Methods and apparatus to determine a state of a media presentation device

• US 9,924,224 B2
• Filed: 10/29/2015
• Issued: 03/20/2018
• Est. Priority Date: 04/03/2015
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Srinivasan, Venugopal, Lee, Morris, Davis, Jeremey M.
• Primary Examiner(s): Tran, Hai V
• Application Number:
  US14/926,885
• Publication Number:
  US 20160295279A1
• Time in Patent Office: 873 Days
• CPC Class Codes: G10L 19/018 Audio watermarking, i.e. embedding inaudible data in the audio signal
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04H 2201/50 characterised by the use of watermarks
• CPC Class Codes: H04H 2201/90 characterised by the use of signatures
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/44213 Monitoring of end-user related data arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages

Abstract

Methods and apparatus to determine a state of a media presentation device are disclosed. Example disclosed methods include generating a first set of weighted coefficients based on first audio received by first and second microphones at a first time. Example disclosed methods include generating a second set of weighted coefficients based on second audio received by the first and second microphones at a second time after the first time. Example disclosed methods include comparing the first set of coefficients and the second set of coefficients to generate a similarity value. Example disclosed methods include, when the similarity value satisfies a threshold, determining that the media presentation device is in a first state. Example disclosed methods include, when the similarity value does not satisfy the threshold, determining that the media presentation device is in a second state.

Claims

1. A method of determining a state of a media presentation device, the method comprising:

generating, using an echo cancellation algorithm, a first set of weighted coefficients based on first audio received by first and second microphones at a first time;

generating, using the echo cancellation algorithm, a second set of weighted coefficients based on second audio received by the first and second microphones at a second time after the first time;

comparing the first set of weighted coefficients and the second set of weighted coefficients by calculating a dot product between the first set of weighted coefficients and the second set of weighted coefficients to generate a similarity value;

when the similarity value satisfies a first threshold, determining that the media presentation device is in a first state;

when the similarity value does not satisfy the first threshold, determining that the media presentation device is in a second state; and

controlling a metering device based on whether the media presentation device is in the first state or the second state.

2. The method of claim 1, further including:

when the media presentation device is in the first state, extracting a watermark from the second audio.

3. The method of claim 1, wherein the generating of the first and second sets of weighted coefficients includes applying the echo cancellation algorithm using a finite impulse response filter to generate the first set of weighted coefficients and to generate the second set of weighted coefficients.

4. The method of claim 1, wherein the first state includes an on state, and wherein the second state includes an off state.

5. The method of claim 1, further including:

applying a third set of weighted coefficients to one or more samples of third audio received by the first microphone to provide a filter output;

comparing the filter output to a sample of the third audio received by the second microphone to generate an error signal; and

when the error signal exceeds a second threshold, adjusting the first set of weighted coefficients based on the error signal.

6. The method of claim 5, wherein the error signal, X_e(n), includes X_e(n)=X_d (n)−

Y_O(n), wherein X_d(n) represents an audio sample and Y₀(n) represents a summed filter output of multiple audio samples and n is an iteration index, and wherein the first set of weighted coefficients is adjusted based on the error signal by W_m(n+1)=W_m(n)+μ

X_eX_m(n), wherein W_m(n+1) and W_m are weight coefficients, X_m(n) is a weighted audio sample, and μ

is a learning factor.

7. The method of claim 5, wherein the comparing of the filter output to the sample of the third audio received by the second microphone to generate the error signal further includes subtracting the filter output from the sample of the third audio received by the second microphone to generate the error signal.

8. A tangible computer readable storage medium comprising instructions that, when executed, cause a machine to at least:

generate, using an echo cancellation algorithm, a first set of weighted coefficients based on first audio received by first and second microphones at a first time;

generate, using the echo cancellation algorithm, a second set of weighted coefficients based on second audio received by the first and second microphones at a second time after the first time;

compare the first set of weighted coefficients and the second set of weighted coefficients by calculating a dot product between the first set of weighted coefficients and the second set of weighted coefficients to generate a similarity value;

when the similarity value satisfies a first threshold, determine that a media presentation device is in a first state;

when the similarity value does not satisfy the first threshold, determine that the media presentation device is in a second state; and

control a metering device based on whether the media presentation device is in the first state or the second state.

9. The tangible computer readable storage medium of claim 8, further including instructions that, when executed, cause the machine to, when the media presentation device is in the first state, extract a watermark from the second audio.

10. The tangible computer readable storage medium of claim 8, further including instructions that, when executed, cause the machine to generate the first and second sets of weighted coefficients by applying the echo cancellation algorithm using a finite impulse response filter to generate the first set of weighted coefficients and to generate the second set of weighted coefficients.

11. The tangible computer readable storage medium of claim 8, wherein the first state includes an on state, and wherein the second state includes an off state.

12. The tangible computer readable storage medium of claim 8, further including instructions that, when executed, cause the machine to:

apply a third set of weighted coefficients to one or more samples of a third audio received by the first microphone to provide a filter output;

compare the filter output to a sample of the third audio received by the second microphone to generate an error signal; and

when the error signal exceeds a second threshold, adjust the first set of weighted coefficients based on the error signal.

13. The tangible computer readable storage medium of claim 12, wherein the error signal, X_e(n), includes X_e(n)=X_d (n)−

Y_O(n), wherein X_d(n) represents an audio sample and Y₀(n) represents a summed filter output of multiple audio samples and n is an iteration index, and wherein the first set of weighted coefficients is adjusted based on the error signal by W_m (n+1)=W_m(n)+μ

X_eX_m(n), wherein W_m(n+1) and W_m are weight coefficients, X_m(n) is a weighted audio sample, and μ

is a learning factor.

14. The tangible computer readable storage medium of claim 12, wherein the instructions, when executed, cause the machine to compare the filter output to the sample of the third audio received by the second microphone to generate the error signal by subtracting the filter output from the sample of the third audio received by the second microphone to generate the error signal.

15. A metering device comprising a processor to implement a source detector including an adaptive audio filter, an audio comparator, and a state determiner,

the adaptive audio filter to at least:

generate, using an echo cancellation algorithm, a first set of weighted coefficients based on first audio received by first and second microphones at a first time; and

generate, using the echo cancellation algorithm, a second set of weighted coefficients based on second audio received by the first and second microphones at a second time after the first time;

the audio comparator to at least;

compare the first set of weighted coefficients and the second set of weighted coefficients by calculating a dot product between the first set of weighted coefficients and the second set of weighted coefficients to generate a similarity value; and

the state determiner to at least;

when the similarity value satisfies a first threshold, determine that the media presentation device is in a first state;

when the similarity value does not satisfy the first threshold, determine that the media presentation device is in a second state; and

control the metering device based on whether the media presentation device is in the first state or the second state.

16. The metering device of claim 15, wherein the metering device is to generate the first and second sets of weighted coefficients by applying the echo cancellation algorithm using a finite impulse response filter to generate the first set of weighted coefficients and to generate the second set of weighted coefficients.

17. The metering device of claim 15, wherein the first state includes an on state, and wherein the second state includes an off state.

18. The metering device of claim 15, wherein the metering device is further to:

apply a third set of weighted coefficients to one or more samples of a third audio received by the first microphone to provide a filter output;

compare the filter output to a sample of the third audio received by the second microphone to generate an error signal; and

when the error signal exceeds a second threshold, adjust the first set of weighted coefficients based on the error signal.

19. The metering device of claim 18, wherein the error signal, X_e(n), includes X_e(n)=X_d(n)−

Y_O(n), wherein X_d(n) represents an audio sample and Y₀(n) represents a summed filter output of multiple audio samples and n is an iteration index, and wherein the first set of weighted coefficients is adjusted based on the error signal by W_m (n+1)=W_m(n)+μ

X_eX_m(n), wherein W_m(n+1) and W_m are weight coefficients, X_m(n) is a weighted audio sample, and μ

is a learning factor.

20. The metering device of claim 18, wherein the metering device is to compare the filter output to the sample of the third audio received by the second microphone to generate the error signal by subtracting the filter output from the sample of the third audio received by the second microphone to generate the error signal.