{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:05:54Z","timestamp":1778346354559,"version":"3.51.4"},"reference-count":60,"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\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3428336","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T18:23:17Z","timestamp":1721067797000},"page":"98436-98449","source":"Crossref","is-referenced-by-count":5,"title":["Triangular Region Cut-Mix Augmentation Algorithm-Based Speech Emotion Recognition System With Transfer Learning Approach"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4055-5425","authenticated-orcid":false,"given":"V.","family":"Preethi","sequence":"first","affiliation":[{"name":"Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V.","family":"Elizabeth Jesi","sequence":"additional","affiliation":[{"name":"Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bimodal speech emotion recognition using pre-trained language models","author":"Heusser","year":"2019","journal-title":"arXiv:1912.02610"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app11135796"},{"key":"ref4","volume-title":"mkosaka1\/Speech Emotion Recognition: Using Convolutional Neural Networks in Speech Emotion Recognition on the RAVDESS Audio Dataset","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414635"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2023.11.038"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00111"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1453\/1\/012085"},{"issue":"1","key":"ref11","first-page":"9885","article-title":"A group-theoretic framework for data augmentation","volume":"21","author":"Chen","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2008.4697274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref16","article-title":"AutoAugment: Learning augmentation policies from data","author":"Cubuk","year":"2018","journal-title":"arXiv:1805.09501"},{"key":"ref17","first-page":"6665","article-title":"Fast AutoAugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref19","article-title":"Improving auto-augment via augmentation-wise weight sharing","author":"Tian","year":"2020","journal-title":"arXiv:2009.14737"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref22","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref23","volume-title":"Audio recognition using Mel spectrograms and convolution neural networks","author":"Thornton","year":"2019"},{"issue":"7","key":"ref24","first-page":"1","article-title":"Convolutional deep belief networks on CIFAR-10","volume":"40","author":"Krizhevsky","year":"2010","journal-title":"Unpublished Manuscript"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.643202"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10101163"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3481003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s19183992"},{"issue":"2","key":"ref32","first-page":"116","article-title":"Study of nonlinear properties of vocal tract and its effectiveness in speaker modeling","volume":"43","author":"Kumar","year":"2016","journal-title":"J. Acoust. Soc. India"},{"key":"ref33","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/355161a0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.08.003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/s20226688"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.5111059"},{"key":"ref41","first-page":"1","article-title":"NnAudio: A PyTorch audio processing tool using 1D convolution neural networks","volume-title":"Proc. ISMIR-Late Breaking Demo","author":"Cheuk"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"ref44","article-title":"Shake-shake regularization","author":"Gastaldi","year":"2017","journal-title":"arXiv:1705.07485"},{"key":"ref45","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref46","volume-title":"Ebouteillon\/Freesound Audio Tagging","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/s20185212"},{"key":"ref48","article-title":"Towards interpretable and transferable speech emotion recognition: Latent representation based analysis of features, methods and corpora","author":"Das","year":"2021","journal-title":"arXiv:2105.02055"},{"key":"ref49","article-title":"EmotionX-HSU: Adopting pre-trained BERT for emotion classification","author":"Luo","year":"2019","journal-title":"arXiv:1907.09669"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/app10207385"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3390\/app10010205"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/app13084750"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096789"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/s22165941"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"issue":"11","key":"ref57","first-page":"59","article-title":"Energy conservation using voice recognition","volume":"3","author":"Ali","year":"2013","journal-title":"Ibrahim J. Inf. Eng. Appl."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990405"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10597587.pdf?arnumber=10597587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:34:44Z","timestamp":1721928884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10597587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3428336","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}