mlsanityData to 14 Oct 2026

Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition

arXiv 2509.20397 ↗First posted 23 Sep 2025eess.AS cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Speech impairments resulting from congenital disorders, such as cerebral palsy, down syndrome, or apert syndrome, as well as acquired brain injuries due to stroke, traumatic accidents, or tumors, present major challenges to automatic speech recognition (ASR) systems. Despite recent advancements, state-of-the-art ASR models like Whisper still struggle with non-normative speech due to limited training data availability and high acoustic variability. Moreover, collecting and annotating non-normative speech is burdensome: speaking is effortful for many affected individuals, while laborious annotation often requires caregivers familiar with the speaker. This work introduces a novel ASR personalization method based on Bayesian Low-rank Adaptation for data-efficient fine-tuning. We validate our method on the English UA-Speech dataset and a newly collected German speech dataset, BF-Sprache, from a child with structural speech impairment. The dataset and approach are designed to reflect the challenges of low-resource settings that include individuals with speech impairments. Our method significantly improves ASR accuracy for impaired speech while maintaining data and annotation efficiency, offering a practical path toward inclusive ASR.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

20 of 34 references.

References · 20

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  4. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  5. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 173
  6. 2023Bayesian Low-rank Adaptation for Large Language Modelscited by 115
  7. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 102
  8. 2024Asymmetry in Low-Rank Adapters of Foundation Modelscited by 86
  9. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 45
  10. 2024LoRA Dropout as a Sparsity Regularizer for Overfitting Controlcited by 35
  11. 2024MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuningcited by 31
  12. 2022Speaker adaptation for Wav2vec2 based dysarthric ASRcited by 21
8 more
  1. 2022On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approachescited by 13
  2. 2024Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gatescited by 8
  3. 2023Parameter-efficient Dysarthric Speech Recognition Using Adapter Fusion and Householder Transformationcited by 6
  4. 2024Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptationcited by 6
  5. 2025Improving LoRA with Variational Learningcited by 5
  6. 2025Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speechcited by 4
  7. 2023A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessmentcited by 3
  8. 2024Hypernetworks for Personalizing ASR to Atypical Speechcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognitioncited by 1
  2. 2026Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speechcited by 0
  3. 2026Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Basescited by 0
  4. 2026Understanding Personalization Gains in Whispercited by 0