# Prosody-Driven Privacy-Preserving Dementia Detection

arXiv: https://arxiv.org/abs/2407.03470 · HTML: https://mlsanity.com/paper/2407.03470/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 17 of 17)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [Introducing the VoicePrivacy Initiative](https://mlsanity.com/paper/2005.01387/) (2020)
- [Evaluating Voice Conversion-based Privacy Protection against Informed Attackers](https://mlsanity.com/paper/1911.03934/) (2019)
- [Privacy-preserving Voice Analysis via Disentangled Representations](https://mlsanity.com/paper/2007.15064/) (2020)
- [Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation](https://mlsanity.com/paper/2012.04454/) (2020)
- [Speaker Anonymization with Phonetic Intermediate Representations](https://mlsanity.com/paper/2207.04834/) (2022)
- [Differentially Private Adversarial Auto-Encoder to Protect Gender in Voice Biometrics](https://mlsanity.com/paper/2307.02135/) (2023)
- [A bridge between features and evidence for binary attribute-driven perfect privacy](https://mlsanity.com/paper/2110.05840/) (2021)
- [Privacy-oriented manipulation of speaker representations](https://mlsanity.com/paper/2310.06652/) (2023)
- [Privacy-preserving Representation Learning for Speech Understanding](https://mlsanity.com/paper/2310.17194/) (2023)

## Built on by (most cited first, 3 of 3)

- [DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech](https://mlsanity.com/paper/2410.04188/) (2024)
- [WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper](https://mlsanity.com/paper/2505.21551/) (2025)
- [Temporal-Aware Iterative Speech Model for Dementia Detection](https://mlsanity.com/paper/2510.00030/) (2025)

## Abstract (arXiv)

Speaker embeddings extracted from voice recordings have been proven valuable for dementia detection. However, by their nature, these embeddings contain identifiable information which raises privacy concerns. In this work, we aim to anonymize embeddings while preserving the diagnostic utility for dementia detection. Previous studies rely on adversarial learning and models trained on the target attribute and struggle in limited-resource settings. We propose a novel approach that leverages domain knowledge to disentangle prosody features relevant to dementia from speaker embeddings without relying on a dementia classifier. Our experiments show the effectiveness of our approach in preserving speaker privacy (speaker recognition F1-score .01%) while maintaining high dementia detection score F1-score of 74% on the ADReSS dataset. Our results are also on par with a more constrained classifier-dependent system on ADReSSo (.01% and .66%), and have no impact on synthesized speech naturalness.