Methods and apparatus to improve detection of audio signatures
Methods, apparatus, systems and articles of manufacture are disclosed to improve detection of audio signatures. An example apparatus includes a TDOA determiner to determine a first time difference of arrival for a first audio sensor of a meter and a second audio sensor of the meter, and a second time difference of arrival for the first audio sensor and a third audio sensor of the meter, a TDOA matcher to determine a match by comparing the first time difference of arrival to a first virtual source time difference of arrival and a second virtual source time difference of arrival, responsive to determining that the first time difference of arrival matches the first virtual source time difference of arrival, identify a first virtual source location as the location of a media presentation device, and remove an audio recording of the second audio sensor to reduce a computational burden on the processor.
1. An apparatus comprising:
a TDOA determiner to determine a first time difference of arrival for a first audio sensor of a meter and a second audio sensor of the meter based on a first audio recording from the first audio sensor and a second audio recording from the second audio sensor, and a second time difference of arrival for the first audio sensor and a third audio sensor of the meter based on the first audio recording and a third audio recording from the third audio sensor; and
a TDOA matcher to:
determine a match by comparing the first time difference of arrival to i) a first virtual source time difference of arrival and ii) a second virtual source time difference of arrival;
in response to determining that the first time difference of arrival matches the first virtual source time difference of arrival, identify a first virtual source location as the location of a media presentation device presenting media; and
remove the second audio recording to reduce a computational burden on the processor.
2. The apparatus of claim 1 , wherein the meter includes the first audio sensor positioned at a first position on the meter, the second audio sensor positioned at a second position on the meter, the third audio sensor positioned at a third position on the meter, and a fourth audio sensor positioned at a fourth position on the meter.
3. The apparatus of claim 2 , wherein determining the first virtual source location and a second virtual source location is based on the first position, the second position, the third position, and the fourth position.
4. The apparatus of claim 1 , further including a virtual source determiner to:
determine the first virtual source location for a first virtual audio source radially positioned about the meter, and the second virtual source location for a second virtual audio source radially positioned around the meter, the first virtual source location different than the second virtual source location; and
determine the first virtual source time difference of arrival for a first pair of audio sensors of the meter based on the first virtual source location, and the second virtual source time difference of arrival for a second pair of audio sensors of the meter based on the second virtual source location.
5. The apparatus of claim 4 , wherein the first pair of audio sensors includes the first audio sensor and the second audio sensor, and the second pair of audio sensors includes the first audio sensor and the third audio sensor.
6. The apparatus of claim 5 , wherein the virtual source determiner to:
calculate a first time for a first virtual signal to reach the first audio sensor based on a distance of the first virtual source from the first audio sensor and the speed of sound;
calculate a second time for the first virtual signal to reach the second audio sensor based on a distance of the first virtual source from the second audio sensor and the speed of sound; and
determine the first virtual source time difference of arrival based on a difference between the first time and the second time.
7. The apparatus of claim 5 , wherein the virtual source determiner to:
calculate a third time for a second virtual signal to reach the first audio sensor based on a distance of the second virtual source from the first audio sensor and the speed of sound;
calculate a fourth time for the second virtual signal to reach the third audio sensor based on a distance of the second virtual source from the third audio sensor and the speed of sound; and
determine the second virtual source time difference of arrival based on a difference between the third time and the fourth time.
8. The apparatus of claim 1 , further including an audio transformer to:
process the first audio recording using a short-time Fourier transform to obtain a first audio transform with first time-frequency bins;
process the second audio recording using the short-time Fourier transform to obtain a second audio transform with second time-frequency bins; and
process the third audio recording using the short-time Fourier transform to obtain a third audio transform with third time-frequency bins.
9. The apparatus of claim 8 , wherein the TDOA determiner to:
calculate a first inter-channel time difference between the first transform and the second transform, the first inter-channel time difference representative of the first time difference of arrival; and
calculate a second inter-channel time difference between the first transform and the third transform, the second inter-channel time difference representative of the second time difference of arrival.
10. A method comprising:
determining, by executing an instruction with a processor, a first time difference of arrival for a first audio sensor of a meter and a second audio sensor of the meter based on a first audio recording from the first audio sensor and a second audio recording from the second audio sensor, and a second time difference of arrival for the first audio sensor and a third audio sensor of the meter based on the first audio recording and a third audio recording from the third audio sensor;
determining, by executing an instruction with the processor, a match by comparing the first time difference of arrival to i) a first virtual source time difference of arrival and ii) a second virtual source time difference of arrival;
in response to determining that the first time difference of arrival matches the first virtual source time difference of arrival, identifying, by executing an instruction with the processor, a first virtual source location as the location of a media presentation device presenting media; and
removing, by executing an instruction with the processor, the second audio recording to reduce a computational burden on the processor.
11. The method of claim 10 , wherein the meter includes the first audio sensor positioned at a first position on the meter, the second audio sensor positioned at a second position on the meter, the third audio sensor positioned at a third position on the meter, and a fourth audio sensor positioned at a fourth position on the meter, the determining of the first virtual source location and a second virtual source location is based on the first position, the second position, the third position, and the fourth position.
12. The method of claim 10 , further including determining the first virtual source location for a first virtual audio source radially positioned about the meter, and the second virtual source location for a second virtual audio source radially positioned around the meter, the first virtual source location different than the second virtual source location; and
determining the first virtual source time difference of arrival for a first pair of audio sensors of the meter based on the first virtual source location, and the second virtual source time difference of arrival for a second pair of audio sensors of the meter based on the second virtual source location.
13. The method of claim 10 , wherein determining the first virtual source time difference of arrival based on the first virtual source location includes:
calculating a first time for a first virtual signal to reach the first audio sensor based on a distance of the first virtual source from the first audio sensor and the speed of sound;
calculating a second time for the first virtual signal to reach the second audio sensor based on a distance of the first virtual source from the second audio sensor and the speed of sound; and
determining the first virtual source time difference of arrival based on a difference between the first time and the second time.
14. The method of claim 10 , wherein determining the second virtual source time difference of arrival based on the second virtual source location includes:
calculating a third time for a second virtual signal to reach the first audio sensor based on a distance of the second virtual source from the first audio sensor and the speed of sound;
calculating a fourth time for the second virtual signal to reach the third audio sensor based on a distance of the second virtual source from the third audio sensor and the speed of sound; and
determining the second virtual source time difference of arrival based on a difference between the third time and the fourth time.
15. The method of claim 10 , further including:
processing the first audio recording using a short-time Fourier transform to obtain a first audio transform with first time-frequency bins;
processing the second audio recording using the short-time Fourier transform to obtain a second audio transform with second time-frequency bins; and
processing the third audio recording using the short-time Fourier transform to obtain a third audio transform with third time-frequency bins.
16. The method of claim 15 , further including:
calculating a first inter-channel time difference between the first transform and the second transform, the first inter-channel time difference representative of the first time difference of arrival; and
calculating a second inter-channel time difference between the first transform and the third transform, the second inter-channel time difference representative of the second time difference of arrival.
17. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:
determine a first time difference of arrival for a first audio sensor of a meter and a second audio sensor of the meter based on a first audio recording from the first audio sensor and a second audio recording from the second audio sensor, and a second time difference of arrival for the first audio sensor and a third audio sensor of the meter based on the first audio recording and a third audio recording from the third audio sensor;
determine a match by comparing the first time difference of arrival to i) a first virtual source time difference of arrival and ii) a second virtual source time difference of arrival;
in response to determining that the first time difference of arrival matches the first virtual source time difference of arrival, identify a first virtual source location as the location of a media presentation device presenting media; and
remove the second audio recording to reduce a computational burden on the processor.
18. The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the machine to:
determine the first virtual source location for a first virtual audio source radially positioned about the meter, and the second virtual source location for a second virtual audio source radially positioned around the meter, the first virtual source location different than the second virtual source location; and
determine the first virtual source time difference of arrival for a first pair of audio sensors of the meter based on the first virtual source location, and the second virtual source time difference of arrival for a second pair of audio sensors of the meter based on the second virtual source location, the first pair of audio sensors includes the first audio sensor and the second audio sensor, and the second pair of audio sensors includes the first audio sensor and the third audio sensor.
19. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the machine to:
calculate a first time for a first virtual signal to reach the first audio sensor based on a distance of the first virtual source from the first audio sensor and the speed of sound;
calculate a second time for the first virtual signal to reach the second audio sensor based on a distance of the first virtual source from the second audio sensor and the speed of sound;
determine the first virtual source time difference of arrival based on a difference between the first time and the second time;
calculate a third time for a second virtual signal to reach the first audio sensor based on a distance of the second virtual source from the first audio sensor and the speed of sound;
calculate a fourth time for the second virtual signal to reach the third audio sensor based on a distance of the second virtual source from the third audio sensor and the speed of sound; and
determine the second virtual source time difference of arrival based on a difference between the third time and the fourth time.
20. The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the machine to:
process the first audio recording using a short-time Fourier transform to obtain a first audio transform with first time-frequency bins;
process the second audio recording using the short-time Fourier transform to obtain a second audio transform with second time-frequency bins;
process the third audio recording using the short-time Fourier transform to obtain a third audio transform with third time-frequency bins;
calculate a first inter-channel time difference between the first transform and the second transform, the first inter-channel time difference representative of the first time difference of arrival; and
calculate a second inter-channel time difference between the first transform and the third transform, the second inter-channel time difference representative of the second time difference of arrival.