Less Stress, More Privacy: Stress Detection on Anonymized Speech of Air Traffic Controllers

TL;DR

This paper demonstrates that effective stress detection in air traffic controllers' anonymized speech is achievable with deep learning, maintaining high accuracy while respecting privacy regulations like GDPR.

Contribution

It evaluates various architectures for stress detection on anonymized ATC speech, achieving high accuracy and showing privacy preservation does not hinder model performance.

Findings

93.6% accuracy on anonymized SUSAS dataset

80.1% accuracy on anonymized ATC simulation dataset

Privacy-preserving stress detection is feasible with deep learning

Abstract

Air traffic control (ATC) demands multi-tasking under time pressure with high consequences of an error. This can induce stress. Detecting stress is a key point in maintaining the high safety standards of ATC. However, processing ATC voice data entails privacy restrictions, e.g. the General Data Protection Regulation (GDPR) law. Anonymizing the ATC voice data is one way to comply with these restrictions. In this paper, different architectures for stress detection for anonymized ATCO speech are evaluated. Our best networks reach a stress detection accuracy of 93.6% on an anonymized version of the Speech Under Simulated and Actual Stress (SUSAS) dataset and an accuracy of 80.1% on our anonymized ATC simulation dataset. This shows that privacy does not have to be an impediment in building well-performing deep-learning-based models.