RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition
On the map: Retrieval-augmented generation → Conversational and speech RAG
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 8 references that are in the map. First posted on arXiv 5 Aug 2025.
Builds on
5 of 8 references.
References · 5
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
- 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Retrieval-Augmented Speech Recognition Approach for Domain Challenges
- 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
- 2025GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems
- 2024Speech Retrieval-Augmented Generation without Automatic Speech Recognition
- 2024Retrieval Augmented Correction of Named Entity Speech Recognition Errors
- 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
- 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
- 2024Retrieval Augmented End-to-End Spoken Dialog Models