Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example

TL;DR

This paper introduces DDSP-QbE, a voice conversion method that effectively anonymizes elderly and pathological speech while preserving prosody and domain-specific features, crucial for health monitoring.

Contribution

The paper presents a novel voice conversion approach using differentiable digital signal processing and query-by-example, specifically designed for elderly and pathological speech domains.

Findings

Outperforms state-of-the-art in intelligibility and prosody preservation

Maintains speaker anonymity across diverse datasets and pathologies

Experts validate preservation of clinically relevant speech attributes

Abstract

Speech anonymisation aims to protect speaker identity by changing personal identifiers in speech while retaining linguistic content. Current methods fail to retain prosody and unique speech patterns found in elderly and pathological speech domains, which is essential for remote health monitoring. To address this gap, we propose a voice conversion-based method (DDSP-QbE) using differentiable digital signal processing and query-by-example. The proposed method, trained with novel losses, aids in disentangling linguistic, prosodic, and domain representations, enabling the model to adapt to uncommon speech patterns. Objective and subjective evaluations show that DDSP-QbE significantly outperforms the voice conversion state-of-the-art concerning intelligibility, prosody, and domain preservation across diverse datasets, pathologies, and speakers while maintaining quality and speaker anonymity. Experts validate domain preservation by analysing twelve clinically pertinent domain attributes.