{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T20:18:43Z","timestamp":1791058723053,"version":"4.1.0"},"reference-count":27,"publisher":"IEEE","license":[{"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/icassp39728.2021.9414542","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"641-645","source":"Crossref","is-referenced-by-count":38,"title":["LSSED: A Large-Scale Dataset and Benchmark for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Weiquan","family":"Fan","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangmin","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofen","family":"Xing","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyan","family":"Huang","sequence":"additional","affiliation":[{"name":"UBTECH Robotics Corp,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref12","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":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053561"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2537926"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3006331"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202008.0645.v1","article-title":"Recognizing more emotions with less data using self-supervised transfer learning","author":"boigne","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.06.066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref3","article-title":"A database of german emotional speech","author":"burkhardt","year":"2005","journal-title":"Ninth European Conference on Speech Communication and Technology"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"},{"key":"ref8","article-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations","author":"poria","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"ref2","article-title":"you stupid tin box”-children interacting with the aibo robot: A cross-linguistic emotional speech corpus","author":"batliner","year":"2004","journal-title":"LREC"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.06.004"},{"key":"ref1","first-page":"ii-1","article-title":"Hidden markov model-based speech emotion recognition","volume":"2","author":"schuller","year":"2003","journal-title":"2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003 Proceedings (ICASSP'03)"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref22","article-title":"Pyramidal convolution: Rethinking convolutional neural networks for visual recognition","author":"duta","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053727"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659587"},{"key":"ref26","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","author":"gratch","year":"2014","journal-title":"LREC"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054087"}],"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\/09414542.pdf?arnumber=9414542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:19Z","timestamp":1659485899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414542","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}