Audio Representation Learning and Downstream Task Modeling: A Survey

Kaihong Wang; Liang He

Audio Representation Learning and Downstream Task Modeling: A Survey

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Audio representation learning has revolutionized acoustic intelligence, enabling audio foundation models to generalize and perform well across various downstream tasks. To better characterize the paradigm shift in general representation extraction and modeling, this survey presents a unified decoupled framework separating audio processing into audio-to-feature representation learning and feature-to-target downstream modeling. We systematically review modeling domains, representation forms, architectures, and pre-training paradigms, while categorizing five integration mechanisms and downstream modeling paradigms. Furthermore, we summarize representative systems and discuss key trade-offs, providing practical guidelines for designing next-generation audio foundation models.

Anthology ID:: 2026.multilll-1.12
Volume:: Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning
Month:: November
Year:: 2026
Address:: Hengqin, Zhuhai, China
Editors:: Xiaoman Wang, Qianyu Wang, Zhengyuan Liu, Nancy F. Chen, Zheng Yuan, Yunshi Lan, Jing Jiang
Venues:: Multi-LLL | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 100–130
Language:
URL:: https://aclanthology.org/2026.multilll-1.12/
DOI:
Bibkey:
Cite (ACL):: Kaihong Wang and Liang He. 2026. Audio Representation Learning and Downstream Task Modeling: A Survey. In Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning, pages 100–130, Hengqin, Zhuhai, China. Association for Computational Linguistics.
Cite (Informal):: Audio Representation Learning and Downstream Task Modeling: A Survey (Wang & He, Multi-LLL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.multilll-1.12.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{wang-he-2026-audio,
    title = "Audio Representation Learning and Downstream Task Modeling: A Survey",
    author = "Wang, Kaihong  and
      He, Liang",
    editor = "Wang, Xiaoman  and
      Wang, Qianyu  and
      Liu, Zhengyuan  and
      Chen, Nancy F.  and
      Yuan, Zheng  and
      Lan, Yunshi  and
      Jiang, Jing",
    booktitle = "Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning",
    month = nov,
    year = "2026",
    address = "Hengqin, Zhuhai, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.multilll-1.12/",
    pages = "100--130",
    ISBN = "979-8-89176-449-1",
    abstract = "Audio representation learning has revolutionized acoustic intelligence, enabling audio foundation models to generalize and perform well across various downstream tasks. To better characterize the paradigm shift in general representation extraction and modeling, this survey presents a unified decoupled framework separating audio processing into audio-to-feature representation learning and feature-to-target downstream modeling. We systematically review modeling domains, representation forms, architectures, and pre-training paradigms, while categorizing five integration mechanisms and downstream modeling paradigms. Furthermore, we summarize representative systems and discuss key trade-offs, providing practical guidelines for designing next-generation audio foundation models."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-he-2026-audio">
    <titleInfo>
        <title>Audio Representation Learning and Downstream Task Modeling: A Survey</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kaihong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Xiaoman</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Qianyu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zhengyuan</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="given">F</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zheng</namePart>
            <namePart type="family">Yuan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yunshi</namePart>
            <namePart type="family">Lan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jing</namePart>
            <namePart type="family">Jiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-449-1</identifier>
    </relatedItem>
    <abstract>Audio representation learning has revolutionized acoustic intelligence, enabling audio foundation models to generalize and perform well across various downstream tasks. To better characterize the paradigm shift in general representation extraction and modeling, this survey presents a unified decoupled framework separating audio processing into audio-to-feature representation learning and feature-to-target downstream modeling. We systematically review modeling domains, representation forms, architectures, and pre-training paradigms, while categorizing five integration mechanisms and downstream modeling paradigms. Furthermore, we summarize representative systems and discuss key trade-offs, providing practical guidelines for designing next-generation audio foundation models.</abstract>
    <identifier type="citekey">wang-he-2026-audio</identifier>
    <location>
        <url>https://aclanthology.org/2026.multilll-1.12/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>100</start>
            <end>130</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Audio Representation Learning and Downstream Task Modeling: A Survey
%A Wang, Kaihong
%A He, Liang
%Y Wang, Xiaoman
%Y Wang, Qianyu
%Y Liu, Zhengyuan
%Y Chen, Nancy F.
%Y Yuan, Zheng
%Y Lan, Yunshi
%Y Jiang, Jing
%S Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-449-1
%F wang-he-2026-audio
%X Audio representation learning has revolutionized acoustic intelligence, enabling audio foundation models to generalize and perform well across various downstream tasks. To better characterize the paradigm shift in general representation extraction and modeling, this survey presents a unified decoupled framework separating audio processing into audio-to-feature representation learning and feature-to-target downstream modeling. We systematically review modeling domains, representation forms, architectures, and pre-training paradigms, while categorizing five integration mechanisms and downstream modeling paradigms. Furthermore, we summarize representative systems and discuss key trade-offs, providing practical guidelines for designing next-generation audio foundation models.
%U https://aclanthology.org/2026.multilll-1.12/
%P 100-130

Download as File

Markdown (Informal)

[Audio Representation Learning and Downstream Task Modeling: A Survey](https://aclanthology.org/2026.multilll-1.12/) (Wang & He, Multi-LLL 2026)

Audio Representation Learning and Downstream Task Modeling: A Survey (Wang & He, Multi-LLL 2026)

ACL

Kaihong Wang and Liang He. 2026. Audio Representation Learning and Downstream Task Modeling: A Survey. In Proceedings of the 1st Workshop on Multi-modality and Multi-lingual Language Learning, pages 100–130, Hengqin, Zhuhai, China. Association for Computational Linguistics.