RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915452037365760 |
|---|---|
| author | Wang, Pengcheng Li, Sheng Shinozaki, Takahiro |
| author_facet | Wang, Pengcheng Li, Sheng Shinozaki, Takahiro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition Wang, Pengcheng Li, Sheng Shinozaki, Takahiro Audio and Speech Processing Computation and Language 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. |
| title | RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2508.14048 |