{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T19:05:45Z","timestamp":1775329545842,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746022","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3678-3682","source":"Crossref","is-referenced-by-count":20,"title":["Selective Mutual Learning: An Efficient Approach for Single Channel Speech Separation"],"prefix":"10.1109","author":[{"given":"Ha Minh","family":"Tan","sequence":"first","affiliation":[{"name":"National Central University,Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Duc-Quang","family":"Vu","sequence":"additional","affiliation":[{"name":"National Central University,Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Chung-Ting","family":"Lee","sequence":"additional","affiliation":[{"name":"National Central University,Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Yung-Hui","family":"Li","sequence":"additional","affiliation":[{"name":"National Central University,Dept. of Computer Science and Information Engineering,Taiwan"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"National Central University,Dept. of Computer Science and Information Engineering,Taiwan"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099856"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682695"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675335"},{"key":"ref10","first-page":"61","article-title":"Deep clustering and conventional networks for music separation: Stronger together","author":"luo","year":"2017","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i16.17644","article-title":"Tune-in: Training under negative environments with interference for attention networks simulating cocktail party effect","author":"wang","year":"2021","journal-title":"AAAI"},{"key":"ref14","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"ref16","first-page":"46","article-title":"Dual-path rnn: effi-cient long sequence modeling for time-domain single-channel speech separation","author":"luo","year":"2020","journal-title":"ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref29","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"recommendation","year":"2001","journal-title":"ITU-T Rec P 862"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE53005.2021.9621886"},{"key":"ref2","first-page":"7","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2014","journal-title":"IEEE\/ACM TASLP"},{"key":"ref9","first-page":"483","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"williamson","year":"2015","journal-title":"IEEE\/ACM TASLP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078640"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413837"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"10709","DOI":"10.1609\/aaai.v35i12.17280","article-title":"Enhanced audio tagging via multi-to single-modal teacher-student mutual learning","volume":"35","author":"yin","year":"2021","journal-title":"AAAI"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref26","first-page":"626","article-title":"Sdr–half-baked or well done?","author":"roux","year":"2019","journal-title":"ICASSP"},{"key":"ref25","first-page":"632","article-title":"End-to-end automatic speech recognition with deep mutual learning","author":"masumura","year":"2020","journal-title":"APSIPA"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746022.pdf?arnumber=9746022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:14:34Z","timestamp":1700507674000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746022","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}