SpeechRAG retrieves audio passages directly with a speech adapter feeding a frozen text retriever, matching ground-truth text retrieval and beating ASR cascades on high-WER speech.
Robust multi model rag pipeline for documents containing text, table & images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Speech Retrieval-Augmented Generation without Automatic Speech Recognition
SpeechRAG retrieves audio passages directly with a speech adapter feeding a frozen text retriever, matching ground-truth text retrieval and beating ASR cascades on high-WER speech.