{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:25Z","timestamp":1763192005591,"version":"3.45.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229167","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["PromptLTS: Text-Guided Controllable Speech Generation from Lip Movements"],"prefix":"10.1109","author":[{"given":"Wenlong","family":"Xu","sequence":"first","affiliation":[{"name":"Zhejiang University,School of Software Technology,Ningbo,China"}]},{"given":"Xuelin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Software Technology,Ningbo,China"}]},{"given":"Yanliang","family":"Tan","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Software Technology,Ningbo,China"}]},{"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Software Technology,Ningbo,China"}]},{"given":"Junlin","family":"An","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Software Technology,Ningbo,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"133 328","article-title":"Classifier-guided gradient modulation for enhanced multimodal learning","volume":"37","author":"Guo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"article-title":"Smoothing the shift: Towards stable test-time adaptation under complex multimodal noises","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Guo","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"Ren","key":"ref10"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref11"},{"article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","year":"2023","author":"Jiang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-645"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-866"},{"key":"ref16","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"article-title":"Prompttts 2: Describing and generating voices with text prompt","year":"2023","author":"Leng","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1337"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162495"},{"key":"ref23","first-page":"2758","article-title":"Lip to speech synthesis with visual context attentional gan","volume":"34","author":"Kim","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19966"},{"key":"ref26","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref28","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref30","first-page":"10 970","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref34"},{"article-title":"Lipnet: End-to-end sentence-level lipreading","year":"2016","author":"Assael","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"article-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"ref38"},{"key":"ref39","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"16 582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume":"34","author":"Hu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10770"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-492"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02056"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref45"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229167.pdf?arnumber=11229167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:10Z","timestamp":1763191810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229167","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}