Audio De-identification: A New Entity Recognition Task

TL;DR

This paper introduces the task of audio de-identification, combining speech recognition and entity recognition to detect and redact personal information in medical conversation recordings, and provides a new benchmark for evaluation.

Contribution

It defines the novel task of audio de-ID, proposes a pipeline integrating ASR and NER with alignment, and introduces a new evaluation metric and benchmark dataset.

Findings

Pipeline achieves promising detection accuracy.

New metric effectively evaluates audio de-ID performance.

Benchmark dataset enables standardized evaluation.

Abstract

Named Entity Recognition (NER) has been mostly studied in the context of written text. Specifically, NER is an important step in de-identification (de-ID) of medical records, many of which are recorded conversations between a patient and a doctor. In such recordings, audio spans with personal information should be redacted, similar to the redaction of sensitive character spans in de-ID for written text. The application of NER in the context of audio de-identification has yet to be fully investigated. To this end, we define the task of audio de-ID, in which audio spans with entity mentions should be detected. We then present our pipeline for this task, which involves Automatic Speech Recognition (ASR), NER on the transcript text, and text-to-audio alignment. Finally, we introduce a novel metric for audio de-ID and a new evaluation benchmark consisting of a large labeled segment of the Switchboard and Fisher audio datasets and detail our pipeline's results on it.