Methods and apparatus to determine an audience composition based on voice recognition
Methods, apparatus, systems and articles of manufacture are disclosed. An example apparatus includes a controller to cause a people meter to emit a prompt for input of audience identification information at a first time and determine a first audience count based on the input, an audio detector to determine a second audience count based on signatures generated from audio data captured in the media environment, and a comparator to cause the people meter to not emit the prompt for at least a first time period after the first time when the first audience count is equal to the second audience count.
1. A system comprising:
interface circuitry to obtain audio data;
a processor; and
a memory storing instructions that, when executed by the processor, cause the system to perform operations comprising:
generating a target signature from the audio data, the target signature associated with a first time interval;
comparing the target signature to a plurality of reference signatures in a library of reference signatures, the plurality of reference signatures associated with one or more identified audience members;
in response to a determination that the target signature is not associated with a match in the library of reference signatures, causing a meter to emit a prompt for input of audience identification information associated with the first time interval;
tagging the target signature generated from the audio data with metadata, wherein tagging the target signature comprises:
combining audience metadata comprising the audience identification information with audio metadata comprising one or more characteristics of the audio data from which the target signature was generated to generate combined metadata for the target signature; and
tagging the target signature with the combined metadata.
2. The system of claim 1 , wherein the target signature is one of a plurality of target signatures associated with the first time interval, and wherein the operations further comprise:
determining a first people count associated with the first time interval based on comparison of the target signatures to the library of reference signatures; and
determining whether to cause the meter to emit the prompt for input of audience identification information based on the first people and a second people count associated with a second time interval prior to the first time interval.
3. The system of claim 2 , wherein the operations further comprise:
causing the meter to emit the prompt for input of audience identification information in response to the first people count not matching the second people count; and
causing the meter to not emit the prompt for input of audience identification information in response to the first people count matching the second people count.
4. The system of claim 3 , wherein the operations further comprise: notifying the meter to reset a timer for scheduling generation of prompts.
5. The system of claim 2 , wherein the operations further comprise: determining the first people count based on a number of matches of the target signatures to different reference signatures associated with different ones of the identified audience members.
6. The system of claim 1 , wherein the operations further comprise: initiating signature generation and comparison in response to a media device being turned on.
7. The system of claim 1 , wherein the operations further comprise: performing signature generation and comparison in response to detection of a signal associated with control of a media device.
8. The system of claim 1 , wherein the operations further comprise:
storing the target signature tagged with the combined metadata in a database.
9. The system of claim 1 , wherein the audio metadata comprises metadata indicative of a device that captured the audio data.
10. A non-transitory computer readable storage medium comprising computer readable instructions that, when executed, cause a processor to perform operations comprising:
generating a target signature from audio data, the target signature associated with a first time interval;
comparing the target signature to a plurality of reference signatures in a library of reference signatures, the plurality of reference signatures associated with one or more identified audience members;
in response to a determination that the target signature is not associated with a match in the library of reference signatures, causing a meter to emit a prompt for input of audience identification information associated with the first time interval;
tagging the target signature generated from the audio data with metadata, wherein tagging the target signature comprises:
combining audience metadata comprising the audience identification information with audio metadata comprising one or more characteristics of the audio data from which the target signature was generated to generate combined metadata for the target signature; and
tagging the target signature with the combined metadata.
11. The non-transitory computer readable storage medium of claim 10 , wherein the target signature is one of a plurality of target signatures associated with the first time interval, and wherein the operations further comprise:
determining a first people count associated with the first time interval based on comparison of the target signatures to the library of reference signatures; and
determining whether to cause the meter to emit the prompt for input of audience identification information based on the first people and a second people count associated with a second time interval prior to the first time interval.
12. The non-transitory computer readable storage medium of claim 11 , wherein the operations further comprise:
causing the meter to emit the prompt for input of audience identification information in response to the first people count not matching the second people count; and
causing the meter to not emit the prompt for input of audience identification information in response to the first people count matching the second people count.
13. The non-transitory computer readable storage medium of claim 12 , wherein to the operations further comprise: notifying the meter to reset a timer for scheduling generation of prompts.
14. The non-transitory computer readable storage medium of claim 11 , wherein the operations further comprise: determining the first people count based on a number of matches of the target signatures to different reference signatures associated with different ones of the identified audience members.
15. The non-transitory computer readable storage medium of claim 10 , wherein the operations further comprise: initiating signature generation and comparison in response to a media device being turned on.
16. The non-transitory computer readable storage medium of claim 10 , wherein the operations further comprise: performing signature generation and comparison in response to detection of a signal associated with control of a media device.
17. A method comprising:
generating a target signature from audio data, the target signature associated with a first time interval;
comparing, by executing a first instruction with a processor, the target signature to a plurality of reference signatures in a library of reference signatures, the plurality of reference signatures associated with one or more identified audience members;
in response to a determination that the target signature is not associated with a match in the library of reference signatures, triggering, by executing a second instruction with the processor, a meter to emit a prompt for input of audience identification information associated with the first time interval;
assigning an audience member identifier to the audience identification information associated with the first time interval; and
tagging the target signature generated from the audio data with metadata, wherein tagging the target signature comprises:
combining audience metadata comprising the audience member identifier with audio metadata comprising one or more characteristics of the audio data from which the target signature was generated to generate combined metadata for the target signature; and
tagging the target signature with the combined metadata.
18. The method of claim 17 , wherein the target signature is one of a plurality of target signatures associated with the first time interval, and wherein the method further comprises:
determining a first people count associated with the first time interval based on comparison of the target signatures to the library of reference signatures; and
determining whether to trigger the meter to emit the prompt for input of audience identification information based on the first people and a second people count associated with a second time interval prior to the first time interval.
19. The method of claim 18 , further comprising:
triggering the meter to emit the prompt for input of audience identification information in response to the first people count not matching the second people count; and
causing the meter to not emit the prompt for input of audience identification information in response to the first people count matching the second people count.
20. The method of claim 19 , wherein the causing of the meter to not emit the prompt comprises: notifying the meter to reset a timer for scheduling generation of prompts.