Engagement measurement of media consumers based on the acoustic environment

Abstract

Methods, apparatus, systems and articles of manufacture to measure engagement of media consumers based on acoustic environment are disclosed. Example apparatus disclosed herein are to identify media device audio data and ambient environment audio data from sensed audio data collected from an environment, and determine classification data for the media device audio data and the ambient environment audio data. Disclosed example apparatus are also to process the classification data with a machine learning model to calculate an engagement metric. Disclosed example apparatus are further to determine whether at least one individual is engaged with media in the environment based on the engagement metric.

1 . An apparatus comprising:
 at least one memory;   instructions; and   processor circuitry to execute the instructions to:
 identify media device audio data and ambient environment audio data from sensed audio data collected from an environment; 
 determine classification data for the media device audio data and the ambient environment audio data; 
 process the classification data with a machine learning model to calculate an engagement metric; and 
 determine whether at least one individual is engaged with media in the environment based on the engagement metric. 
   
     
     
         2 . The apparatus of  claim 1 , wherein the processor circuitry is to obtain the sensed audio data from a first meter and a second meter, the first meter and the second meter to monitor a media device in the environment. 
     
     
         3 . The apparatus of  claim 2 , wherein the processor circuitry is to obtain meter data from the first meter and the second meter, the meter data including at least one of motion data or audio volume, and the processor circuitry is to determine the engagement metric based on the meter data. 
     
     
         4 . The apparatus of  claim 1 , wherein the machine learning model is a first machine learning model, and to determine the classification data, the processor circuitry is to:
 process the ambient environment audio data with a second machine learning model to determine one or more sound classifications;   process the ambient environment audio data with a third machine learning model to determine key word classifications; and   process the media device audio data with the third machine learning model to determine contextual classifications.   
     
     
         5 . The apparatus of  claim 4 , wherein the sound classifications are based on a library of sounds corresponding to at least one of laughing, eating, drinking, snoring, vacuum cleaning, or walking. 
     
     
         6 . The apparatus of  claim 4 , wherein the processor circuitry is to execute the second machine learning model and the third machine learning model concurrently. 
     
     
         7 . The apparatus of  claim 1 , wherein the processor circuitry is to apply weights to the classification data. 
     
     
         8 . The apparatus of  claim 7 , wherein the processor circuitry is to process the weighted classification data with the machine learning model to calculate the engagement metric. 
     
     
         9 . The apparatus of  claim 1 , wherein the processor circuitry is to train the machine learning model based on a combination of (i) second sensed audio data collected by a media device meter and (ii) panelist survey data that is time aligned with the second sensed audio data. 
     
     
         10 . The apparatus of  claim 1 , wherein the processor circuitry is to determine whether the at least one individual is engaged with the media in the environment based on whether the engagement metric satisfies a threshold. 
     
     
         11 . At least one non-transitory computer readable medium comprising instructions which, when executed, cause one or more processors to at least:
 identify media device audio data and ambient environment audio data from sensed audio data collected from an environment;   determine classification data for the media device audio data and the ambient environment audio data;   process the classification data with a machine learning model to calculate an engagement metric; and   determine whether at least one individual is engaged with media in the environment based on the engagement metric.   
     
     
         12 . The at least one non-transitory computer readable medium of  claim 11 , wherein the instructions are to cause the one or more processors to obtain the sensed audio data from a first meter and a second meter, the first meter and the second meter to monitor a media device in the environment. 
     
     
         13 . (canceled) 
     
     
         14 . The at least one non-transitory computer readable medium of  claim 11 , wherein the machine learning model is a first machine learning model, and the instructions are to cause the one or more processors to determine the classification data by:
 processing the ambient environment audio data with a second machine learning model to determine one or more sound classifications;   processing the ambient environment audio data with a third machine learning model to determine key word classifications; and   processing the media device audio data with the third machine learning model to determine contextual classifications.   
     
     
         15 . (canceled) 
     
     
         16 . (canceled) 
     
     
         17 . The at least one non-transitory computer readable medium of  claim 11 , wherein the instructions are to cause the one or more processors to apply weights to the classification data. 
     
     
         18 . The at least one non-transitory computer readable medium of  claim 17 , wherein the instructions are to cause the one or more processors to process the weighted classification data with the machine learning model to calculate the engagement metric. 
     
     
         19 . The at least one non-transitory computer readable medium of  claim 11 , wherein the instructions are to cause the one or more processors to train the machine learning model based on a combination of (i) second sensed audio data collected by a media device meter and (ii) panelist survey data that is time aligned with the second sensed audio data. 
     
     
         20 . The at least one non-transitory computer readable medium of  claim 1 , wherein the instructions are to cause the one or more processors to determine whether the at least one individual is engaged with the media in the environment based on whether the engagement metric satisfies a threshold. 
     
     
         21 . A method comprising:
 identifying media device audio data and ambient environment audio data from sensed audio data collected from an environment;   determining, by executing an instruction with at least one processor, classification data for the media device audio data and the ambient environment audio data;   processing the classification data with a machine learning model to calculate an engagement metric; and   determining, by executing an instruction with the at least one processor, whether at least one individual is engaged with media in the environment based on the engagement metric.   
     
     
         22 . (canceled) 
     
     
         23 . (canceled) 
     
     
         24 . The method of  claim 21 , wherein the machine learning model is a first machine learning model, and the determining of the classification data includes:
 processing the ambient environment audio data with a second machine learning model to determine one or more sound classifications;   processing the ambient environment audio data with a third machine learning model to determine key word classifications; and   processing the media device audio data with the third machine learning model to determine contextual classifications.   
     
     
         25 .- 29 . (canceled) 
     
     
         30 . The method of  claim 21 , wherein the determining of whether the at least one individual is engaged with the media in the environment is based on whether the engagement metric satisfies a threshold. 
     
     
         31 .- 51 . (canceled)