{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:36:38Z","timestamp":1776886598036,"version":"3.51.2"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001352","name":"National University of Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001352","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["R-252-000-A56-114"],"award-info":[{"award-number":["R-252-000-A56-114"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2341003"],"award-info":[{"award-number":["T2341003"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023]]},"DOI":"10.1109\/taslp.2023.3317568","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:34:24Z","timestamp":1695666864000},"page":"3746-3759","source":"Crossref","is-referenced-by-count":5,"title":["Disentangled Adversarial Domain Adaptation for Phonation Mode Detection in Singing and Speech"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7330-801X","authenticated-orcid":false,"given":"Yixin","family":"Wang","sequence":"first","affiliation":[{"name":"Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-7035","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0637-8664","authenticated-orcid":false,"given":"Xiangming","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8826-0362","authenticated-orcid":false,"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[{"name":"MOE KLINNS Laboratory Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-1260","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102952"},{"key":"ref57","first-page":"1","article-title":"The truth of the f-measure","volume":"1","author":"sasaki","year":"2007","journal-title":"Teach Tutor Mater"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.02.004"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3130975"},{"key":"ref59","article-title":"Adam: A. method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref14","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"ref53","first-page":"531","article-title":"Mutual information neural estimation","author":"belghazi","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747603"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-76"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3004760"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054248"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3182271"},{"key":"ref19","author":"abercrombie","year":"1967","journal-title":"Elements of General Phonetics"},{"key":"ref18","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2404035"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref46","first-page":"1647","article-title":"Conditional adversarial domain adaptation","author":"long","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2866707"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095669"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref44","first-page":"1015","article-title":"Automatic classification of phonation types in spontaneous speech: Towards a new workflow for the characterization of speakers voice quality","author":"chanclu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1399"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3022237"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4906836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00082-1"},{"key":"ref9","article-title":"Analysis and automatic classification of phonation modes in singing","author":"yesiler","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1135"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2013.821496"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2014.11.002"},{"key":"ref5","first-page":"384","article-title":"Analysis and detection of singing techniques in repertoires of J-pop solo singers","author":"yamamoto","year":"0","journal-title":"Proc 23rd Int Soc Music Inf Retrieval Conf"},{"key":"ref40","first-page":"26","article-title":"On modeling glottal source information for phonation assessment in parkinson's disease","author":"v\u00e1squez-correa","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.02.007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0041-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2759002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.1490365"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2015.03.014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.402044"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2245653"},{"key":"ref2","first-page":"69","article-title":"Vocal fold vibration patterns and phonatory modes","volume":"35","author":"sundberg","year":"1994","journal-title":"STL-QPSR"},{"key":"ref1","author":"ladefoged","year":"1971","journal-title":"Preliminaries to Linguistic Phonetics"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2498"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2502"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.2001.0147"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1159\/000266415"},{"key":"ref26","first-page":"37","article-title":"Laryngeal Voice Quality Classification, Ser. Cambridge Studies” in Linguistics.","author":"esling","year":"2019"},{"key":"ref25","author":"sundberg","year":"1987","journal-title":"The Science of the Singing Voice"},{"key":"ref20","first-page":"1","article-title":"The phonetic description of voice quality","volume":"31","author":"laver","year":"1980","journal-title":"Cambridge Studies in Linguistics London"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4896462"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.424266"},{"key":"ref65","first-page":"367","article-title":"Mir_eval: A transparent implementation of common MIR metrics","author":"raffel","year":"0","journal-title":"Proc 15th Int Soc Music Inf Retrieval Conf"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2006.12.008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2003.05.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906726"},{"key":"ref60","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","first-page":"454","article-title":"PDAugment: Data augmentation by pitch and duration adjustments for automatic lyrics transcription","author":"zhang","year":"0","journal-title":"Proc 23rd Int Soc Music Inf Retrieval Conf"},{"key":"ref61","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10262362.pdf?arnumber=10262362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:37:52Z","timestamp":1699904272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3317568","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}