# Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches

arXiv: https://arxiv.org/abs/2508.08027 · HTML: https://mlsanity.com/paper/2508.08027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Connecting Speech Encoder and Large Language Model for ASR](https://mlsanity.com/paper/2309.13963/) (2023)
- [ASR Error Correction using Large Language Models](https://mlsanity.com/paper/2409.09554/) (2024)
- [Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation](https://mlsanity.com/paper/2401.00662/) (2024)
- [Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition](https://mlsanity.com/paper/2307.08234/) (2023)
- [Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation](https://mlsanity.com/paper/2407.18461/) (2024)
- [Do End-to-End Speech Recognition Models Care About Context?](https://mlsanity.com/paper/2102.09928/) (2021)
- [Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition](https://mlsanity.com/paper/2309.10524/) (2023)
- [DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition](https://mlsanity.com/paper/2501.19010/) (2025)

## Abstract (arXiv)

Speech Recognition (ASR) due to phoneme distortions and high variability. While self-supervised ASR models like Wav2Vec, HuBERT, and Whisper have shown promise, their effectiveness in dysarthric speech remains unclear. This study systematically benchmarks these models with different decoding strategies, including CTC, seq2seq, and LLM-enhanced decoding (BART,GPT-2, Vicuna). Our contributions include (1) benchmarking ASR architectures for dysarthric speech, (2) introducing LLM-based decoding to improve intelligibility, (3) analyzing generalization across datasets, and (4) providing insights into recognition errors across severity levels. Findings highlight that LLM-enhanced decoding improves dysarthric ASR by leveraging linguistic constraints for phoneme restoration and grammatical correction.