@inproceedings{sridhar-etal-2026-spatial,
title = "Spatial Audio Question Answering and Reasoning on Dynamic Source Movements",
author = "Sridhar, Arvind Krishna and
Guo, Yinyi and
Visser, Erik",
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.132/",
pages = "2680--2704",
ISBN = "979-8-89176-462-0",
abstract = "Spatial audio understanding aims to enable machines to interpret complex auditory scenes, particularly when sound sources move over time. In this work, we study Spatial Audio Question Answering (SAQA) with a focus on movement reasoning, where a model must infer object motion, position and directional changes directly from stereo audio. First, we introduce a movement-centric spatial audio augmentation framework that synthesizes diverse motion patterns from isolated mono audio events, enabling controlled and scalable training data generation. Second, we propose an end-to-end multimodal finetuning approach with a thinking mode, which allows audio-language models to produce explicit intermediate reasoning steps before predicting an answer. Third, we investigate the impact of query-conditioned source separation as a preprocessing stage and compare three inference regimes: no masking, an audio grounding model (AGM), and ground-truth masks. Our results show that the benefits of thinking mode are most pronounced when paired with high-quality source separation rather than in isolation, with an improvement of +5.1{\%} when a single event is present in the question. These findings highlight the relationship between movement modeling, reasoning, and separation quality, offering new insights for advancing spatial audio understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sridhar-etal-2026-spatial">
<titleInfo>
<title>Spatial Audio Question Answering and Reasoning on Dynamic Source Movements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arvind</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Sridhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinyi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Visser</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>Spatial audio understanding aims to enable machines to interpret complex auditory scenes, particularly when sound sources move over time. In this work, we study Spatial Audio Question Answering (SAQA) with a focus on movement reasoning, where a model must infer object motion, position and directional changes directly from stereo audio. First, we introduce a movement-centric spatial audio augmentation framework that synthesizes diverse motion patterns from isolated mono audio events, enabling controlled and scalable training data generation. Second, we propose an end-to-end multimodal finetuning approach with a thinking mode, which allows audio-language models to produce explicit intermediate reasoning steps before predicting an answer. Third, we investigate the impact of query-conditioned source separation as a preprocessing stage and compare three inference regimes: no masking, an audio grounding model (AGM), and ground-truth masks. Our results show that the benefits of thinking mode are most pronounced when paired with high-quality source separation rather than in isolation, with an improvement of +5.1% when a single event is present in the question. These findings highlight the relationship between movement modeling, reasoning, and separation quality, offering new insights for advancing spatial audio understanding.</abstract>
<identifier type="citekey">sridhar-etal-2026-spatial</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.132/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2680</start>
<end>2704</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spatial Audio Question Answering and Reasoning on Dynamic Source Movements
%A Sridhar, Arvind Krishna
%A Guo, Yinyi
%A Visser, Erik
%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 sridhar-etal-2026-spatial
%X Spatial audio understanding aims to enable machines to interpret complex auditory scenes, particularly when sound sources move over time. In this work, we study Spatial Audio Question Answering (SAQA) with a focus on movement reasoning, where a model must infer object motion, position and directional changes directly from stereo audio. First, we introduce a movement-centric spatial audio augmentation framework that synthesizes diverse motion patterns from isolated mono audio events, enabling controlled and scalable training data generation. Second, we propose an end-to-end multimodal finetuning approach with a thinking mode, which allows audio-language models to produce explicit intermediate reasoning steps before predicting an answer. Third, we investigate the impact of query-conditioned source separation as a preprocessing stage and compare three inference regimes: no masking, an audio grounding model (AGM), and ground-truth masks. Our results show that the benefits of thinking mode are most pronounced when paired with high-quality source separation rather than in isolation, with an improvement of +5.1% when a single event is present in the question. These findings highlight the relationship between movement modeling, reasoning, and separation quality, offering new insights for advancing spatial audio understanding.
%U https://aclanthology.org/2026.findings-emnlp.132/
%P 2680-2704
Markdown (Informal)
[Spatial Audio Question Answering and Reasoning on Dynamic Source Movements](https://aclanthology.org/2026.findings-emnlp.132/) (Sridhar et al., Findings 2026)
ACL