the textual representation.

8. A method as defined in claim 1, wherein selecting the at least one word comprises selecting a word descriptive of content in the media composition data.

9. A method as defined in claim 1, wherein selecting the at least one word comprises selecting a word to be used for searching for the media composition data in a plurality of servers coupled via an internetwork.

10. A method as defined in claim 1, wherein locating the word in the watermark comprises at least one of truncating the word to a predetermined character length or omitting predetermined characters from the word to form a partial word and locating the partial word in the watermark.

11. An apparatus, comprising:

a data interface to receive media composition data;

a word selector to select at least one word present in an audio track of the media composition data; and

a watermark encoder to locate the word in a watermark.

12. An apparatus as defined in claim 11, further comprising a watermark embedder to associate the watermark with the media composition data.

13. An apparatus as defined in claim 11, wherein the media composition data includes at least one of audio data or video data.

14. An apparatus as defined in claim 11, wherein the at least one word is indicative of a product name or a product type mentioned in the media composition data.

15. An apparatus as defined in claim 11, wherein the word selector is to select the at least one word by:

retrieving closed caption text from the media composition data; and

selecting the at least one word from the closed caption text.

16. An apparatus as defined in claim 11, wherein the word selector is to select the at least one word based on a weighted value associated with the at least one word.

17. An apparatus as defined in claim 11, wherein the word selector is to select the at least one word by:

retrieving at least a portion of the audio track from the media composition data;

performing a speech-to-text conversion to generate a textual representation of the at least the portion of the audio track; and

selecting the at least one word from the textual representation.

18. An apparatus as defined in claim 11, wherein the word selector is to select the at least one word by selecting a word descriptive of content in the media composition data.

19. An apparatus as defined in claim 11, wherein the word selector is to select the at least one word by selecting a word to be used for searching for the media composition data in a plurality of servers coupled via an internetwork.

20. A machine accessible medium having instructions stored thereon that, when executed, cause a machine to:

receive media composition data;

select at least one word present in an audio track of the media composition data; and

locate the word in a watermark.

21. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to associate the watermark with the media composition data.

22. A machine accessible medium as defined in claim 20, wherein the media composition data includes at least one of audio data or video data.

23. A machine accessible medium as defined in claim 20, wherein the at least one word is indicative of a product name or a product type mentioned in the media composition data.

24. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to select the at least one word by:

retrieving closed caption text from the media composition data; and

selecting the at least one word from the closed caption text.

25. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to select the at least one word by selecting the at least one word based on a weighted value associated with the at least one word.

26. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to select the at least one word by:

retrieving at least a portion of the audio track from the media composition data;

performing a speech-to-text conversion to generate a textual representation of the at least the portion of the audio track; and

selecting the at least one word from the textual representation.

27. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to select the at least one word by selecting a word descriptive of content in the media composition data.

28. A machine accessible medium as defined in claim 20 having instructions stored thereon that, when executed, cause the machine to select the at least one word by selecting a word to be used for searching for the media composition data in a plurality of servers coupled via an internetwork.

29-51. -51. (canceled)