{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:27:12Z","timestamp":1781537232502,"version":"3.54.5"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DFG, German Research Foundation","award":["460884988"],"award-info":[{"award-number":["460884988"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006290013"],"award-info":[{"award-number":["202006290013"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2023YFC2506804"],"award-info":[{"award-number":["2023YFC2506804"]}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2021ZD0201900"],"award-info":[{"award-number":["2021ZD0201900"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272044"],"award-info":[{"award-number":["62272044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Fellow Program from the Beijing Institute of Technology, China"},{"name":"National Key Research and Development Project","award":["2020AAA0106200"],"award-info":[{"award-number":["2020AAA0106200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936005"],"award-info":[{"award-number":["61936005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001038"],"award-info":[{"award-number":["62001038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/taffc.2024.3475729","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:44:52Z","timestamp":1728323092000},"page":"861-874","source":"Crossref","is-referenced-by-count":6,"title":["STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2417-1328","authenticated-orcid":false,"given":"Yi","family":"Chang","sequence":"first","affiliation":[{"name":"GLAM – The Group on Language, Audio, & Music, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0707-5016","authenticated-orcid":false,"given":"Zhao","family":"Ren","sequence":"additional","affiliation":[{"name":"University of Bremen, Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-0561","authenticated-orcid":false,"given":"Zixing","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jing","sequence":"additional","affiliation":[{"name":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1918-6453","authenticated-orcid":false,"given":"Kun","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2348-7515","authenticated-orcid":false,"given":"Xi","family":"Shao","sequence":"additional","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3514-5413","authenticated-orcid":false,"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Medical Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9809-7028","authenticated-orcid":false,"given":"Tanja","family":"Schultz","sequence":"additional","affiliation":[{"name":"University of Bremen, Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM – The Group on Language, Audio, & Music, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2020.3006860"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925464"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app122110951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094895"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282092"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref13","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00930"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560660"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413467"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tdsc.2022.3189397"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796934"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17663"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363271"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1869"},{"key":"ref31","article-title":"Robust federated learning against adversarial attacks for speech emotion recognition","author":"Chang","year":"2022"},{"key":"ref32","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155483"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199"},{"key":"ref35","first-page":"14963","article-title":"Transferable sparse adversarial attack","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"He"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682896"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017462"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414866"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446616"},{"key":"ref46","first-page":"1","article-title":"Delving into transferable adversarial examples and black-box attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_3"},{"key":"ref50","first-page":"745","article-title":"Singing voice separation with deep U-net convolutional networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Jansson"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553571"},{"key":"ref56","first-page":"1","article-title":"Audio super resolution using neural networks","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Kuleshov"},{"key":"ref57","first-page":"334","article-title":"Wave-u-Net: A multi-scale neural network for end-to-end audio source separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Stoller"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20637"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423348"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-019-09450-y"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3169091"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.10.015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384733"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054087"},{"key":"ref69","first-page":"1947","article-title":"Speech emotion recognition based on attention weight correction using word-level confidence measure","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Pepino"},{"key":"ref70","first-page":"1","article-title":"Mitigating adversarial effects through randomization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie"},{"key":"ref71","first-page":"1","article-title":"Ensemble adversarial training: Attacks and defenses","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tram\u00e8r"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23198"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3294394"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11018643\/10706816.pdf?arnumber=10706816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:01:47Z","timestamp":1748887307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":73,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3475729","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}