{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:18:23Z","timestamp":1753600703030,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096565","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["A Multi-Scale Feature Aggregation Based Lightweight Network for Audio-Visual Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Haitao","family":"Xu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Liangfa","family":"Wei","sequence":"additional","affiliation":[{"name":"Machine Learning Group,Ethereal Audio Lab,Shenzhen,China"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Jianming","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Yannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Machine Learning Group,Ethereal Audio Lab,Shenzhen,China"}]},{"given":"Tian","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Xin","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1201\/b14529"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASLP.2014.2364452"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TASLP.2014.2352935"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP40776.2020.9053033"},{"key":"ref5","volume-title":"Speechreading by humans and machines: models, systems, and applications","volume":"150","author":"Stork","year":"2013"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TASLP.2021.3066303"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/interspeech.2018-1955"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3197517.3201357"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TASLP.2022.3153265"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2018.8462527"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ISCAS51556.2021.9401772"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP.2019.8682061"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/34.927464"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP43922.2022.9747888"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2018-1400"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCE.2018.8326315"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2020-1104"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/interspeech.2020-1397"},{"year":"2020","author":"Tao","journal-title":"Hierarchical multiscale attention for semantic segmentation","key":"ref19"},{"year":"2018","author":"Wang","journal-title":"Csi-net: Unified human body characterization and pose recognition","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2020-1065"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref23","first-page":"6570","article-title":"Robust audiovisual speech recognition using bimodal DFSMN with multicondition training and dropout regularization","author":"Zhang","year":"2019","journal-title":"ICASSP"},{"key":"ref24","first-page":"638","article-title":"Attentive fusion enhanced audio-visual encoding for transformer based robust speech recognition","author":"Wei","year":"2020","journal-title":"APSIPA-ASC"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1121\/1.2229005"},{"key":"ref26","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","volume-title":"Proceedings of Int. Society for Music Information Retrieval","author":"Fonseca"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/TASL.2010.2041110"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICASSP.2001.941023"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICASSP.2010.5495701"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ICASSP39728.2021.9414053"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.21437\/Interspeech.2022-10041"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096565.pdf?arnumber=10096565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:51:32Z","timestamp":1709247092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096565","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}