大型音频语言模型能忽略多语言干扰项吗？对其选择性听觉注意能力的评估

Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2605.17225 (eess) [Submitted on 17 May 2026 (v1), last revised 17 Sep 2026 (this version, v2)] Title:Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities Authors:Heejoon Koo View a PDF of the paper titled Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities, by Heejoon Koo View PDF HTML (experimental) 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 spoken-language 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 model-dependent 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 an primary capability for reliable LALMs deployment. Comments: Subjects: Audio and Speech Processing (eess.AS) Cite as: arXiv:2605.17225 [eess.AS] (or arXiv:2605.17225v2 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2605.17225 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Heejoon Koo [view email] [v1] Sun, 17 May 2026 02:13:58 UTC (383 KB) [v2] Thu, 17 Sep 2026 16:11:59 UTC (386 KB) Full-text links: Access Paper: View a PDF of the paper titled Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities, by Heejoon Koo View PDF HTML (experimental) TeX Source view license Current browse context: eess.AS new | recent | 2026-05 Change to browse by: eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)