{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:04:33Z","timestamp":1772553873437,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414035","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7263-7267","source":"Crossref","is-referenced-by-count":14,"title":["Deepemocluster: a Semi-Supervised Framework for Latent Cluster Representation of Speech Emotions"],"prefix":"10.1109","author":[{"given":"Wei-Cheng","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kusha","family":"Sridhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2636"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: Audio and music signal analysis in python","author":"mcfee","year":"2015","journal-title":"Python in Science Conference (SciPy 2015)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref11","article-title":"Improving cross-corpus speech emotion recognition with adversarial discriminative domain generalization (ADDoG)","author":"gideon","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2293"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"The European Conference on Computer Vision (ECCV 2018)"},{"key":"ref17","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"238","DOI":"10.21437\/Interspeech.2014-60","article-title":"Building a naturalistic emotional speech corpus by retrieving expressive behaviors from existing speech corpora","author":"mariooryad","year":"2014","journal-title":"2014 IEEE INTERSPEECH"},{"key":"ref4","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS 2012)"},{"key":"ref27","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","author":"rasmusi","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS 2015)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"338","DOI":"10.21437\/Interspeech.2014-80","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"2014 IEEE INTERSPEECH"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1670","DOI":"10.21437\/Interspeech.2008-463","article-title":"Scripted dialogs versus improvisation: Lessons learned about emotional elicitation techniques from the IEMOCAP database","author":"busso","year":"2008","journal-title":"Interspeech 2008-Eurospeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195387643.003.0008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/sce.20203"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.006"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.21437\/Interspeech.2017-200","article-title":"Efficient emotion recognition from speech using deep learning on spectrograms","author":"satt","year":"2017","journal-title":"in INTERSPEECH 2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2759338"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414035.pdf?arnumber=9414035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:46Z","timestamp":1672129906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414035","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}