Neural Network Audio Location Detection for Audience Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Personal portable metering devices (PPMs) face challenges in accurately determining media exposure in households due to issues like spillover, hijacking, varying volume levels, and environmental factors, leading to inaccurate credit of media content exposure.
Innovation Solution
A location detection system using neural network models with a reference and portable unit to determine audience member locations by correlating audio samples from stationary and non-stationary units, employing time-domain and frequency-domain analyses to calculate correlation coefficients and determine distances from media devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If PPM detects media content using audio signal analysis, then media exposure monitoring capability is improved, but measurement precision deteriorates due to spillover and hijacking effects
Solution Approach 1:
The patent segments the audio signal analysis into multiple frequency bands (bass, mid-range, treble) and analyzes correlation coefficients for each band separately. This allows the system to identify which frequency ranges are being affected by spillover or hijacking and make targeted adjustments to the exposure credit calculation, thereby maintaining monitoring capability while improving measurement precision.
Solution Approach 2:
The system dynamically changes the correlation threshold parameter based on the analyzed audio characteristics and environmental conditions. By adjusting the threshold according to the detected spillover or hijacking severity, the system adapts its detection sensitivity to maintain accurate media exposure measurement across varying household conditions.
2Productivity
If PPM credits media exposure based on detected audio signals, then media exposure credit is awarded, but reliability deteriorates due to improper crediting from spillover and hijacking
Solution Approach 1:
The patent implements a feedback mechanism where the correlation analysis results are used to adjust the exposure credit awarding decision. The system continuously monitors the correlation coefficients between reference audio signals and detected signals, and uses this feedback to determine whether to grant, reduce, or deny media exposure credit, thereby ensuring reliable and accurate credit awarding.
Solution Approach 2:
The system performs preliminary analysis of audio signal characteristics before awarding exposure credit. By detecting potential spillover or hijacking conditions in advance through correlation analysis and applying corrective threshold adjustments beforehand, the system prevents improper crediting rather than correcting it after the fact, thus maintaining high reliability in exposure credit awarding.
Data Source
AI summary
A disclosed example method involves determining, using a neural network at a stationary unit, a first distance of a first portable audio detector from the stationary unit, the first portable audio detector associated with a first panelist, the stationary unit located in proximity to the media presentation device. The example method also involves determining, using the neural network, a second distance of a second portable audio detector from the stationary unit, the second portable audio detector associated with a second panelist. In response to the first distance being less than a threshold distance, the media is credited as exposed to the first panelist. In response to the second distance being more than the threshold distance, the media is not credited as exposed to the second panelist.