mlsanityData to 7 Oct 2026

Towards interfacing large language models with ASR systems using confidence measures and prompting

arXiv 2407.21414 ↗First posted 31 Jul 2024eess.AS cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work investigates post-hoc correction of ASR transcripts with LLMs. To avoid introducing errors into likely accurate transcripts, we propose a range of confidence-based filtering methods. Our results indicate that this can improve the performance of less competitive ASR systems.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 31 Jul 2024.

Builds on

16 of 28 references.

References · 16

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 71
  6. 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
  7. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  8. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  9. 2023Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognitioncited by 56
  10. 2017Dynamic Evaluation of Neural Sequence Modelscited by 53
  11. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  12. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
4 more
  1. 2022Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systemscited by 23
  2. 2023Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understandingcited by 21
  3. 2023Multi-stage Large Language Model Correction for Speech Recognitioncited by 13
  4. 2023Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Studycited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Confidence-Guided Error Correction for Disordered Speech Recognitioncited by 1
  2. 2025Game-Oriented ASR Error Correction via RAG-Enhanced LLMcited by 0
  3. 2026Au-M-ol: A Unified Model for Medical Audio and Language Understandingcited by 0
  4. 2026Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisiancited by 0