{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:15:06Z","timestamp":1783156506676,"version":"3.54.6"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025Z055"],"award-info":[{"award-number":["2025Z055"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","award":["LZJMD25D050002"],"award-info":[{"award-number":["LZJMD25D050002"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133881","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:05:35Z","timestamp":1778169935000},"page":"133881","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multimodal addressee detection in in-vehicle multi-party dialogue: An end-to-end fine-tuning approach based on Qwen2.5-Omni"],"prefix":"10.1016","volume":"695","author":[{"given":"Zhonglin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjie","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongwei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoyue","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2815-8611","authenticated-orcid":false,"given":"Shibo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133881_bib0005","series-title":"Proceedings of Interspeech 2022","first-page":"1821","article-title":"Turn-taking prediction for natural conversational speech","author":"Chang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133881_bib0010","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.neucom.2026.133881_bib0015","series-title":"Proceedings of Interspeech 2025","first-page":"5788","article-title":"Adaptive knowledge distillation for device-directed speech detection","author":"Chi","year":"2025"},{"key":"10.1016\/j.neucom.2026.133881_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.wocn.2021.101123","article-title":"Acoustic-phonetic properties of siri- and human-directed speech","volume":"90","author":"Cohn","year":"2022","journal-title":"J. Phon."},{"key":"10.1016\/j.neucom.2026.133881_bib0025","doi-asserted-by":"crossref","DOI":"10.3389\/fcomm.2021.675704","article-title":"Prosodic differences in human- and alexa-directed speech, but similar local intelligibility adjustments","volume":"6","author":"Cohn","year":"2021","journal-title":"Front. Commun."},{"key":"10.1016\/j.neucom.2026.133881_bib0030","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","first-page":"2088","article-title":"Talk2car: taking control of your self-driving Car","author":"Deruyttere","year":"2019"},{"key":"10.1016\/j.neucom.2026.133881_bib0035","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2026.133881_bib0040","series-title":"AAAI Fall Symposium: Aurally Informed Performance","first-page":"22","article-title":"Are you talking to me? Dialogue systems supporting mixed teams of humans and robots","author":"Dowding","year":"2006"},{"key":"10.1016\/j.neucom.2026.133881_bib0045","series-title":"Proceedings of the 18th ACM International Conference on Multimedia","first-page":"1459","article-title":"openSMILE: the Munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010"},{"key":"10.1016\/j.neucom.2026.133881_bib0050","series-title":"Proceedings of Interspeech 2020","first-page":"5036","article-title":"Conformer: convolution-augmented transformer for speech recognition","author":"Gulati","year":"2020"},{"key":"10.1016\/j.neucom.2026.133881_bib0055","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.133881_bib0060","series-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing","first-page":"3451","article-title":"HuBERT: self-supervised speech representation learning by masked prediction of hidden units","volume":"vol. 29","author":"Hsu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133881_bib0065","series-title":"International Conference on Learning Representations","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133881_bib0070","series-title":"Proceedings of Interspeech 2019","first-page":"3342","article-title":"A study for improving device-directed speech detection toward frictionless human\u2013machine interaction","author":"Huang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133881_bib0075","series-title":"Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology","first-page":"330","article-title":"An LLM benchmark for addressee recognition in multi-modal multi-party dialogue","author":"Inoue","year":"2025"},{"key":"10.1016\/j.neucom.2026.133881_bib0080","series-title":"Proceedings of the 5th SIGdial Workshop on Discourse and Dialogue","first-page":"89","article-title":"Towards automatic addressee identification in multi-party dialogues","author":"Jovanovic","year":"2004"},{"key":"10.1016\/j.neucom.2026.133881_bib0085","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.133881_bib0090","series-title":"Proceedings of the 29th Symposium on Operating Systems Principles","first-page":"611","article-title":"Efficient memory management for large language model serving with PagedAttention","author":"Kwon","year":"2023"},{"key":"10.1016\/j.neucom.2026.133881_bib0095","series-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"221","article-title":"Using out-of-domain data for lexical addressee detection in human\u2013human\u2013computer dialog","author":"Lee","year":"2013"},{"key":"10.1016\/j.neucom.2026.133881_bib0100","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.133881_bib0105","series-title":"Proceedings of Interspeech 2018","first-page":"1225","article-title":"Device-directed utterance detection","author":"Mallidi","year":"2018"},{"key":"10.1016\/j.neucom.2026.133881_bib0110","series-title":"Proceedings of the 15th ACM International Conference on Multimodal Interaction","first-page":"35","article-title":"Implementation and evaluation of a multimodal addressee identification mechanism for multiparty conversation systems","author":"Nakano","year":"2013"},{"key":"10.1016\/j.neucom.2026.133881_bib0115","first-page":"32","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133881_bib0120","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.neucom.2026.133881_bib0125","series-title":"Proceedings of Interspeech 2017","first-page":"3442","article-title":"The INTERSPEECH 2017 computational paralinguistics challenge: addressee, cold & snoring","author":"Schuller","year":"2017"},{"key":"10.1016\/j.neucom.2026.133881_bib0130","series-title":"Proceedings of Interspeech 2012","first-page":"334","article-title":"Learning when to listen: detecting system-addressed speech in human\u2013human\u2013computer dialog","author":"Shriberg","year":"2012"},{"key":"10.1016\/j.neucom.2026.133881_bib0135","series-title":"Proceedings of Interspeech 2013","first-page":"2559","article-title":"Addressee detection for dialog systems using temporal and spectral dimensions of speaking style","author":"Shriberg","year":"2013"},{"key":"10.1016\/j.neucom.2026.133881_bib0140","series-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","first-page":"615","article-title":"Alexa in the wild: collecting unconstrained conversations with a modern voice assistant in a public environment","author":"Siegert","year":"2020"},{"key":"10.1016\/j.neucom.2026.133881_bib0145","series-title":"Proceedings of the LREC 2018 Workshop","article-title":"Voice assistant conversation corpus (VACC): a multi-scenario dataset for addressee detection in human\u2013computer interaction using amazon\u2019s ALEXA","author":"Siegert","year":"2018"},{"key":"10.1016\/j.neucom.2026.133881_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2020.101178","article-title":"Turn-taking in conversational systems and human-robot interaction: a review","volume":"67","author":"Skantze","year":"2021","journal-title":"Computer Speech & Language"},{"key":"10.1016\/j.neucom.2026.133881_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129315","article-title":"SEDA-EEG: a semi-supervised emotion recognition network with domain adaptation for cross-subject EEG analysis","volume":"622","author":"Tan","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133881_bib0160","series-title":"Proceedings of the 9th International Conference on Multimodal Interfaces","first-page":"94","article-title":"Multimodal cues for addressee-hood in triadic communication with a human information retrieval agent","author":"Terken","year":"2007"},{"key":"10.1016\/j.neucom.2026.133881_bib0165","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2314","article-title":"Multimodal addressee detection in multiparty dialogue systems","author":"Tsai","year":"2015"},{"key":"10.1016\/j.neucom.2026.133881_bib0170","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/TMM.2015.2454332","article-title":"A study of multimodal addressee detection in human\u2013human\u2013computer interaction","volume":"17","author":"Tsai","year":"2015","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.133881_bib0175","first-page":"30","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133881_bib0180","author":"Wagner"},{"key":"10.1016\/j.neucom.2026.133881_bib0185","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"10451","article-title":"A multimodal approach to device-directed speech detection with large language models","author":"Wagner","year":"2024"},{"key":"10.1016\/j.neucom.2026.133881_bib0190","series-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"8377","article-title":"Understanding computer-directed utterances in multi-user dialog systems","author":"Wang","year":"2013"},{"key":"10.1016\/j.neucom.2026.133881_bib0195","series-title":"Proceedings of Interspeech 2020","first-page":"4258","article-title":"Wake word detection with alignment-free lattice-free MMI","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133881_bib0200","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"38","article-title":"Transformers: state-of-the-art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.neucom.2026.133881_bib0205","article-title":"AI-driven Automation of aviation equipment inspection: insights from a complex adaptive systems perspective","volume":"7","author":"Wu","year":"2026","journal-title":"Innovation"},{"key":"10.1016\/j.neucom.2026.133881_bib0210","author":"Xu"},{"key":"10.1016\/j.neucom.2026.133881_bib0215","author":"Yang"},{"key":"10.1016\/j.neucom.2026.133881_bib0220","series-title":"International Conference on Learning Representations","article-title":"Mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226012786?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226012786?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:16:38Z","timestamp":1783152998000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226012786"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":44,"alternative-id":["S0925231226012786"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133881","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal addressee detection in in-vehicle multi-party dialogue: An end-to-end fine-tuning approach based on Qwen2.5-Omni","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133881","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133881"}}