{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:38:29Z","timestamp":1753601909104,"version":"3.37.3"},"reference-count":31,"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095716","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":6,"title":["A Lightweight Fourier Convolutional Attention Encoder for Multi-Channel Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Siyu","family":"Sun","sequence":"first","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Jian","family":"Jin","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Zhe","family":"Han","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Xianjun","family":"Xia","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Yijian","family":"Xiao","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Piao","family":"Ding","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Shenyi","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance,RTC Lab,China"}]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[{"name":"University of Western Australia,School of Engineering, Electrical, Electronic and Computer Engineering,Perth,Australia"}]},{"given":"Haijian","family":"Zhang","sequence":"additional","affiliation":[{"name":"WuHan University,School of Electronic Information,WuHan,China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3","article-title":"CBAM: Convolutional Block Attention Module","author":"woo","year":"2018","journal-title":"ECC 2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747888"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref11","first-page":"4479","article-title":"Fast fourier convolution","volume":"33","author":"chi","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref16","first-page":"4794","article-title":"Deep feedforward sequential memory networks for speech synthesis","author":"bi","year":"2018","journal-title":"IEEE ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462155"},{"article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","year":"2016","author":"veaux","key":"ref24"},{"article-title":"Aishell-3: A multi-speaker Mandarin TTS corpus and the baselines","year":"2020","author":"shi","key":"ref23"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-603"},{"key":"ref22","first-page":"1","article-title":"AISHELL1: An open-source Mandarin speech corpus and a speech recognition baseline","author":"bu","year":"2017","journal-title":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (OCOCOSDA)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688126"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref8","first-page":"1862","article-title":"Real-time multichannel speech enhancement based on neural network masking with attention model","author":"xue","year":"2021","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1457"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref6","first-page":"9211","article-title":"The PCGAIID system for L3DAS22 Challenge: MIMO and MISO convolutional recurrent network for multi channel speech enhancement and speech recognition","author":"li","year":"2022","journal-title":"IEEE ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683385"}],"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\/10095716.pdf?arnumber=10095716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:04Z","timestamp":1700506864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095716","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}