mlsanityData to 14 Oct 2026

Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian

arXiv 2605.19711 ↗First posted 19 May 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large language models (LLMs) have shown promise for improving ASR through generative error correction (GER), but their effectiveness in low-resource settings remains underexplored. In addition, it remains unclear to what extent data contamination influences the reported improvements in LLM-based GER. This study investigates LLM-based GER for low-resource Frisian. In addition to a public corpus, we construct and use a Frisian offline dataset with non-public texts for evaluation to control for potential data contamination. Results show that GER improves ASR performance in most settings, with the best GPT-5.1 results surpassing oracle WERs. Comparable gains on the offline dataset indicate that improvements reflect true correction ability. We further provide a detailed error analysis revealing model correction patterns.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

17 of 21 references.

References · 17

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  5. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 348
  6. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  7. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 147
  8. 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 72
  9. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 57
  10. 2023An Open Source Data Contamination Report for Large Language Modelscited by 51
  11. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 42
  12. 2023Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentationcited by 31
5 more
  1. 2024ASR Error Correction using Large Language Modelscited by 24
  2. 2024Towards interfacing large language models with ASR systems using confidence measures and promptingcited by 4
  3. 2025LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Contextcited by 4
  4. 2025Large Language Models based ASR Error Correction for Child Conversationscited by 2
  5. 2025Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASRcited by 2

Built on by

Not cited yet.