Methods and apparatus for increasing the robustness of media signatures
View Patent ↗Methods and apparatus for determining increasing robustness of media signatures are disclosed. An example apparatus includes a characteristic analyzer to analyze a media signal based on a signature algorithm to identify a comparison between a first characteristic and a second characteristic that does not satisfy a threshold; and a characteristic enhancer to adjust at least one of the first characteristic or the second characteristic to satisfy the threshold.
1. An apparatus to enhance characteristics of a signature, the apparatus comprising:
a characteristic analyzer to analyze an audio signal based on a signature algorithm to identify a first computed difference between (A) a first characteristic of the audio signal and (B) a second characteristic of the audio signal that does not satisfy a threshold;
a characteristic enhancer to, in response to identification of the first difference that does not satisfy the threshold, adjust at least one of the first characteristic or the second characteristic of the audio signal to create an enhanced audio signal for which a subsequent computed difference between the first characteristic of the enhanced audio signal and the second characteristic of the enhanced audio signal satisfies the threshold; and
a transmitter to transmit the enhanced audio signal to a media output device.
2. The apparatus of claim 1 , wherein the characteristic enhancer is to adjust at least one of the first characteristic or the second characteristic by boosting the first characteristic of the audio signal or attenuating the second characteristic of the audio signal.
3. The apparatus of claim 1 , wherein the characteristic enhancer is to adjust at least one of the first characteristic or the second characteristic of the audio signal prior to the enhanced audio signal being output by the media output device.
4. The apparatus of claim 1 , wherein:
the first characteristic of the audio signal is at least one of a first energy of a first frequency band of the audio signal, a first energy of the audio signal at a first time, a first discrete cosine transform coefficient, or a first peak frequency at a first time; and
the second characteristic of the audio signal is at least one of a second energy of a second frequency band of the audio signal, a second energy of the audio signal at a second time, a second discrete cosine transform coefficient, or a second peak frequency at a second time.
5. The apparatus of claim 1 , further including a signature settings determiner to select the signature algorithm from a plurality of signature algorithms, the signature algorithm to generate a signature bit based on the difference of the first and second characteristics of the audio signal.
6. The apparatus of claim 1 , wherein the characteristic enhancer is to adjust at least one of the first characteristic of the audio signal or the second characteristic of the audio signal to increase the difference between the first characteristic of the enhanced audio signal and second characteristics of the enhanced audio signal.
7. A method to enhance characteristics of a signature, the method comprising:
analyzing, by executing an instruction with a processor, an input audio signal based on a signature algorithm to compute a first difference of a first characteristic of the input audio signal and a second characteristic of the input audio signal;
determining whether the first difference satisfies a threshold;
when the first difference does not satisfy the threshold, adjusting, by executing an instruction with the processor, at least one of the first characteristic or the second characteristic of the input audio signal to generate an enhanced audio signal for which a subsequent computed difference between the first characteristic of the enhanced audio signal and the second characteristic of the enhanced audio signal satisfies the threshold; and
transmitting the enhanced audio signal to a media output device.
8. The method of claim 7 , wherein the adjusting of at least one of the first characteristic or the second characteristic of the input audio signal includes at least one of boosting the first characteristic of the input audio signal or attenuating the second characteristic of the input audio signal.
9. The method of claim 7 , wherein the adjusting of at least one of the first characteristic of the input audio signal or the second characteristic of the input audio signal occurs prior to the enhanced audio signal being output by the media output device.
10. The method of claim 7 , wherein:
the first characteristic of the input audio is at least one of a first energy of a first frequency band of the input audio signal, a first energy of the input audio signal at a first time, a first discrete cosine transform coefficient, or a first peak frequency at a first time; and
the second characteristic of the input audio is at least one of a second energy of a second frequency band of the input audio signal, a second energy of the input audio signal at a second time, a second discrete cosine transform coefficient, or a second peak frequency at a second time.
11. The method of claim 7 , further including selecting the signature algorithm from a plurality of signature algorithms, the signature algorithm to generate a signature bit based on the difference of the first and second characteristics of the input audio signal.
12. The method of claim 7 , wherein:
the first and subsequent differences are mathematical differences; and
the adjusting of at least one of the first characteristic or the second characteristic of the input audio signal increases the difference between the first characteristic and the second characteristic of the enhanced audio signal.
13. A tangible computer readable medium comprising instructions which, when executed, cause a machine to at least:
analyze an input audio signal based on a signature algorithm to perform a first difference of a first characteristic of the input audio signal and a second characteristic of the input audio signal;
determine that the first difference does not satisfy a threshold;
adjust at least one of the first characteristic or the second characteristic of the input audio signal to generate an enhanced audio signal for which a subsequent computed difference between the first characteristic of the enhanced audio signal and the second characteristic of the enhanced audio signal satisfies the threshold; and
output the enhanced audio signal to a media output device.
14. The computer readable medium of claim 13 , wherein the instructions, when executed, cause the machine to adjust at least one of the first characteristic or the second characteristic of the input audio signal by boosting the first characteristic or attenuating the second characteristic of the input audio signal.
15. The computer readable medium of claim 13 , wherein the instructions, when executed, cause the machine to adjust at least one of the first characteristic or the second characteristic of the input audio signal prior to the enhanced audio signal being output by the media output device.
16. The computer readable medium of claim 13 , wherein:
the first characteristic is at least one of a first energy of a first frequency band of the input audio signal, a first energy of the input audio signal at a first time, a first discrete cosine transform coefficient, or a first peak frequency at a first time; and
the second characteristic is at least one of a second energy of a second frequency band of the input audio signal, a second energy of the input audio signal at a second time, a second discrete cosine transform coefficient, or a second peak frequency at a second time.
17. The computer readable medium of claim 13 , wherein instructions cause the machine to limit the adjustment of the at least one of the first characteristic or the second characteristic of the input audio signal to avoid at least one of audible distortion, violation of media requirements, or a negative effect on a subsequent comparison.
18. The computer readable medium of claim 13 , wherein the instructions cause the machine to select the signature algorithm from a plurality of signature algorithms, the signature algorithm to generate a signature bit based on the difference of the first and second characteristics of the input audio signal.
19. The method of claim 7 , wherein the first characteristic of the input audio signal and the second characteristic of the input audio signal correspond to the same characteristic type, the characteristic type being a frequency-based energy, a time-based energy, or a time-based peak frequency.