Methods and apparatus to perform audio sensor selection in an audience measurement device
Methods, apparatus, systems and articles of manufacture to perform audio sensor selection in an audience metering device are disclosed. An example method includes identifying a plurality of audio sensor configurations supported by the audience metering device. A first quality metric of a first media identifier determined from first audio received via a first one of the audio sensor configurations is computed. A second quality metric of a second media identifier determined from second audio received via a second one of the audio sensor configurations is computed. One of the first one of the audio sensor configurations or the second one of the audio sensor configurations is selected based on a comparison of the first quality metric and the second quality metric. Media monitoring is performed at the audience metering device using the selected one of the audio sensor configurations.
1. A method to perform audio sensor selection in an audience metering device, the method comprising:
identifying a plurality of audio sensor configurations supported by the audience metering device, the plurality of audio sensor configurations for configuring a plurality of audio sensors of the audience metering device, the plurality of audio sensor configurations identifying different combinations of the plurality of audio sensors to be activated;
computing, by executing an instruction with a processor, a first quality metric of a first media identifier determined from first audio received via the plurality of audio sensors in accordance with a first one of the audio sensor configurations;
computing, by executing an instruction with the processor, a second quality metric of a second media identifier determined from second audio received via the plurality of audio sensors in accordance with a second one of the audio sensor configurations;
selecting one of the first one of the audio sensor configurations or the second one of the audio sensor configurations based on a comparison of the first quality metric and the second quality metric; and
performing media monitoring at the audience metering device using the selected one of the audio sensor configurations.
2. The method of claim 1 , further including storing the selected one of the first audio sensor configurations in a configuration memory.
3. The method of claim 1 , wherein the selecting of the one of the first one of the audio sensor configurations or the second one of the audio sensor configurations is performed when at least one of the first quality metric or the second quality metric satisfies a quality metric change threshold.
4. The method of claim 1 , wherein the first one of the audio sensor configurations corresponds to at least one forward facing microphone.
5. The method of claim 1 , wherein the first one of the audio sensor configurations corresponds to at least one rear facing microphone.
6. The method of claim 1 , wherein the first one of the audio sensor configurations corresponds to a combination of at least one forward facing microphone and at least one rear facing microphone.
7. The method of claim 1 , wherein the identification of the plurality of audio sensor configurations is performed periodically.
8. The method of claim 1 , wherein the first quality metric is a signal to noise ratio.
9. An apparatus to perform audio sensor selection, the apparatus comprising:
at least two audio sensors to receive audio at an audience metering device;
a selection tester to:
identify a plurality of audio sensor configurations supported by the audience metering device, the plurality of audio sensor configurations for configuring the at least two audio sensors of the audience metering device, the plurality of audio sensor configurations identifying different combinations of the at least two audio sensors to be activated;
obtain a first quality metric of a first media identifier corresponding to audio received via the at least two audio sensors in accordance with a first one of the audio sensor configurations;
obtain a second quality metric of a second media identifier corresponding to the audio received via the at least two audio sensors in accordance with a second one of the audio sensor configurations; and
select one of the first one of the audio sensor configurations or the second one of the audio sensor configurations based on a comparison of the first quality metric and the second quality metric; and
a media identifier to identify audio received at the audience metering device using the selected one of the audio sensor configurations.
10. The apparatus of claim 9 , further including a configuration memory to store the selected one of the audio sensor configurations.
11. The apparatus of claim 9 , wherein the selection tester is to select the one of the first one of the audio sensor configurations or the second one of the audio sensor configurations when at least one of the first quality metric or the second quality metric satisfies a quality metric change threshold.
12. The apparatus of claim 9 , further including an audio sensor selector to combine audio received via the selected one of the first one of the audio sensor configurations or the second one of the audio sensor configurations to form combined audio, the media identifier to perform the identification based on the combined audio.
13. The apparatus of claim 9 , wherein the first one of the audio sensor configurations corresponds to at least one forward facing microphone.
14. The apparatus of claim 9 , wherein the first one of the audio sensor configurations corresponds to at least one rear facing microphone.
15. The apparatus of claim 9 , wherein the first one of the audio sensor configurations corresponds to a combination of at least one forward facing microphone and at least one rear facing microphone.
16. The apparatus of claim 9 , wherein the identification of the first one of the audio sensor configurations and the second one of the audio sensor configurations is performed periodically.
17. The apparatus of claim 9 , wherein the first quality metric is a signal to noise ratio.
18. A non-transitory readable medium comprising instructions which, when executed, cause an audience metering device to at least:
identify a plurality of audio sensor configurations supported by the audience metering device, the plurality of audio sensor configurations for configuring a plurality of audio sensors of the audience metering device, the plurality of audio sensor configurations identifying different combinations of the plurality of audio sensors to be activated;
compute a first quality metric of a first media identifier determined from first audio received via the plurality of audio sensor in accordance with a first one of the audio sensor configurations;
compute a second quality metric of a second media identifier determined from second audio received via a second one of the audio sensor configurations;
select one of the first one of the audio sensor configurations or the second one of the audio sensor configurations based on a comparison of the first quality metric and the second quality metric; and
perform media monitoring at the audience metering device using the selected one of the audio sensor configurations.
19. The non-transitory readable medium of claim 18 , wherein the instructions, when executed, further cause the audience metering device to store the selected one of the first audio sensor configurations in a configuration memory.
20. The non-transitory readable medium of claim 18 , wherein the selection of the one of the first one of the audio sensor configurations or the second one of the audio sensor configurations is performed when at least one of the first quality metric or the second quality metric satisfies a quality metric change threshold.