<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-large-language">
    <titleInfo>
        <title>When Large Language Models Meet Speech: A Survey on Integration Approaches</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhengdong</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shuichiro</namePart>
        <namePart type="family">Shimizu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yahan</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenhui</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for future research.</abstract>
    <identifier type="citekey">yang-etal-2025-large-language</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1041</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1041/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>20298</start>
            <end>20315</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Large Language Models Meet Speech: A Survey on Integration Approaches
%A Yang, Zhengdong
%A Shimizu, Shuichiro
%A Yu, Yahan
%A Chu, Chenhui
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F yang-etal-2025-large-language
%X Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which is naturally related to text. This paper surveys the integration of speech with LLMs, categorizing the methodologies into three primary approaches: text-based, latent-representation-based, and audio-token-based integration. We also demonstrate how these methods are applied across various speech-related applications and highlight the challenges in this field to offer inspiration for future research.
%R 10.18653/v1/2025.findings-acl.1041
%U https://aclanthology.org/2025.findings-acl.1041/
%U https://doi.org/10.18653/v1/2025.findings-acl.1041
%P 20298-20315

Markdown (Informal)

[When Large Language Models Meet Speech: A Survey on Integration Approaches](https://aclanthology.org/2025.findings-acl.1041/) (Yang et al., Findings 2025)

• When Large Language Models Meet Speech: A Survey on Integration Approaches (Yang et al., Findings 2025)

ACL

• Zhengdong Yang, Shuichiro Shimizu, Yahan Yu, and Chenhui Chu. 2025. When Large Language Models Meet Speech: A Survey on Integration Approaches. In Findings of the Association for Computational Linguistics: ACL 2025, pages 20298–20315, Vienna, Austria. Association for Computational Linguistics.