eess.ASNov 8, 2026

Task-adaptive anonymisation enables privacy-preserving sharing of clinical speech data

Authors: Ziyun Cui, Haoyu Niu, Wen Wu, Hao Sun, Sihan Zhang, Chang Lei, Yun Zhang, Chunyun Sun, 

Organizations: Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. · Shanghai Artificial Intelligence Laboratory, Shanghai 200032, China. · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China. · Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Beijing 100084, China. · 

Abstract

Clinical speech is increasingly used for disease screening and clinical assessment, but directly distributing speech recordings poses privacy risks because they contain both speaker-identifying voiceprints and sensitive spoken content. Existing speech anonymisation approaches are primarily developed for general speech applications or task-specific clinical speech and overlook that different clinical tasks rely on distinct speech characteristics, necessitating task-adaptive anonymisation strategies to protect patient privacy while preserving clinical utility. Here we introduce CASA, a clinically adaptive speech anonymisation agent that transforms anonymisation from a fixed processing procedure into a task-guided optimisation process, dynamically tailoring voiceprint and content anonymisation to task-specific privacy and clinical utility requirements. Through recursive self-improvement (RSI), CASA iteratively evaluates and refines anonymisation strategies against task-specific privacy and clinical utility requirements, while learning from these outcomes to guide more efficient planning in subsequent clinical tasks. CASA is validated across 14 clinical tasks encompassing five languages, diverse elicitation paradigms, and mental health, cognitive and voice disorders. CASA preserved disease-related classification performance while meeting speaker-anonymisation requirements across all clinical tasks, versus only 8/14 for the strongest fixed method. Assessments of resistance to speaker re-identification by external attackers and identification and redaction of sensitive personal information in clinical speech further demonstrated CASA's dual protection of speaker identity and sensitive spoken content. Clinical expert assessments further supported the preservation of clinically relevant information and the acceptability of anonymised speech for controlled research sharing.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech

    Oct 10, 2026Praphul Singh, Akshat Agarwal, Ratul Ghosh +5Speaker AnonymizationSpeech Editing

  2. VoxAnon: A balanced dataset for a fair evaluation of speech anonymization

    Oct 9, 2026Orane Dufour, Paul Magron, Mickael RouvierPrivacy-Preserving Speech ProcessingSpeaker Anonymization

  3. The Content Leash: Mitigating Degenerate Solutions in Invertible Speaker Anonymization

    Oct 27, 2026Nirjon Mobarak Talukder, Rafid Ahmed, Mohammad Ishrak Abedin +1Speaker AnonymizationPrivacy-Preserving Speech Processing