{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:28:42Z","timestamp":1783528122697,"version":"3.55.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249408","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1904-1909","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing"],"prefix":"10.1109","author":[{"given":"Zehua","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolou","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lantian","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LipNet: Sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2497"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref8","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-432"},{"key":"ref10","article-title":"AlignVSR: Audio-visual cross-modal alignment for visual speech recognition","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3566695"},{"key":"ref12","article-title":"Audio-visual LLM for video understanding","author":"Shu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"A survey on generative AI and LLM for video generation, understanding, and streaming","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-2074-6_36"},{"key":"ref15","article-title":"Improving image captioning descriptiveness by ranking and LLM-based fusion","author":"Bianco","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32628\/cseit25111238"},{"key":"ref17","article-title":"Image captioning using multimodal LLMs","author":"Tiet","year":"2025","journal-title":"LU-CS-EX"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889251"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref20","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi"},{"key":"ref21","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Seed-ASR: Understanding diverse speech and contexts with LLM-based speech recognition","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref27","article-title":"Eliciting the priors of large language models using iterated in-context learning","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2509"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095796"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref33","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Singapore, Singapore","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249408.pdf?arnumber=11249408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:08Z","timestamp":1764399068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249408","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}