# DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction

arXiv: https://arxiv.org/abs/2506.07510 · HTML: https://mlsanity.com/paper/2506.07510/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Large Language Models with Controllable Working Memory](https://mlsanity.com/paper/2211.05110/) (2022)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [STOP: A dataset for Spoken Task Oriented Semantic Parsing](https://mlsanity.com/paper/2207.10643/) (2022)
- [Retrieval Augmented Correction of Named Entity Speech Recognition Errors](https://mlsanity.com/paper/2409.06062/) (2024)
- [Contextualization of ASR with LLM using phonetic retrieval-based augmentation](https://mlsanity.com/paper/2409.15353/) (2024)
- [Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation](https://mlsanity.com/paper/2410.13198/) (2024)
- [Space-Efficient Representation of Entity-centric Query Language Models](https://mlsanity.com/paper/2206.14885/) (2022)

## Built on by (most cited first, 4 of 4)

- [Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations](https://mlsanity.com/paper/2606.13464/) (2026)
- [Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction](https://mlsanity.com/paper/2602.12287/) (2026)
- [AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking](https://mlsanity.com/paper/2609.01828/) (2026)
- [Talk2Agent: Benchmarking Voice Interfaces for Text Agents](https://mlsanity.com/paper/2609.38867/) (2026)

## Abstract (arXiv)

We present DeRAGEC, a method for improving Named Entity (NE) correction in Automatic Speech Recognition (ASR) systems. By extending the Retrieval-Augmented Generative Error Correction (RAGEC) framework, DeRAGEC employs synthetic denoising rationales to filter out noisy NE candidates before correction. By leveraging phonetic similarity and augmented definitions, it refines noisy retrieved NEs using in-context learning, requiring no additional training. Experimental results on CommonVoice and STOP datasets show significant improvements in Word Error Rate (WER) and NE hit ratio, outperforming baseline ASR and RAGEC methods. Specifically, we achieved a 28% relative reduction in WER compared to ASR without postprocessing. Our source code is publicly available at: https://github.com/solee0022/deragec