Anonymising Elderly And Pathological Speech: Voice Conversion Using DDSP And Query-by-example

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.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyghosh2024anonymising

Related papers

• Self-supervised Speech Representations Preserve Speech Characteristics While Anonymizing Voices (2022)0.00
• Improving Voice Quality In Speech Anonymization With Just Perception-informed Losses (2024)0.00
• Privacy-utility Balanced Voice De-identification Using Adversarial Examples (2022)0.00
• IQDUBBING: Prosody Modeling Based On Discrete Self-supervised Speech Representation For Expressive Voice Conversion (2022)0.00
• Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding (2024)7.16
• Duta-vc: A Duration-aware Typical-to-atypical Voice Conversion Approach With Diffusion Probabilistic Model (2023)0.00
• Learning Explicit Prosody Models And Deep Speaker Embeddings For Atypical Voice Conversion (2020)7.16
• Preserving Spoken Content In Voice Anonymisation With Character-level Vocoder Conditioning (2024)3.58