{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:39:52Z","timestamp":1765391992385,"version":"3.46.0"},"reference-count":43,"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"}],"funder":[{"DOI":"10.13039\/501100003009","name":"Science and Technology Development Fund, Macau, SAR,","doi-asserted-by":"publisher","award":["0004\/2023\/ITP1"],"award-info":[{"award-number":["0004\/2023\/ITP1"]}],"id":[{"id":"10.13039\/501100003009","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3639444","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:49:26Z","timestamp":1764701366000},"page":"205066-205075","source":"Crossref","is-referenced-by-count":0,"title":["A Self-Improving Ensemble Learning Framework for Human Non-Speech Vocalization Classification"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5529-704X","authenticated-orcid":false,"given":"Yonghai","family":"Wang","sequence":"first","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macau SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengshen","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Macau SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4254-9643","authenticated-orcid":false,"given":"Nana","family":"Shan","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Taishan University, Taian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-021-00375-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02405-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-013-0324-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21215"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3133208"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12233"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref9","first-page":"148","article-title":"Vocal Imitation Set v1.1.3: Thousands of vocal imitations of hundreds of sounds from the AudioSet ontology","volume-title":"Proc. Workshop Detection Classification Acoustic Scenes Events","author":"Kim"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746828"},{"key":"ref11","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref12","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3233\/faia200188"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref16","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017","journal-title":"arXiv.1703.01780"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2012.2205597"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2014.2339736"},{"key":"ref20","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"32","author":"Graves"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref22","article-title":"A closer look at weak label learning for audio events","author":"Shah","year":"2018","journal-title":"arXiv.1804.09288"},{"key":"ref23","article-title":"SSAST: Self-supervised audio spectrogram transformer","author":"Gong","year":"2021","journal-title":"arXiv:2110.09784"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2020.3006378"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3120633"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref27","article-title":"Self-training with noisy student improves ImageNet classification","author":"Xie","year":"2019","journal-title":"arXiv:1911.04252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01071"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00608"},{"key":"ref30","article-title":"Uncertainty-aware self-training for text classification with few labels","author":"Mukherjee","year":"2020","journal-title":"arXiv:2006.15315"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11460-011-0126-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref35","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:1905.11946"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"issue":"1","key":"ref37","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","first-page":"1793","article-title":"ASVP-ESD: A dataset and its benchmark for emotion recognition using both speech and non-speech utterances","volume":"8","author":"Landry","year":"2020","journal-title":"Global Sci. J."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1037\/emo0001048"},{"key":"ref40","first-page":"1","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889317"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icasspw62465.2024.10625960"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890672"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11272072.pdf?arnumber=11272072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:33:44Z","timestamp":1765391624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11272072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3639444","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}