mlsanityData to 7 Oct 2026

ClaritySpeech: Dementia Obfuscation in Speech

arXiv 2507.09282 ↗First posted 12 Jul 2025cs.CL cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Dementia, a neurodegenerative disease, alters speech patterns, creating communication barriers and raising privacy concerns. Current speech technologies, such as automatic speech transcription (ASR), struggle with dementia and atypical speech, further challenging accessibility. This paper presents a novel dementia obfuscation in speech framework, ClaritySpeech, integrating ASR, text obfuscation, and zero-shot text-to-speech (TTS) to correct dementia-affected speech while preserving speaker identity in low-data environments without fine-tuning. Results show a 16% and 10% drop in mean F1 score across various adversarial settings and modalities (audio, text, fusion) for ADReSS and ADReSSo, respectively, maintaining 50% speaker similarity. We also find that our system improves WER (from 0.73 to 0.08 for ADReSS and 0.15 for ADReSSo) and speech quality from 1.65 to ~2.15, enhancing privacy and accessibility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 12 Jul 2025.

Builds on

23 of 35 references.

References · 23

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
  5. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 381
  6. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
  7. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  8. 2024VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wildcited by 118
  9. 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 104
  10. 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
  11. 2023MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectracited by 51
  12. 2023HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesiscited by 35
11 more
  1. 2020Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic reviewcited by 29
  2. 2020Privacy-preserving Voice Analysis via Disentangled Representationscited by 24
  3. 2023FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Modelscited by 23
  4. 2020Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservationcited by 13
  5. 2022Data Augmentation for Dementia Detection in Spoken Languagecited by 7
  6. 2023Accurate synthesis of Dysarthric Speech for ASR data augmentationcited by 7
  7. 2021A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversioncited by 6
  8. 2020Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversioncited by 5
  9. 2023Differentially Private Adversarial Auto-Encoder to Protect Gender in Voice Biometricscited by 3
  10. 2024DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speechcited by 3
  11. 2024Quantifying the effect of speech pathology on automatic and human speaker verificationcited by 1

Built on by

Not cited yet.