{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:55:59Z","timestamp":1753602959806,"version":"3.37.3"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100005125","name":"EMI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005125","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095892","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Towards Learning Emotion Information from Short Segments of Speech"],"prefix":"10.1109","author":[{"given":"Tilak","family":"Purohit","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarthak","family":"Yadav","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Vlasenko","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Pavankumar","family":"Dubagunta","sequence":"additional","affiliation":[{"name":"Uniphore Software Systems,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Magimai.-Doss","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-488"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"article-title":"On the impact of word error rate on acoustic-linguistic speech emotion recognition: An update for the deep learning era","year":"2021","author":"amiriparian","key":"ref34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2168"},{"key":"ref37","article-title":"Gradient-based spectral visualization of CNNs using raw waveforms","author":"muckenhirn","year":"2018","journal-title":"Tech Rep IDIAP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2020.00013"},{"key":"ref36","article-title":"Striving for simplicity: The all convolutional net","author":"springenberg","year":"2015","journal-title":"ICLR (Workshop)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462165"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.01.004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683498"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1240"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-612"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.136"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-104"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551792"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478582"},{"key":"ref24","article-title":"Ensemble of SVM trees for multimodal emotion recognition","author":"rozgi?","year":"2012","journal-title":"Proceedings Asia Pacific Signal and Information processing Association Annual Summit and Conference"},{"key":"ref23","article-title":"A multi-task learning framework for emotion recognition using 2D continuous space","author":"xia","year":"2015","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref26","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"openSMILE – The Munich Versatile and Fast Open-Source Audio Feature Extractor","author":"eyben","year":"2010","journal-title":"Proc of ACM Multimedia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554812"},{"key":"ref22","article-title":"Improving speech emotion recognition with unsupervised representation learning on unla-beled speech","author":"neumann","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-670"},{"key":"ref27","article-title":"openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit","author":"schmitt","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1124"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-692"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9125-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095892.pdf?arnumber=10095892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:56:59Z","timestamp":1700506619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095892","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}