{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T18:33:14Z","timestamp":1791052394657,"version":"4.1.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3561359","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T17:52:23Z","timestamp":1744825943000},"page":"67616-67631","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Model Robustness in Noisy Environments: Unlocking Advanced Mono-Channel Speech Enhancement With Cooperative Learning and Transformer Networks"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8048-1330","authenticated-orcid":false,"given":"Wei","family":"Hu","sequence":"first","affiliation":[{"name":"School of Music and Dance, Nanchang Vocational University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Music and Dance, Nanchang Vocational University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53468-3_31"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746902"},{"issue":"3","key":"ref3","first-page":"401","article-title":"Voice activity detection using clustering-based method in spectro-temporal features space","volume":"10","author":"Esfandian","year":"2022","journal-title":"J. AI Data Mining"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.053"},{"key":"ref5","article-title":"Complex spectral mapping with attention based convolution recurrent neural network for speech enhancement","author":"Zhou","year":"2021","journal-title":"arXiv:2104.05267"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2021.000058"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2022.3150322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10781"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3265839"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401787"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3333971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02328-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3102\/00346543050002315"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.32604\/iasc.2023.028090"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/math10193666"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09817-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2361"},{"key":"ref24","article-title":"Self-attention does not need O(n2) memory","author":"Rabe","year":"2021","journal-title":"arXiv:2112.05682"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref27","article-title":"Speech enhancement using a deep mixture of experts","author":"Chazan","year":"2017","journal-title":"arXiv:1703.09302"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109228"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3355393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref31","article-title":"THCHS-30: A free Chinese speech corpus","author":"Wang","year":"2015","journal-title":"arXiv:1512.01882"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-11903-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683741"},{"key":"ref37","first-page":"1","article-title":"On some features of log-spectral distortion as speech quality measure","volume":"1","author":"Prodeus","year":"2016","journal-title":"Autom. Softw. Dev. Eng. J."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12182"},{"key":"ref39","article-title":"TFCN: Temporal-frequential convolutional network for single-channel speech enhancement","author":"Jia","year":"2022","journal-title":"arXiv:2201.00480"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref41","article-title":"Understanding AdamW through proximal methods and scale-freeness","author":"Zhuang","year":"2022","journal-title":"arXiv:2202.00089"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3102\/1076998619872761"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.918623"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979982"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3128374"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36702-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3236242"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE54056.2021.9721524"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832336"},{"key":"ref52","article-title":"VINP: Variational Bayesian inference with neural speech prior for joint ASR-effective speech dereverberation and blind RIR identification","author":"Wang","year":"2025","journal-title":"arXiv:2502.07205"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3294247"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP48669.2020.9321080"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3245-6_5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCS.2006.301514"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10966882.pdf?arnumber=10966882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:07:07Z","timestamp":1745514427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10966882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3561359","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}