Exploring Generative Error Correction for Dysarthric Speech Recognition
Not on the map. Why?
Abstract (arXiv)
Despite the remarkable progress in end-to-end Automatic Speech Recognition (ASR) engines, accurately transcribing dysarthric speech remains a major challenge. In this work, we proposed a two-stage framework for the Speech Accessibility Project Challenge at INTERSPEECH 2025, which combines cutting-edge speech recognition models with LLM-based generative error correction (GER). We assess different configurations of model scales and training strategies, incorporating specific hypothesis selection to improve transcription accuracy. Experiments on the Speech Accessibility Project dataset demonstrate the strength of our approach on structured and spontaneous speech, while highlighting challenges in single-word recognition. Through comprehensive analysis, we provide insights into the complementary roles of acoustic and linguistic modeling in dysarthric speech recognition
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
24 of 35 references.
References · 24
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
- 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
- 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
- 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
- 2019pyannote.audio: neural building blocks for speaker diarizationcited by 175
12 more
- 2024CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptionscited by 33
- 2024Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyondcited by 20
- 2024Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentationcited by 17
- 2024Benchmarking Representations for Speech, Music, and Acoustic Eventscited by 14
- 2024Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesiscited by 14
- 2024Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditionscited by 11
- 2023ITALIC: An Italian Intent Classification Datasetcited by 10
- 2024A Contrastive Learning Approach to Mitigate Bias in Speech Modelscited by 9
- 2025Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speechcited by 7
- 2024Voice Disorder Analysis: a Transformer-based Approachcited by 5
- 2025voc2vec: A Foundation Model for Non-Verbal Vocalizationcited by 5
- 2025FlanEC: Exploring Flan-T5 for Post-ASR Error Correctioncited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.