RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery
This addresses costly entity errors in domains like finance, medicine, and air traffic control, representing a novel method for a known bottleneck.
The paper tackled the problem of correcting entity recognition errors in Automatic Speech Recognition (ASR) for rare and domain-specific terms, introducing RECOVER, an agentic correction framework that achieved 8-46% relative reductions in entity-phrase word error rate and increased recall by up to 22 percentage points across five datasets.
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.