{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:12:20Z","timestamp":1784160740670,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3069818","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T20:31:57Z","timestamp":1617136317000},"page":"51231-51241","source":"Crossref","is-referenced-by-count":63,"title":["Autoencoder With Emotion Embedding for Speech Emotion Recognition"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9925-0848","authenticated-orcid":false,"given":"Chenghao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC49280.2020.9152357"},{"key":"ref71","first-page":"1","article-title":"Intermediary fuzzification in speech emotion recognition","author":"assuncao","year":"2020","journal-title":"Proc IEEE Int Conf Fuzzy Syst (FUZZ-IEEE)"},{"key":"ref70","article-title":"Automatic speech emotion recognition using machine learning","author":"kerkeni","year":"2019","journal-title":"Social Media and Machine Learning"},{"key":"ref39","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref38","first-page":"1","article-title":"The INTERSPEECH 2010 paralinguistic challenge","author":"schuller","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2288990"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297715"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553396"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-019-01246-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref36","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv 1703 10135"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-55387-8_2"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref62","first-page":"1","article-title":"Ensemble of SVM trees for multimodal emotion recognition","author":"rozgic","year":"2012","journal-title":"Proc Signal Inf Process Assoc Annu Summit Conf (APSIPA ASC)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2014.6865245"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2886","DOI":"10.21437\/Interspeech.2013-256","article-title":"Using denoising autoencoder for emotion recognition","author":"xia","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"ref66","article-title":"Variational autoencoders for learning latent representations of speech emotion: A preliminary study","author":"latif","year":"2017","journal-title":"arXiv 1712 08708"},{"key":"ref29","article-title":"Multi-channel auto-encoder for speech emotion recognition","author":"zong","year":"2018","journal-title":"arXiv 1810 10662"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref68","article-title":"Multi-task semi-supervised adversarial autoencoding for speech emotion recognition","author":"latif","year":"2019","journal-title":"arXiv 1907 06078"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854514"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIGSYS.2019.8811080"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICETECH.2015.7275003"},{"key":"ref21","first-page":"934","article-title":"Speech emotion recognition using a deep autoencoder","volume":"16","author":"cibau","year":"2013","journal-title":"Anales de la XV Reunion de Procesamiento de la Informacion y Control"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER.2016.7574841"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICOT.2016.8278965"},{"key":"ref26","first-page":"3593","article-title":"Facing realism in spontaneous emotion recognition from speech: Feature enhancement by autoencoder with LSTM neural networks","author":"zhang","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-692"},{"key":"ref50","first-page":"373","article-title":"Expression of emotion and attitude through temporal speech variations","volume":"2","author":"mozziconacci","year":"2000","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.364"},{"key":"ref56","first-page":"1","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google home","author":"kim","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref55","first-page":"1","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref54","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv 1412 5567"},{"key":"ref53","first-page":"1","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume":"117","author":"jaitly","year":"2013","journal-title":"Proc ICML Workshop Deep Learn Audio Speech Lang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-207"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref40","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2018-5"},{"key":"ref15","article-title":"Transfer learning from sound representations for anger detection in speech","author":"ezzeldin a elshaer","year":"2019","journal-title":"arXiv 1902 02120"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2705696"},{"key":"ref17","article-title":"Cross corpus speech emotion classification—An effective transfer learning technique","author":"latif","year":"2018","journal-title":"arXiv 1801 06353"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.79"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367230"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref6","first-page":"6","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ReTIS.2015.7232907"},{"key":"ref8","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"422","article-title":"Emotion recognition through speech using neural network","volume":"5","author":"rawat","year":"2015","journal-title":"Int J"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref42","article-title":"A learned representation for artistic style","author":"dumoulin","year":"2016","journal-title":"arXiv 1610 07629"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.437"},{"key":"ref44","first-page":"464","article-title":"Two at once: Enhancing learning and generalization capacities via IBN-Net","author":"pan","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09389805.pdf?arnumber=9389805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T04:50:50Z","timestamp":1724734250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9389805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3069818","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}