Methods and apparatus for identifying media content using temporal signal characteristics

1. A method to identify media, comprising:

generating, by executing an instruction with a processor, interval sums based on peaks in a media signal received at a monitored site corresponding to media;

identifying, by executing an instruction with the processor, signal peaks based on the generated interval sums;

generating, by executing an instruction with the processor, a signature of the received media signal based on normalized curve features, wherein the normalized curve features respectively correspond to the identified signal peaks at corresponding temporal locations of the corresponding signal peak; and

determining, by executing an instruction with the processor, whether the media signal corresponds to a reference signal based on a comparison of a reference signature and the signature of the received media signal.

2. The method as defined in claim 1 , further including smoothing the generated interval sums.

3. The method as defined in claim 1 , wherein the determining of whether the media signal corresponds to the reference signal includes performing a correlation of the signature of the media signal and the reference signature.

4. The method as defined in claim 1 , further including generating the normalized curve features by respectively generating peaks having heights, widths, and center locations.

5. The method as defined in claim 4 , wherein the heights of the normalized curve features are equal and the widths of the normalized curve features are equal.

6. The method as defined in claim 4 , wherein the height of the signature of the media signal is substantially zero at temporal locations other than locations corresponding to the normalized curve features.

7. The method as defined in claim 1 , wherein the determining of whether the media signal corresponds to the reference signal includes determining whether an index value is greater than a threshold.

8. The method as defined in claim 1 , wherein the media is associated with at least one of a broadcast program or a local media source.

9. The method as defined in claim 1 , wherein the media includes at least one of audio or video.

10. The method as defined in claim 1 , further including generating the reference signature by:

generating second interval sums based on peaks in the reference signal;

identifying second signal peaks based on the generated second interval sums; and

generating the reference signature based on second normalized curve features, wherein the second normalized curve features respectively correspond to the second signal peaks at corresponding temporal locations of the one of the second signal peaks.

11. A method to monitor exposure to media, comprising:

generating interval sums based on peaks in a media signal received at and collected from an exposure site by executing an instruction with a processor;

identifying signal peaks based on the generated interval sums by executing an instruction with the processor;

generating a signature of the media signal based on normalized curve features by executing an instruction with the processor, the normalized curve features respectively corresponding to the signal peaks at corresponding temporal locations of the corresponding signal peaks; and

identifying the media signal by performing a comparison of the signature of the media signal and a reference signature representative of known media by executing an instruction with the processor.

12. The method as defined in claim 11 , further including smoothing the generated interval sums.

13. The method as defined in claim 11 , further including:

generating second interval sums based on peaks in a known media signal;

identifying second signal peaks based on the generated second interval sums; and

generating the reference signature based on second normalized curve features, wherein the second normalized curve features respectively correspond to the second signal peaks at corresponding temporal locations of the corresponding second signal peaks.

14. The method as defined in claim 11 , further including identifying a second media signal based on a comparison of a signature of the second media signal and a reference signature representative of known media.

15. The method as defined in claim 14 , wherein the identifying of the media signal and the second media signal includes comparing first and second index values with a first threshold.

16. The method as defined in claim 15 , further including identifying a third media signal, wherein exposure to the third media signal occurs between exposure to the first media signal and exposure to the second media signal, and identifying the third media signal includes comparing a third index value with a second threshold lower than the first threshold.

17. An apparatus to identify media, comprising:

a summer to generate interval sums based on peaks in a media signal received at a monitored site;

a peak identifier to identify signal peaks based on the generated interval sums;

a feature generator to generate a signature of the media signal based on normalized curve features, the normalized curve features respectively corresponding to the identified signal peaks at corresponding temporal locations of the corresponding signal peaks; and

an index comparator to determine whether the media signal corresponds to a reference signal based on a comparison of the signature of the media signal and a reference signature corresponding to the reference signal, at least one of the summer, the peak identifier, the feature generator, or the index comparator including hardware.

18. The apparatus as defined in claim 17 , further including a smoother to smooth the interval sums.

19. The apparatus as defined in claim 17 , further including a correlator to perform a correlation of the signature of the media signal and the reference signature, the index comparator to determine whether the media signal corresponds to the reference signal based on the correlation.

20. The apparatus as defined in claim 17 , wherein the feature generator is to generate the normalized curve features by generating peaks having respective heights, respective widths, and respective center locations.

21. The apparatus as defined in claim 20 , wherein the feature generator is to generate the respective peaks to have same heights and to have same widths.

22. The apparatus as defined in claim 20 , wherein the height of the signature of the media signal is substantially zero at temporal locations other than locations corresponding to the normalized curve features.

23. The apparatus as defined in claim 17 , wherein the index comparator is to determine whether the media signal corresponds to the reference signal by determining whether an index value is greater than a threshold.

24. The apparatus as defined in claim 17 , wherein the media is associated with at least one of a broadcast program or a local media source.

25. The apparatus as defined in claim 17 , wherein the summer is to generate second interval sums based on peaks in a known media signal, the peak identifier is to identify second signal peaks based on the generated second interval sums, and the feature generator is to generate the reference signature based on second normalized curve features, the second normalized curve features respectively corresponding to the second signal peaks at respective temporal locations of the second signal peaks.

26. A tangible computer readable storage device comprising instructions which, when executed, cause a machine to at least:

generate interval sums based on peaks in a media signal received at a monitored site;

identify signal peaks based on the generated interval sums;

generate a signature of the media signal based on normalized curve features, the normalized curve features respectively corresponding to respective ones of the identified signal peaks at corresponding temporal locations; and

determine whether the media signal corresponds to a reference signal based on a comparison of a reference signature and the signature of the media signal.

27. The tangible computer readable storage device as defined in claim 26 , wherein the instructions further cause the machine to smooth the generated interval sums.

28. The tangible computer readable storage device as defined in claim 26 , wherein the instructions cause the machine to determine whether the media signal corresponds to the reference signal by performing a correlation of the signature of the media signal and the reference signature.

29. The tangible computer readable storage device as defined in claim 26 , wherein the instructions further cause the machine to generate the normalized curve features by respectively generating peaks having heights, widths, and center locations.

30. The tangible computer readable storage device as defined in claim 29 , wherein the heights of the normalized curve features are equal and the widths of the normalized curve features are equal.

31. The tangible computer readable storage device as defined in claim 29 , wherein the height of the signature of the media signal is substantially zero at temporal locations other than locations corresponding to normalized curve features.

32. The tangible computer readable storage device as defined in claim 26 , wherein the instructions cause the machine to determine whether the media signal corresponds to the reference signal by determining whether an index value is greater than a threshold.

33. The tangible computer readable storage device as defined in claim 26 , wherein the media is associated with at least one of a broadcast program or a local media source.

34. The tangible computer readable storage device as defined in claim 26 , wherein the instructions cause the machine:

generate second interval sums based on peaks in the reference signal;

identify second signal peaks based on the generated second interval sums; and

generate the reference signature based on second normalized curve features, the second normalized curve features respectively corresponding to respective ones of the second signal peaks at corresponding temporal locations.