mlsanityData to 7 Oct 2026

RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery

arXiv 2603.16411 ↗First posted 17 Mar 2026cs.CL eess.AScited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the ASR output, post-ASR correction becomes difficult. To address this, we introduce RECOVER, an agentic correction framework that serves as a tool-using agent. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints. The hypotheses are used using different strategies, namely, 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, and LLM-Select. Evaluated across five diverse datasets, it achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points. The LLM-Select achieves the best overall performance in entity correction while maintaining overall WER.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 30 of its 35 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

30 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025VoiceAgentBench: Are Voice Assistants ready for agentic tasks?9 Oct
  2. 2025Agentic AI Frameworks: Architectures, Protocols, and Design Challenges13 Aug

Other references · 28

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2024GPT-4o System Cardcited by 4,467
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  7. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  8. 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 192
  9. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  10. 2020Contextual RNN-T For Open Domain ASRcited by 85
  11. 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 71
  12. 2019Two-Pass End-to-End Speech Recognitioncited by 62
16 more
  1. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 60
  2. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  3. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
  4. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  5. 2024ASR Error Correction using Large Language Modelscited by 23
  6. 2022Error Correction in ASR using Sequence-to-Sequence Modelscited by 19
  7. 2022ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communicationscited by 19
  8. 2020Automatic Speech Recognition Benchmark for Air-Traffic Communicationscited by 17
  9. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  10. 2025ContextASR-Bench: A Massive Contextual Speech Recognition Benchmarkcited by 14
  11. 2023Multi-stage Large Language Model Correction for Speech Recognitioncited by 13
  12. 2023Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Studycited by 7
  13. 2024Improving Domain-Specific ASR with LLM-Generated Contextual Descriptionscited by 6
  14. 2025ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languagescited by 3
  15. 2025Large Language Models based ASR Error Correction for Child Conversationscited by 2
  16. 2024Unifying Global and Near-Context Biasing in a Single Trie Passcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction
  2. 2026agentic-ger: terminology recovery in long-form speech using global context
  3. 2024Retrieval Augmented Correction of Named Entity Speech Recognition Errors
  4. 2024Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
  5. 2025DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
  6. 2025LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context
  7. 2025Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context
  8. 2026Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction