Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study

arXiv:2608.01865 · cs.CL · Submitted 2026-08-15 · Read on arXiv

Darwin Jelestin Muthu, Navya Gupta, Wei Lin Tay, Zhengchen Zhang, Daniel Wang Zhengkui, Rong Tong

cs.CL

Submitted: 2026-08-15

Updated: 2026-08-18

Code: https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fine-Tuning — 10× in this paper · explained in 5 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Decoder — 4× in this paper · explained in 2 episodes
• LoRA Adaptation — 4× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 4× in this paper · explained in 3 episodes
• Adam — 3× in this paper · explained in 3 episodes
• Automatic Speech Recognition (ASR) — 3× in this paper · explained in 2 episodes
• Linear Probe — 3× in this paper · explained in 3 episodes
• Acoustic Features — 2× in this paper · explained in 1 episode
• Augmentation — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Data Augmentation — 2× in this paper · explained in 10 episodes
• F1 Score — 2× in this paper · explained in 4 episodes
• Transformer Encoder — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Character Error Rate — 1× in this paper
• Class Imbalance — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Feature Extraction — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Latent Diffusion Model — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 17 episodes
• Overfitting — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization
• OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering