@inproceedings{guo-etal-2026-survey,
title = "A Survey of Audio Reasoning in Audio Foundation Models",
author = "Guo, Zhihan and
Cui, Wenqian and
Lin, Guan-Ting and
Tan, Daxin and
Li, Jingyao and
Zheng, Qiyong and
Wang, Dingdong and
Xiong, Jing and
Shi, Han and
Jia, Jiaya and
King, Irwin",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.349/",
pages = "7295--7312",
ISBN = "979-8-89176-462-0",
abstract = "Reasoning is now central to modern foundation models, but remains underdeveloped in the audio modality. Unlike text transcripts, audio contains not only words but also vocal cues, background events, and temporal patterns, all of which can be necessary for reliable inference. This survey presents the first dedicated synthesis of audio reasoning in multimodal foundation models. We formulate audio reasoning as reasoning-augmented generation grounded in acoustic evidence, distinguishing it from conventional audio understanding. We then organize existing work around two core settings: **Audio-to-Text reasoning**, where models infer textual answers from acoustic input, and **Audio-to-Speech reasoning**, where models reason before or during speech generation under latency constraints. Finally, we summarize evaluation practices and challenges in acoustic grounding, shortcut learning, modality hallucination, and latency-constrained interaction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-survey">
<titleInfo>
<title>A Survey of Audio Reasoning in Audio Foundation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihan</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqian</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guan-Ting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daxin</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiyong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dingdong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaya</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irwin</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Reasoning is now central to modern foundation models, but remains underdeveloped in the audio modality. Unlike text transcripts, audio contains not only words but also vocal cues, background events, and temporal patterns, all of which can be necessary for reliable inference. This survey presents the first dedicated synthesis of audio reasoning in multimodal foundation models. We formulate audio reasoning as reasoning-augmented generation grounded in acoustic evidence, distinguishing it from conventional audio understanding. We then organize existing work around two core settings: **Audio-to-Text reasoning**, where models infer textual answers from acoustic input, and **Audio-to-Speech reasoning**, where models reason before or during speech generation under latency constraints. Finally, we summarize evaluation practices and challenges in acoustic grounding, shortcut learning, modality hallucination, and latency-constrained interaction.</abstract>
<identifier type="citekey">guo-etal-2026-survey</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.349/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>7295</start>
<end>7312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Audio Reasoning in Audio Foundation Models
%A Guo, Zhihan
%A Cui, Wenqian
%A Lin, Guan-Ting
%A Tan, Daxin
%A Li, Jingyao
%A Zheng, Qiyong
%A Wang, Dingdong
%A Xiong, Jing
%A Shi, Han
%A Jia, Jiaya
%A King, Irwin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F guo-etal-2026-survey
%X Reasoning is now central to modern foundation models, but remains underdeveloped in the audio modality. Unlike text transcripts, audio contains not only words but also vocal cues, background events, and temporal patterns, all of which can be necessary for reliable inference. This survey presents the first dedicated synthesis of audio reasoning in multimodal foundation models. We formulate audio reasoning as reasoning-augmented generation grounded in acoustic evidence, distinguishing it from conventional audio understanding. We then organize existing work around two core settings: **Audio-to-Text reasoning**, where models infer textual answers from acoustic input, and **Audio-to-Speech reasoning**, where models reason before or during speech generation under latency constraints. Finally, we summarize evaluation practices and challenges in acoustic grounding, shortcut learning, modality hallucination, and latency-constrained interaction.
%U https://aclanthology.org/2026.findings-emnlp.349/
%P 7295-7312
Markdown (Informal)
[A Survey of Audio Reasoning in Audio Foundation Models](https://aclanthology.org/2026.findings-emnlp.349/) (Guo et al., Findings 2026)
ACL
- Zhihan Guo, Wenqian Cui, Guan-Ting Lin, Daxin Tan, Jingyao Li, Qiyong Zheng, Dingdong Wang, Jing Xiong, Han Shi, Jiaya Jia, and Irwin King. 2026. A Survey of Audio Reasoning in Audio Foundation Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 7295–7312, Budapest, Hungary. Association for Computational Linguistics.