Methods and apparatus to perform audio watermarking and watermark detection and extraction

• US 10,467,286 B2
• Filed: 09/07/2017
• Issued: 11/05/2019
• Est. Priority Date: 10/24/2008
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Srinivasan, Venugopal, Topchy, Alexander
• Primary Examiner(s): Han, Qi
• Application Number:
  US15/698,373
• Publication Number:
  US 20170371960A1
• Time in Patent Office: 789 Days
• Field of Search: 704500, 704501, 704502, 704200
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G11B 20/10 Digital recording or reproducing
• 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 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00

Abstract

Methods and apparatus to audio watermarking and watermark detection and extracted are described herein. Disclosed example methods to decode a watermark from an audio signal include averaging a second sequence of audio samples stored in a buffer with a first sequence of audio samples stored in the buffer to determine an averaged sequence of audio samples, the second sequence of audio samples being related to the first sequence of audio samples based on a repetition period associated with watermark data of the watermark to be decoded. Disclosed example methods also include determining whether to enable a stacker. Disclosed example methods further include, in response to the stacker being enabled, decoding the watermark from the averaged sequence of audio samples, and in response to the stacker being disabled, decoding the watermark from the first sequence of audio samples.

Claims

1. An apparatus to decode a watermark from an audio signal, the apparatus comprising:

a stacker to average amplitudes of a second sequence of audio samples of the audio signal stored in a buffer with amplitudes of a first sequence of audio samples of the audio signal stored in the buffer to determine an averaged sequence of audio samples, the second sequence of audio samples related to the first sequence of audio samples based on a repetition period associated with watermark data of the watermark to be decoded;

a stacker controller to control whether to enable the stacker; and

a decoder to;

decode the watermark from the averaged sequence of audio samples when the stacker is enabled by the stacker controller; and

decode the watermark from the first sequence of audio samples when the stacker is not enabled by the stacker controller.

2. The apparatus of claim 1, wherein to control whether the stacker is enabled, the stacker controller is to:

process the audio signal to determine whether the audio signal is distorted;

enable the stacker when the audio signal is distorted; and

disable the stacker when the audio signal is not distorted.

3. The apparatus of claim 1, wherein the stacker controller is to process a control signal from a switch to control whether the stacker is enabled.

4. The apparatus of claim 1, wherein the stacker controller is to sum one or more error indications generated by the decoder when decoding watermarks to determine whether to enable the stacker.

5. The apparatus of claim 4, wherein the stacker controller is to:

enable the stacker when the sum of error indications meets a threshold; and

disable the stacker when the sum of error indications does not meet the threshold.

6. The apparatus of claim 1, wherein the decoded watermark is further analyzed by a validator to determine whether the decoded watermark matches a previously decoded watermark.

7. The apparatus of claim 6, wherein the validator is to:

determine the decoded watermark is validated when the decoded watermark matches the previously decoded watermark; and

determine the decoded watermark is in error when the decoded watermark does not match the previously decoded watermark.

8. A method to decode a watermark from an audio signal, the method comprising:

averaging amplitudes of a second sequence of audio samples stored in a buffer with amplitudes of a first sequence of audio samples stored in the buffer to determine an averaged sequence of audio samples when a stacker process is enabled, the second sequence of audio samples related to the first sequence of audio samples based on a repetition period associated with watermark data of the watermark to be decoded;

determining whether to enable the stacker process;

in response to the stacker process being enabled, decoding the watermark from the averaged sequence of audio samples; and

in response to the stacker process being disabled, decoding the watermark from the first sequence of audio samples.

9. The method of claim 8, wherein the determining of whether to enable the stacker process includes:

processing the audio signal to determine whether the audio signal is distorted;

enabling the stacker process when the audio signal is distorted; and

disabling the stacker process when the audio signal is not distorted.

10. The method of claim 8, wherein the determining of whether to enable the stacker process includes processing a control signal from a switch.

11. The method of claim 8, wherein the determining of whether to enable the stacker process includes summing one or more error indications generated when decoding watermarks.

12. The method of claim 11, wherein the determining of whether to enable the stacker process further includes:

enabling the stacker process in response to the sum of error indications meeting a threshold; and

disabling the stacker process in response to the sum of error indications not meeting the threshold.

13. The method of claim 8, further including validating the decoded watermark by determining whether the decoded watermark matches a previously decoded watermark.

14. The method of claim 13, wherein the validating of the decoded watermark further includes:

validating the decoded watermark in response to the decoded watermark matching the previously decoded watermark; and

invalidating the decoded watermark in response to the decoded watermark not matching the previously decoded watermark.

15. A computer readable storage disc or storage device comprising instructions that, when executed, cause a processor to at least:

average amplitudes of a second sequence of audio samples stored in a buffer with amplitudes of a first sequence of audio samples stored in the buffer to determine an averaged sequence of audio samples when a stacker process is enabled, the second sequence of audio samples related to the first sequence of audio samples based on a repetition period associated with watermark data of the watermark to be decoded;

determine whether to enable the stacker process;

decode the watermark from the averaged sequence of audio samples when the stacker process is enabled; and

decode the watermark from the first sequence of audio samples when the stacker process is not enabled.

16. The computer readable storage disc or storage device as defined in claim 15, wherein the instructions, when executed, cause the processor to determine whether to enable the stacker process by:

processing an audio signal to determine whether the audio signal is distorted;

enable the stacker process when the audio signal is distorted; and

disable the stacker process when the audio signal is not distorted.

17. The computer readable storage disc or storage device as defined in claim 15, wherein the instructions, when executed, cause the processor to determine whether to enable the stacker process by summing one or more error indications generated when decoding watermarks.

18. The computer readable storage disc or storage device as defined in claim 17, wherein the instructions, when executed, further cause the processor to determine whether to enable the stacker process by:

enabling the stacker process when the sum of error indications meets a threshold; and

disabling the stacker process when the sum of error indications does not meet the threshold.

19. The computer readable storage disc or storage device as defined in claim 15, wherein the instructions, when executed, further cause the processor to validate the decoded watermark by determining whether the decoded watermark matches a previously decoded watermark.

20. The computer readable storage disc or storage device as defined in claim 19, wherein the instructions, when executed, further cause the processor to:

validate the decoded watermark when the decoded watermark matches the previously decoded watermark; and

determine the decoded watermark is in error when the decoded watermark does not match the previously decoded watermark.