Automatic Conflict Detection in Police Body-Worn Audio
This addresses the need for better conflict detection in police-public interactions, which is incremental as it builds on existing body-worn technology but introduces tailored methods for noisy contexts.
The researchers tackled the problem of automatically detecting conflict in police body-worn audio by developing a pipeline that uses adaptive noise removal, non-speech filtering, and new measures based on phrase repetition and intensity, achieving effectiveness on data from the Los Angeles Police Department.
Automatic conflict detection has grown in relevance with the advent of body-worn technology, but existing metrics such as turn-taking and overlap are poor indicators of conflict in police-public interactions. Moreover, standard techniques to compute them fall short when applied to such diversified and noisy contexts. We develop a pipeline catered to this task combining adaptive noise removal, non-speech filtering and new measures of conflict based on the repetition and intensity of phrases in speech. We demonstrate the effectiveness of our approach on body-worn audio data collected by the Los Angeles Police Department.