{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:20:19Z","timestamp":1776093619553,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01MH122367-01"],"award-info":[{"award-number":["1R01MH122367-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3340603","type":"journal-article","created":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T19:46:16Z","timestamp":1701978376000},"page":"917-929","source":"Crossref","is-referenced-by-count":22,"title":["Selective Acoustic Feature Enhancement for Speech Emotion Recognition With Noisy Speech"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1175-1577","authenticated-orcid":false,"given":"Seong-Gyun","family":"Leem","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4405-9031","authenticated-orcid":false,"given":"Daniel","family":"Fulford","sequence":"additional","affiliation":[{"name":"Occupational Therapy and Psychological and Brain Sciences, Boston University, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6613-8668","authenticated-orcid":false,"given":"Jukka-Pekka","family":"Onnela","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Harvard University, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0446-4000","authenticated-orcid":false,"given":"David","family":"Gard","sequence":"additional","affiliation":[{"name":"Department of Psychology, San Francisco State University, San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4075-4072","authenticated-orcid":false,"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/e526112012-054"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3105939"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2478\/aoa-2013-0054"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-998"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747705"},{"key":"ref8","first-page":"2031","article-title":"Metric GAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fu","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2946.001.0001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.2025775"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(91)90027-Q"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/78.212753"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ECMSM.2017.7945915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10131586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref29","article-title":"Curriculum audiovisual learning","author":"Hu","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053581"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-802806-3.00008-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470363"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096138"},{"key":"ref38","article-title":"Dynamic layer customization for noise robust speech emotion recognition in heterogeneous condition training","author":"Wilf","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597437"},{"key":"ref40","first-page":"1","article-title":"Domain separation networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bousmalis","year":"2016"},{"key":"ref41","first-page":"2045","article-title":"Speech emotion recognition using non-linear Teager energy based features in noisy environments","volume-title":"Proc. Eur. Signal Process. Conf.","author":"Georgogiannis","year":"2012"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.21437\/SpeechProsody.2006-150","article-title":"Emotion recognition in the noise applying large acoustic feature sets","volume-title":"Proc. Conf. ISCA Speech Prosody","author":"Schuller","year":"2006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553202"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-01571-2_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-60"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1494"},{"key":"ref50","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-018-0798-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref55","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094301"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10347397.pdf?arnumber=10347397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T15:48:37Z","timestamp":1730821717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10347397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3340603","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}