VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering

Introduces a multimodal retrieval-augmented generation framework for spoken question answering without full transcription reliance.

Recommended citation: Rackauckas, Z., & Hirschberg, J. (2025). "VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering." MAGMaR @ ACL 2025.
Download Paper