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

arXiv: https://arxiv.org/abs/2508.05102 · HTML: https://mlsanity.com/paper/2508.05102/

## Key facts

- Cited by 1 papers 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 (most cited first, 17 of 17)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [Investigation of Data Augmentation Techniques for Disordered Speech Recognition](https://mlsanity.com/paper/2201.05562/) (2022)
- [Towards measuring fairness in speech recognition: Fair-Speech dataset](https://mlsanity.com/paper/2408.12734/) (2024)
- [Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation](https://mlsanity.com/paper/2401.00662/) (2024)
- [Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2205.06445/) (2022)
- [Exploring data augmentation in bias mitigation against non-native-accented speech](https://mlsanity.com/paper/2312.15499/) (2023)
- [Towards Identity Preserving Normal to Dysarthric Voice Conversion](https://mlsanity.com/paper/2110.08213/) (2021)
- [On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures](https://mlsanity.com/paper/2407.17997/) (2024)
- [Improving severity preservation of healthy-to-pathological voice conversion with global style tokens](https://mlsanity.com/paper/2310.02570/) (2023)
- [Towards Automatic Data Augmentation for Disordered Speech Recognition](https://mlsanity.com/paper/2312.08641/) (2023)
- [Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech](https://mlsanity.com/paper/2412.03784/) (2024)

## Built on by (most cited first, 1 of 1)

- [Bridging the Perceptual-Statistical Gap in Dysarthria Assessment: Why Machine Learning Still Falls Short](https://mlsanity.com/paper/2510.22237/) (2025)

## 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.