<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rackauckas-hirschberg-2025-voxrag">
    <titleInfo>
        <title>VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zackary</namePart>
        <namePart type="family">Rackauckas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julia</namePart>
        <namePart type="family">Hirschberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Reno</namePart>
            <namePart type="family">Kriz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kenton</namePart>
            <namePart type="family">Murray</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-280-0</identifier>
    </relatedItem>
    <abstract>We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation, speaker diarization, CLAP audio embeddings, and FAISS retrieval using L2-normalized cosine similarity. We construct a 50-query test set recorded as spoken input by a native English speaker. Retrieval quality was evaluated using LLM-as-a-judge annotations. For very relevant segments, cosine similarity achieved a Recall@10 of 0.34. For somewhat relevant segments, Recall@10 rose to 0.60 and nDCG@10 to 0.27, highlighting strong topical alignment. Answer quality was judged on a 0–2 scale across relevance, accuracy, completeness, and precision, with mean scores of 0.84, 0.58, 0.56, and 0.46 respectively. While precision and retrieval quality remain key limitations, VoxRAG shows that transcription-free speech-to-speech retrieval is feasible in RAG systems.</abstract>
    <identifier type="citekey">rackauckas-hirschberg-2025-voxrag</identifier>
    <identifier type="doi">10.18653/v1/2025.magmar-1.3</identifier>
    <location>
        <url>https://aclanthology.org/2025.magmar-1.3/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>40</start>
            <end>46</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering
%A Rackauckas, Zackary
%A Hirschberg, Julia
%Y Kriz, Reno
%Y Murray, Kenton
%S Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-280-0
%F rackauckas-hirschberg-2025-voxrag
%X We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation, speaker diarization, CLAP audio embeddings, and FAISS retrieval using L2-normalized cosine similarity. We construct a 50-query test set recorded as spoken input by a native English speaker. Retrieval quality was evaluated using LLM-as-a-judge annotations. For very relevant segments, cosine similarity achieved a Recall@10 of 0.34. For somewhat relevant segments, Recall@10 rose to 0.60 and nDCG@10 to 0.27, highlighting strong topical alignment. Answer quality was judged on a 0–2 scale across relevance, accuracy, completeness, and precision, with mean scores of 0.84, 0.58, 0.56, and 0.46 respectively. While precision and retrieval quality remain key limitations, VoxRAG shows that transcription-free speech-to-speech retrieval is feasible in RAG systems.
%R 10.18653/v1/2025.magmar-1.3
%U https://aclanthology.org/2025.magmar-1.3/
%U https://doi.org/10.18653/v1/2025.magmar-1.3
%P 40-46

Markdown (Informal)

[VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering](https://aclanthology.org/2025.magmar-1.3/) (Rackauckas & Hirschberg, MAGMaR 2025)

• VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering (Rackauckas & Hirschberg, MAGMaR 2025)

ACL

• Zackary Rackauckas and Julia Hirschberg. 2025. VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering. In Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025), pages 40–46, Vienna, Austria. Association for Computational Linguistics.