{"slug": "can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of", "title": "Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities", "summary": "A study by Heejoon Koo, published in the Proceedings of the IMPACT-SPEECH Workshop (pages 20–32, Budapest, October 2026), introduced MUSI, a cocktail-party-inspired diagnostic benchmark pairing an English target dialogue with a plausible distractor in English, Spanish, Korean, or Chinese. Testing four open-weight and two closed-source large audio-language models across single-stream, separation-based, and end-to-end cocktail party settings at controlled SNRs, Koo found model-dependent language-conditioned variation and heightened vulnerability at adverse SNRs, with errors dominated by distractor-grounded source confusion. Separation reduced acoustic overlap but often left source attribution unresolved, leading Koo to identify selective auditory attention as a primary capability for reliable LALM deployment.", "body_md": "##### Abstract\n\nRobust 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.\n- Anthology ID:\n- 2026.impactspeech-1.3\n- Volume:\n- [Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs](https://aclanthology.org/volumes/2026.impactspeech-1/)\n- Month:\n- October\n- Year:\n- 2026\n- Address:\n- Budapest, Hungary\n- Editors:\n- [Ravi Shekhar](https://aclanthology.org/people/ravi-shekhar/) ,[Monorama Swain](https://aclanthology.org/people/monorama-swain/) ,[Jagabandhu Mishra](https://aclanthology.org/people/jagabandhu-mishra/unverified/) ,[Sandipan Dhar](https://aclanthology.org/people/sandipan-dhar/unverified/) ,[Haralambos Mouratidis](https://aclanthology.org/people/haralambos-mouratidis/) ,[Matthew Purver](https://aclanthology.org/people/matthew-purver/)\n- Venues:\n- [IMPACT-SPEECH](https://aclanthology.org/venues/impactspeech/) |[WS](https://aclanthology.org/venues/ws/)\n- SIG:\n- Publisher:\n- Association for Computational Linguistics\n- Note:\n- Pages:\n- 20–32\n- Language:\n- URL:\n- [https://aclanthology.org/2026.impactspeech-1.3/](https://aclanthology.org/2026.impactspeech-1.3/)\n- DOI:\n- Cite (ACL):\n- Heejoon Koo. 2026. [Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities](https://aclanthology.org/2026.impactspeech-1.3/) . In*Proceedings of the IMPACT-SPEECH Workshop: Identifying, Measuring, Preventing, and Assessing Consequences of Bias in Speech LLMs* , pages 20–32, Budapest, Hungary. Association for Computational Linguistics.\n- Cite (Informal):\n- [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)\n- PDF:\n- [https://aclanthology.org/2026.impactspeech-1.3.pdf](https://aclanthology.org/2026.impactspeech-1.3.pdf)", "url": "https://wpnews.pro/news/can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of", "canonical_source": "https://aclanthology.org/2026.impactspeech-1.3/", "published_at": "2026-10-24 00:00:00+00:00", "updated_at": "2026-10-25 21:41:26.717931+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research", "ai-safety"], "entities": ["Heejoon Koo", "MUSI", "IMPACT-SPEECH Workshop", "Association for Computational Linguistics", "Budapest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of", "markdown": "https://wpnews.pro/news/can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of.md", "text": "https://wpnews.pro/news/can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of.txt", "jsonld": "https://wpnews.pro/news/can-large-audio-language-models-ignore-multilingual-distractors-an-evaluation-of.jsonld"}}