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. An apparatus to measure an audience in a media environment, the apparatus comprising:
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; and
an audio detector to:
count a number of distinct speech patterns detected in audio data captured in the media environment;
determine a second audience count based on the number of distinct speech patterns detected in the audio data captured in the media environment;
generate signatures from the audio data captured in the media environment;
identify one or more audience members based on comparisons of the generated signatures with a library of reference audience signatures; and
count the one or more audience members identified based on the comparisons of the generated signatures with the library of reference audience signatures to determine a number of identified audience members;
wherein the controller is 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; and
cause the people meter to emit the prompt when the number of identified audience members does not correspond to the number of distinct speech patterns.
2. The apparatus of claim 1 , wherein the library of reference audience signatures includes sample signatures generated from speech associated with the one or more of the audience members.
3. The apparatus of claim 1 , wherein the controller is to cause the people meter to emit the prompt when at least one of (i) the first audience count does not equal the second audience count, or (ii) the input audience identification information does not correspond to the one or more audience members identified based on the comparisons of the generated signatures with a library of reference audience signatures.
4. The apparatus of claim 1 , wherein the input is to include unique identifiers assigned to the audience.
5. The apparatus of claim 1 , wherein the controller is to reset a counter, the controller to cause the people meter to emit the prompt when the counter expires.
6. A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to at least:
cause a people meter to emit a prompt for input of audience identification information at a first time;
determine a first audience count based on the input;
count a number of distinct speech patterns detected in audio data captured in a media environment;
determine a second audience count based on the number of distinct speech patterns detected in the audio data captured in a media environment;
generate signatures from the audio data captured in the media environment;
identify one or more audience members based on comparisons of the generated signatures with a library of reference audience signatures;
count the one or more audience members identified based on the comparisons of the generated signatures with the library of reference audience signatures to determine a number of identified audience members of an audience;
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; and
cause the people meter to emit the prompt when the number of identified audience members does not correspond to the number of distinct speech patterns.
7. The non-transitory computer readable medium of claim 6 , wherein the library of reference audience signatures includes sample signatures generated from speech associated with the one or more of the audience members.
8. The non-transitory computer readable medium of claim 6 , wherein the instructions, when executed, cause the one or more processors to cause the people meter to emit the prompt when at least one of (i) the first audience count does not equal the second audience count, or (ii) the input audience identification information does not correspond to the one or more audience members identified based on the comparisons of the generated signatures with a library of reference audience signatures.
9. The non-transitory computer readable medium of claim 6 , wherein the input is to include unique identifiers assigned to the audience.
10. The non-transitory computer readable medium of claim 6 , wherein the instructions, when executed, cause the one or more processors to send a reset notification to a counter, the people meter to emit the prompt when the counter expires.
11. A method to measure an audience in a media environment, the method comprising:
causing a people meter to emit a prompt for input of audience identification information at a first time;
determining a first audience count based on the input;
counting a number of distinct speech patterns detected in audio data captured in the media environment;
determining a second audience count based on the number of distinct speech patterns detected in the audio data captured in the media environment;
generating signatures from the audio data captured in the media environment;
identifying one or more audience members based on comparisons of the generated signatures with a library of reference audience signatures;
counting the one or more audience members identified based on the comparisons of the generated signatures with the library of reference audience signatures to determine a number of identified audience members;
causing 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; and
causing the people meter to emit the prompt when the number of identified audience members does not correspond to the number of distinct speech patterns.
12. The method of claim 11 , wherein the library of reference audience signatures includes sample signatures generated from speech associated with the one or more of the audience members.
13. The method of claim 11 , further including causing the people meter to emit the prompt when at least one of (i) the first audience count does not equal the second audience count, or (ii) the input audience identification information does not correspond to the one or more audience members identified based on the comparisons of the generated signatures with a library of reference audience signatures.
14. The method of claim 11 , further including sending a reset notification to a counter, the people meter to emit the prompt when the counter expires.