# Developing Speech Processing Pipelines for Police Accountability

arXiv: https://arxiv.org/abs/2306.06086 · HTML: https://mlsanity.com/paper/2306.06086/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 9 Jun 2023.

## Builds on (most cited first, 8 of 8)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications](https://mlsanity.com/paper/2110.05781/) (2021)

## Built on by (most cited first, 2 of 2)

- [Quantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths](https://mlsanity.com/paper/2606.06812/) (2026)
- [Pretrained ASR Pseudo-labeling for Noisy Police Audio](https://mlsanity.com/paper/2609.30469/) (2026)

## Abstract (arXiv)

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.