In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent audio representations to improve an encoder-decoder ASR system. Synthetic training data is generated by fine-tuning Parler-TTS to mimic dysarthric speech, using LLM-generated prompts for corpus-consistent target transcripts. Personalization with x-vectors consistently reduces word error rates (WERs) over non-personalized fine-tuning. AdaLoRA adapters outperform full fine-tuning and standard low-rank adaptation, achieving relative WER reductions of ~23% and ~22%, respectively. Further improvements (~5% WER reduction) come from incorporating wav2vec 2.0-based audio representations. Training with synthetic dysarthric speech yields up to ~7% relative WER improvement over personalized fine-tuning alone.
@article{arxiv.2505.12991,
title = {Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition},
author = {Dominik Wagner and Ilja Baumann and Natalie Engert and Seanie Lee and Elmar Nöth and Korbinian Riedhammer and Tobias Bocklet},
journal= {arXiv preprint arXiv:2505.12991},
year = {2025}
}