Developing Speech Processing Pipelines for Police Accountability
This work addresses the challenge of processing vast amounts of body camera footage for police accountability, offering practical applications but is incremental as it adapts existing models to a specific domain.
The researchers tackled the problem of automatically reviewing police body-worn camera footage by developing a speech processing pipeline using large pre-trained models, achieving a word error rate (WER) of 12-13% for officer speech after fine-tuning, though community member speech had a much higher WER of 43.55-49.07%.
Police body-worn cameras have the potential to improve accountability and transparency in policing. Yet in practice, they result in millions of hours of footage that is never reviewed. We investigate the potential of large pre-trained speech models for facilitating reviews, focusing on ASR and officer speech detection in footage from traffic stops. Our proposed pipeline includes training data alignment and filtering, fine-tuning with resource constraints, and combining officer speech detection with ASR for a fully automated approach. We find that (1) fine-tuning strongly improves ASR performance on officer speech (WER=12-13%), (2) ASR on officer speech is much more accurate than on community member speech (WER=43.55-49.07%), (3) domain-specific tasks like officer speech detection and diarization remain challenging. Our work offers practical applications for reviewing body camera footage and general guidance for adapting pre-trained speech models to noisy multi-speaker domains.