VoxRAG shows that a spoken query can retrieve topically relevant podcast segments via CLAP audio embeddings and FAISS search, with Recall@10 of 0.60 for somewhat relevant segments, though precise answers remain rare.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering
VoxRAG shows that a spoken query can retrieve topically relevant podcast segments via CLAP audio embeddings and FAISS search, with Recall@10 of 0.60 for somewhat relevant segments, though precise answers remain rare.