RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908893742891008 |
|---|---|
| author | Kumar, Abhishek Sachdeva, Aashraya |
| author_facet | Kumar, Abhishek Sachdeva, Aashraya |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16411 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery Kumar, Abhishek Sachdeva, Aashraya Computation and Language Audio and Speech Processing 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. |
| title | RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.16411 |