RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition

Pengcheng Wang, Sheng Li, Takahiro Shinozaki
8/5/2025
eess.AScs.CL

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

In this paper, we propose RAG-Boost (ST-ShinozakiLab Task I system), which enhances the baseline LLM-based ASR system of the MLC-SLM Challenge (task I) with a retrieval-augmented generation (RAG) module on the fly. Each partial ASR hypothesis queries a vector store of audio-text pairs and domain terms, and the retrieved results are fused with the live ASR hypotheses to fix recognition errors. The fused hypotheses are passed to the LLM, yielding improved responses.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation

89% match2024

Retrieval-Augmented Speech Recognition Approach for Domain Challenges

88% match2025

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

85% match1 repo3142024

RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition

84% match2025

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

84% match1 repo7712024

When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs

84% match2025

Cite this paper

@article{wang2025ragboost,
  title  = {RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition},
  author = {Pengcheng Wang and Sheng Li and Takahiro Shinozaki},
  year   = {2025},
  eprint = {2508.14048},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.14048v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.14048.svg)](https://codeofpaper.com/paper/2508.14048)

Discussion