TextlessRAG retrieves document image pages and generates spoken answers directly from an audio query, without OCR, ASR, or TTS, and introduces a bilingual speech-document RAG benchmark.
We also introduce the first bilingual bench- mark for this task and release the first open-source Chinese visual document RAG dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
TextlessRAG: End-to-End Visual Document RAG by Speech Without Text
TextlessRAG retrieves document image pages and generates spoken answers directly from an audio query, without OCR, ASR, or TTS, and introduces a bilingual speech-document RAG benchmark.