{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:07Z","timestamp":1730199307075,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687861","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"114-121","source":"Crossref","is-referenced-by-count":1,"title":["Robust Speech-Age Estimation Using Local Maximum Mean Discrepancy Under Mismatched Recording Conditions"],"prefix":"10.1109","author":[{"given":"Naohiro","family":"Tawara","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Kitagishi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hosana","family":"Kamiyama","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Ijima","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc ASRU"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17313-4_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054134"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.41"},{"journal-title":"Room impulse response and noise database","year":"0","key":"ref35"},{"key":"ref34","article-title":"MU-SAN: A Music, Speech, and Noise Corpus","author":"snyder","year":"2015","journal-title":"ArXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682852"},{"key":"ref12","first-page":"513","article-title":"A kernel method for the two-sample-problem","volume":"19","author":"gretton","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2988928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2104955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref16","first-page":"137","article-title":"Automatic estimation of one's age with his\/her speech based upon acoustic modeling techniques of speakers","volume":"1","author":"minematsu","year":"0","journal-title":"Proc ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00554"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.86"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.107"},{"key":"ref4","article-title":"Joint gender and age estimation based on speech signals using x-vectors and transfer learning","author":"kwasny","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.274"},{"key":"ref3","first-page":"6580","article-title":"A deep neural network based end to end model for joint height and age estimation from short duration speech","author":"vaidyanathan","year":"0","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414272"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682488"},{"key":"ref5","first-page":"319","article-title":"Speaker age estimation using age-dependent insensitive loss","author":"kitagishi","year":"2020","journal-title":"Proc APSIPA"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2816163"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.05.037"},{"key":"ref9","first-page":"260","article-title":"Unsupervised domain adaptation for i-vector speaker recognition","volume":"8","author":"garcia-romero","year":"0","journal-title":"Proc Odyssey The Speaker and Language Recognition Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/99"},{"key":"ref22","first-page":"2096","article-title":"(1)","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","first-page":"909","article-title":"Speaker age estimation by multi-task learning of gender estimation","author":"yuki","year":"0","journal-title":"Reports of the autumn meeting the Acoustical Society of Japan (in Japanese)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref23","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"tzeng","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref26","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc ICML"},{"key":"ref25","article-title":"Central moment discrepancy (CMD) for domain-invariant representation learning","author":"zellinger","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687861.pdf?arnumber=9687861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:26Z","timestamp":1652201906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687861","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}