# Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

arXiv: https://arxiv.org/abs/2211.01646 · HTML: https://mlsanity.com/paper/2211.01646/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2022.

## Built on by (most cited first, 7 of 7)

- [Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition](https://mlsanity.com/paper/2407.13782/) (2024)
- [Use of Speech Impairment Severity for Dysarthric Speech Recognition](https://mlsanity.com/paper/2305.10659/) (2023)
- [Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test](https://mlsanity.com/paper/2305.13108/) (2023)
- [Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading](https://mlsanity.com/paper/2310.05058/) (2023)
- [Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation](https://mlsanity.com/paper/2407.06310/) (2024)
- [DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition](https://mlsanity.com/paper/2501.19010/) (2025)
- [Augmenting Dysarthric Speech Severity Assessment with MOS Supervision](https://mlsanity.com/paper/2606.18645/) (2026)

## Abstract (arXiv)

Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of impaired speech required for ASR system development. This paper presents novel variational auto-encoder generative adversarial network (VAE-GAN) based personalized disordered speech augmentation approaches that simultaneously learn to encode, generate and discriminate synthesized impaired speech. Separate latent features are derived to learn dysarthric speech characteristics and phoneme context representations. Self-supervised pre-trained Wav2vec 2.0 embedding features are also incorporated. Experiments conducted on the UASpeech corpus suggest the proposed adversarial data augmentation approach consistently outperformed the baseline speed perturbation and non-VAE GAN augmentation methods with trained hybrid TDNN and End-to-end Conformer systems. After LHUC speaker adaptation, the best system using VAE-GAN based augmentation produced an overall WER of 27.78% on the UASpeech test set of 16 dysarthric speakers, and the lowest published WER of 57.31% on the subset of speakers with "Very Low" intelligibility.