@inproceedings{koo-2026-large,
title = "Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities",
author = "Koo, Heejoon",
editor = "Shekhar, Ravi and
Swain, Monorama and
Mishra, Jagabandhu and
Dhar, Sandipan and
Mouratidis, Haralambos and
Purver, Matthew",
booktitle = "Proceedings of the {IMPACT}-{SPEECH} Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech {LLM}s",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.impactspeech-1.3/",
pages = "20--32",
ISBN = "979-8-89176-479-8",
abstract = "Robust selective auditory attention under multilingual interference is critical for reliable LALM deployment. We introduce MUSI, a cocktail party-inspired controlled diagnostic evaluation of source-grounded spokenlanguage understanding and reasoning. Each item pairs an English target dialogue with a plausible distractor in English, Spanish, Korean, or Chinese, and evaluates models under (1) single-stream, (2) separation-based, and (3) end-to-end cocktail party settings across controlled SNRs. Across four open-weight and two closed-source LALMs, we find modeldependent language-conditioned variation and heightened vulnerability at adverse SNRs. Errors are dominated by distractor-grounded source confusion, while separation reduces acoustic overlap but often leaves source attribution unresolved. These findings highlight selective auditory attention as a primary capability for reliable LALM deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koo-2026-large">
<titleInfo>
<title>Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heejoon</namePart>
<namePart type="family">Koo</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>Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ravi</namePart>
<namePart type="family">Shekhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monorama</namePart>
<namePart type="family">Swain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jagabandhu</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandipan</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haralambos</namePart>
<namePart type="family">Mouratidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</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">979-8-89176-479-8</identifier>
</relatedItem>
<abstract>Robust selective auditory attention under multilingual interference is critical for reliable LALM deployment. We introduce MUSI, a cocktail party-inspired controlled diagnostic evaluation of source-grounded spokenlanguage understanding and reasoning. Each item pairs an English target dialogue with a plausible distractor in English, Spanish, Korean, or Chinese, and evaluates models under (1) single-stream, (2) separation-based, and (3) end-to-end cocktail party settings across controlled SNRs. Across four open-weight and two closed-source LALMs, we find modeldependent language-conditioned variation and heightened vulnerability at adverse SNRs. Errors are dominated by distractor-grounded source confusion, while separation reduces acoustic overlap but often leaves source attribution unresolved. These findings highlight selective auditory attention as a primary capability for reliable LALM deployment.</abstract>
<identifier type="citekey">koo-2026-large</identifier>
<location>
<url>https://aclanthology.org/2026.impactspeech-1.3/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
%A Koo, Heejoon
%Y Shekhar, Ravi
%Y Swain, Monorama
%Y Mishra, Jagabandhu
%Y Dhar, Sandipan
%Y Mouratidis, Haralambos
%Y Purver, Matthew
%S Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-479-8
%F koo-2026-large
%X Robust selective auditory attention under multilingual interference is critical for reliable LALM deployment. We introduce MUSI, a cocktail party-inspired controlled diagnostic evaluation of source-grounded spokenlanguage understanding and reasoning. Each item pairs an English target dialogue with a plausible distractor in English, Spanish, Korean, or Chinese, and evaluates models under (1) single-stream, (2) separation-based, and (3) end-to-end cocktail party settings across controlled SNRs. Across four open-weight and two closed-source LALMs, we find modeldependent language-conditioned variation and heightened vulnerability at adverse SNRs. Errors are dominated by distractor-grounded source confusion, while separation reduces acoustic overlap but often leaves source attribution unresolved. These findings highlight selective auditory attention as a primary capability for reliable LALM deployment.
%U https://aclanthology.org/2026.impactspeech-1.3/
%P 20-32
Markdown (Informal)
[Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities](https://aclanthology.org/2026.impactspeech-1.3/) (Koo, IMPACT-SPEECH 2026)
ACL