Salvato in:
Dettagli Bibliografici
Autori principali: Xie, Peijin, Qian, Shun, Liu, Bingquan, Wang, Dexin, Sun, Lin, Zhang, Xiangzheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.07538
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912580394549248
author Xie, Peijin
Qian, Shun
Liu, Bingquan
Wang, Dexin
Sun, Lin
Zhang, Xiangzheng
author_facet Xie, Peijin
Qian, Shun
Liu, Bingquan
Wang, Dexin
Sun, Lin
Zhang, Xiangzheng
contents Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further boost performance, we integrate a layout-aware reranking mechanism to refine retrieval. Experiments demonstrate substantial improvements in both efficiency and accuracy. To advance research in this direction, we also release the first bilingual speech--document RAG dataset, featuring Chinese and English voice queries paired with multimodal document content. Both the dataset and our pipeline will be made available at repository:https://github.com/xiepeijinhit-hue/textlessrag
format Preprint
id arxiv_https___arxiv_org_abs_2509_07538
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TextlessRAG: End-to-End Visual Document RAG by Speech Without Text
Xie, Peijin
Qian, Shun
Liu, Bingquan
Wang, Dexin
Sun, Lin
Zhang, Xiangzheng
Computer Vision and Pattern Recognition
Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further boost performance, we integrate a layout-aware reranking mechanism to refine retrieval. Experiments demonstrate substantial improvements in both efficiency and accuracy. To advance research in this direction, we also release the first bilingual speech--document RAG dataset, featuring Chinese and English voice queries paired with multimodal document content. Both the dataset and our pipeline will be made available at repository:https://github.com/xiepeijinhit-hue/textlessrag
title TextlessRAG: End-to-End Visual Document RAG by Speech Without Text
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07538