{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:33Z","timestamp":1730297193512,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023124","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"1037-1044","source":"Crossref","is-referenced-by-count":1,"title":["SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning"],"prefix":"10.1109","author":[{"given":"Zuheng","family":"Kang","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqing","family":"Peng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref12","first-page":"1","article-title":"End-to-end speaker age and height estimation using attention mechanism and triplet loss","author":"kaushik","year":"0","journal-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(96)80019-1"},{"key":"ref15","first-page":"35","article-title":"Age classification: Comparison of human vs machine performance in prompted and spontaneous speech","volume":"2021","author":"burkhardt","year":"2021","journal-title":"Studientexte Zur Sprachkommunikation Elektronische Sprachsignalverarbeitung"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.04.009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref11","first-page":"234","article-title":"Explaining predictions of the x-vector speaker age and gender classifier","author":"kwasny","year":"0","journal-title":"International Conference on De-pendability and Complex Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.401663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2015"},{"key":"ref32","article-title":"The many-to-many mapping between the concordance correlation co-efficient and the mean square error","author":"pandit","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11456"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1996"},{"key":"ref17","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414642"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472637"},{"key":"ref19","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume":"32","author":"hendrycks","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_23"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.764"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00294-w"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-567"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-8272-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2545658"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref27","first-page":"255","article-title":"A concordance correlation coefficient to evaluate reproducibility","author":"lawrence","year":"1989","journal-title":"Biometrics"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2net: A new multi-scale backbone architecture","volume":"43","author":"gao","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683397"},{"key":"ref7","first-page":"319","article-title":"Speaker age estimation using age-dependent insensitive loss","author":"kitagishi","year":"0","journal-title":"2020 Asia-Pacific Signal and Information Pro-cessing Association Annual Summit and Conference (AP-SIPAASC)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.05.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25789-1_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746378"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1557"},{"key":"ref5","article-title":"Phone duration modeling for speaker age estimation in children","author":"shivakumar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023124.pdf?arnumber=10023124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:45Z","timestamp":1676912925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023124","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}