{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:44:43Z","timestamp":1776887083431,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434595","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding"],"prefix":"10.1109","author":[{"given":"Tzu-Wen","family":"Hsu","sequence":"first","affiliation":[{"name":"Purdue University,West Lafayette,United States"}]},{"given":"Ke-Han","family":"Lu","sequence":"additional","affiliation":[{"name":"National Taiwan University Taipei,Taiwan"}]},{"given":"Cheng-Han","family":"Chiang","sequence":"additional","affiliation":[{"name":"National Taiwan University Taipei,Taiwan"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University Taipei,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"OpenAI","year":"2024"},{"key":"ref2","article-title":"Instruction tuning with gpt-4","author":"Peng","year":"2023"},{"key":"ref3","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref5","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref7","first-page":"13590","article-title":"The revolution of multimodal large language models: A survey","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Caffagni"},{"key":"ref8","first-page":"12401","article-title":"MM-LLMs: Recent advances in MultiModal large language models","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Zhang"},{"key":"ref9","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-457"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889444"},{"key":"ref13","article-title":"On the landscape of spoken language models: A comprehensive survey","author":"Arora","year":"2025"},{"key":"ref14","article-title":"Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities","author":"Ghosh","year":"2025"},{"key":"ref15","article-title":"On the landscape of spoken language models: A comprehensive survey","author":"Arora","year":"2025","journal-title":"arXiv preprint arXiv:2504.08528"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448257"},{"key":"ref17","article-title":"Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks","author":"Huang","year":"2025","journal-title":"ICLR"},{"key":"ref18","article-title":"MMAU: A massive multitask audio understanding and reasoning benchmark","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Sakshi"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2025-839","article-title":"Sakura: On the multi-hop reasoning of large audio-language models based on speech and audio information","author":"Yang","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.218"},{"key":"ref21","article-title":"Voicebench: Benchmarking llm-based voice assistants","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2410.17196"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1076"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888384"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref26","article-title":"Siren\u2019s song in the ai ocean: A survey on hallucination in large language models","author":"Zhang","year":"2023"},{"key":"ref27","article-title":"A survey of hallucination in large foundation models","author":"Rawte","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-619"},{"key":"ref30","first-page":"783","article-title":"Trusting your evidence: Hallucinate less with context-aware decoding","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"2","author":"Shi"},{"key":"ref31","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"ref33","first-page":"12286","article-title":"Contrastive decoding: Open-ended text generation as optimization","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Li"},{"key":"ref34","article-title":"Salmonn: Towards generic hearing abilities for large language models","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Tang"},{"key":"ref35","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909680"},{"key":"ref37","article-title":"Delta - contrastive decoding mitigates text hallucinations in large language models","author":"Huang","year":"2025"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.acl-long.687","article-title":"Contrastive decoding: Openended text generation as optimization","author":"Li","year":"2023"},{"key":"ref39","article-title":"Finetuned language models are zero-shot learners","volume-title":"International Conference on Learning Representations","author":"Wei"},{"key":"ref40","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","author":"Kim","year":"2019"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.23919\/EUSIPCO55093.2022.9909680","article-title":"Clotho-aqa: A crowdsourced dataset for audio question answering","author":"Lipping","year":"2022"},{"key":"ref42","article-title":"On the audio hallucinations in large audio-video language models","author":"Nishimura","year":"2024"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434595.pdf?arnumber=11434595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:59Z","timestamp":1775192219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434595","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}