# Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training

arXiv: https://arxiv.org/abs/2001.04260 · HTML: https://mlsanity.com/paper/2001.04260/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2020.

## Built on by (most cited first, 6 of 6)

- [Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition](https://mlsanity.com/paper/2204.01670/) (2022)
- [The effect of speech pathology on automatic speaker verification -- a large-scale study](https://mlsanity.com/paper/2204.06450/) (2022)
- [An Objective Evaluation Framework for Pathological Speech Synthesis](https://mlsanity.com/paper/2107.00308/) (2021)
- [Can we reconstruct a dysarthric voice with the large speech model Parler TTS?](https://mlsanity.com/paper/2506.04397/) (2025)
- [Finding My Voice: Generative Reconstruction of Disordered Speech for Automated Clinical Evaluation](https://mlsanity.com/paper/2509.19231/) (2025)
- [Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching](https://mlsanity.com/paper/2506.16127/) (2025)

## Abstract (arXiv)

Dysarthria is a motor speech impairment affecting millions of people. Dysarthric speech can be far less intelligible than those of non-dysarthric speakers, causing significant communication difficulties. The goal of our work is to develop a model for dysarthric to healthy speech conversion using Cycle-consistent GAN. Using 18,700 dysarthric and 8,610 healthy control Korean utterances that were recorded for the purpose of automatic recognition of voice keyboard in a previous study, the generator is trained to transform dysarthric to healthy speech in the spectral domain, which is then converted back to speech. Objective evaluation using automatic speech recognition of the generated utterance on a held-out test set shows that the recognition performance is improved compared with the original dysarthic speech after performing adversarial training, as the absolute WER has been lowered by 33.4%. It demonstrates that the proposed GAN-based conversion method is useful for improving dysarthric speech intelligibility.