mlsanityData to 14 Oct 2026

Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTS

arXiv 2508.05102 ↗First posted 7 Aug 2025eess.AS cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Dysarthric speech poses significant challenges in developing assistive technologies, primarily due to the limited availability of data. Recent advances in neural speech synthesis, especially zero-shot voice cloning, facilitate synthetic speech generation for data augmentation; however, they may introduce biases towards dysarthric speech. In this paper, we investigate the effectiveness of state-of-the-art F5-TTS in cloning dysarthric speech using TORGO dataset, focusing on intelligibility, speaker similarity, and prosody preservation. We also analyze potential biases using fairness metrics like Disparate Impact and Parity Difference to assess disparities across dysarthric severity levels. Results show that F5-TTS exhibits a strong bias toward speech intelligibility over speaker and prosody preservation in dysarthric speech synthesis. Insights from this study can help integrate fairness-aware dysarthric speech synthesis, fostering the advancement of more inclusive speech technologies.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

17 of 28 references.

References · 17

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  3. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  4. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  5. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  6. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 192
  7. 2022Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparitiescited by 28
  8. 2022Investigation of Data Augmentation Techniques for Disordered Speech Recognitioncited by 27
  9. 2024Towards measuring fairness in speech recognition: Fair-Speech datasetcited by 26
  10. 2024Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentationcited by 17
  11. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
  12. 2023Exploring data augmentation in bias mitigation against non-native-accented speechcited by 11
5 more
  1. 2021Towards Identity Preserving Normal to Dysarthric Voice Conversioncited by 10
  2. 2024On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architecturescited by 4
  3. 2023Improving severity preservation of healthy-to-pathological voice conversion with global style tokenscited by 1
  4. 2023Towards Automatic Data Augmentation for Disordered Speech Recognitioncited by 1
  5. 2024Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speechcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Bridging the Perceptual-Statistical Gap in Dysarthria Assessment: Why Machine Learning Still Falls Shortcited by 0