Distributed audience measurement systems and methods
View Patent ↗Systems and methods are disclosed for customizing, distributing and processing audio fingerprint data. One or more items of audio content are processed to generate pre-recorded audio fingerprints. After identifying one or more specific devices in accordance to panelist and/or household data from a central site, an activation message is communicated to the identified devices, together with the pre-recorded audio fingerprint in accordance with a predetermined schedule. After receiving the activation message, the portable device records the audio content, forms an audio fingerprint, and performs local matching to determine if a match exists. The matching result is then communicated back to the central site for further processing and analysis.
1. A method to process distributed audio fingerprint data for an audience measurement system, comprising:
processing an audio signal to generate an audio fingerprint in a central site;
processing scheduling information data relating to the audio signal;
determining an audience member to poll based on the audio signal;
transmitting an activation signal and the generated audio fingerprint to a targeted portable device associated with the determined audience member based on the scheduling information, the activation signal to cause the portable device associated with the determined audience member to begin capturing audio; and
receiving matching information from the portable device relating to the generated audio fingerprint.
2. The method according to claim 1 , wherein the audio signal comprises one of a commercial, an announcement, or a song.
3. The method according to claim 1 , further comprising processing panelist data to correlate a panelist characteristic to the scheduling information, wherein the panelist data comprises at least one of panelist demographics, media exposure information, retail store visits, purchases, internet usage information, or consumer beliefs and opinions relating to consumer products and services.
4. The method according to claim 3 , wherein the panelist data comprises household-level data.
5. The method according to claim 1 , wherein the activation signal comprises executable code to be executed on the portable device to form a second audio fingerprint on the portable device.
6. The method according to claim 5 , wherein the matching information comprises data relating to a comparison performed at the portable device based on comparing the audio fingerprint and the second audio fingerprint formed at the portable device.
7. The method of claim 1 , wherein transmitting the activation signal comprises transmitting a data message via an internet to the portable device.
8. The method of claim 1 , wherein the scheduling information comprises a known time at which media associated with the audio signal is to be communicated.
9. The method of claim 1 , wherein the matching information includes a result message comprising at least one of identification information of the portable device, identification information of the fingerprint, or a result of a comparison between the generated audio fingerprint and a second audio fingerprint recorded by the portable device in response to the activation signal.
10. An audience measurement system to process audio fingerprint data, comprising:
a processing circuit at a central site, the processing circuit to process an audio signal to generate an audio fingerprint and to determine an audience member to poll based on the audio signal;
a storage device at the central site, the storage device to store scheduling information; and
a communication device at the central site, the communication device to transmit an activation signal and the generated audio fingerprint to a targeted portable device associated with the audience member based on the scheduling information, and the communication device to receive matching information from the portable device relating to the generated audio fingerprint, the activation signal to cause the portable device associated with the audience member to begin capturing audio.
11. The system according to claim 10 , wherein the audio signal comprises at least one of a commercial, an announcement, or a song.
12. The system according to claim 10 , wherein the processing circuit is to process the scheduling information based on the audio signal and panelist data to correlate a panelist characteristic to the scheduling information, the panelist data comprising at least one of panelist demographics, media exposure information, retail store visits, purchases, internet usage information, or consumer beliefs and opinions relating to consumer products and services.
13. The system according to claim 12 , wherein the panelist data comprises household-level data.
14. The system according to claim 10 , wherein the activation signal comprises executable code to be executed on the portable device to cause the portable device to generate a second audio fingerprint.
15. The system according to claim 14 , wherein the matching information is based on a comparison performed by the portable device and comparing the audio fingerprint and the second audio fingerprint generated at the portable device.
16. A portable device to perform audience measurement of audio-based media, comprising:
a communication interface to receive a message targeted to the portable device from a central site, the message comprising an activation signal and a first audio fingerprint;
a recording device to sample ambient sound in a vicinity of the portable device, the recording device to begin sampling in response to executing an instruction corresponding to the activation signal; and
a processing circuit to process the sampled ambient sound to generate a second audio fingerprint and to compare the second audio fingerprint to the first audio fingerprint to determine a match result;
the communication interface to communicate the match result to the central site.
17. The portable device of claim 16 , wherein the processing circuit is to generate the second audio fingerprint by digitally converting an audio signal into a series of features.
18. The portable device of claim 17 , wherein the processing circuit is to generate the second audio fingerprint by modeling the series of features to define a representation of the generated second audio fingerprint.
19. The portable device of claim 18 , wherein the representation comprises at least one of a trace of vectors, a codebook, a sequence of indices to Hidden Markov Model sound classes, or a sequence of error correcting words.
20. The portable device of claim 16 , further comprising a storage device to store panelist data comprising at least one of panelist demographics, media exposure information, retail store visits, purchases, internet usage information, or consumer beliefs and opinions relating to consumer products and services.
21. The portable device of claim 20 , wherein the communication interface is to receive the activation signal after sending at least a portion of the panelist data.
22. The portable device of claim 16 , wherein the activation signal comprises executable code to activate the recording device for a period of time.
23. The portable device of claim 22 , wherein the period of time corresponds to a period of time in which an audio signal is played.
24. The portable device of claim 16 , wherein the communication interface is to receive the message via an internet.