{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T22:08:49Z","timestamp":1772489329043,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100018623","name":"Yiwu City Science and Technology Program","doi-asserted-by":"publisher","award":["24-3-160"],"award-info":[{"award-number":["24-3-160"]}],"id":[{"id":"10.13039\/501100018623","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jinhua City Science and Technology Program","award":["2024-4-265"],"award-info":[{"award-number":["2024-4-265"]}]},{"name":"Jinhua Key Laboratory of Robot Intelligent Welding Technology"},{"name":"Jinhua Public Welfare Technology Application Research Project, in 2024"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3667399","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:48:59Z","timestamp":1771879739000},"page":"29706-29728","source":"Crossref","is-referenced-by-count":0,"title":["Improving Contextual Biasing in Chinese ASR via Multimodal Large Language Models"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1688-1815","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"first","affiliation":[{"name":"Yiwu Industrial and Commercial College, Yiwu, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuxia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang Commerce and Trade School, Jinhua Open University, Jinhua, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1414-9848","authenticated-orcid":false,"given":"Chung-Che","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7319-9095","authenticated-orcid":false,"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.682982"},{"key":"ref2","volume-title":"Wired for Speech: How Voice Activates and Advances the Human-Computer Relationship","author":"Nass","year":"2005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1213-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3192199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref10","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref11","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv: 2312.11805"},{"key":"ref12","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref13","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref14","article-title":"A survey on speech large language models","author":"Peng","year":"2024","journal-title":"arXiv:2410.18908"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3424260"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chorowski"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref23","volume-title":"A Grammar of Spoken Chinese","author":"Chao","year":"1968"},{"key":"ref24","volume-title":"The Prosody of Mandarin Chinese","volume":"118","author":"Shen","year":"1990"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981742"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700816"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-402"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref32","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref34","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-564"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44195-0_32"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.787"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448204"},{"key":"ref40","article-title":"Phi-4-Mini technical report: Compact yet powerful multimodal language models via mixture-of-LoRAs","volume-title":"arXiv:2503.01743","author":"Abouelenin","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448264"},{"key":"ref43","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888744"},{"key":"ref46","article-title":"On using monolingual corpora in neural machine translation","author":"Gulcehre","year":"2015","journal-title":"arXiv:1503.03535"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832281"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-326"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356098"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10991"},{"key":"ref51","article-title":"A prompt pattern catalog to enhance prompt engineering with ChatGPT","author":"White","year":"2023","journal-title":"arXiv:2302.11382"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445918"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref56","article-title":"Gemma 3 technical report","volume-title":"arXiv:2503.19786","author":"Kamath","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11408189.pdf?arnumber=11408189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:57:13Z","timestamp":1772485033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3667399","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}