Audio De-identification: A New Entity Recognition Task

A. Hassidim, I. Cohn, I. Laish, G. Beryozkin, G. Li, I. Shafran, I. Szpektor, T. Hartman, Yossi Matias

Research output: Working paper / PreprintPreprint

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.
Original languageEnglish
Number of pages8
Volume7037
DOIs
StatePublished - 5 May 2019

Publication series

NamearXiv preprint arXiv:1903.,

Fingerprint

Dive into the research topics of 'Audio De-identification: A New Entity Recognition Task'. Together they form a unique fingerprint.

Cite this