{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T04:46:03Z","timestamp":1763959563296,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/ijcnn.2016.7727297","type":"proceedings-article","created":{"date-parts":[[2016,11,8]],"date-time":"2016-11-08T16:15:56Z","timestamp":1478621756000},"page":"921-928","source":"Crossref","is-referenced-by-count":12,"title":["Learning auditory neural representations for emotion recognition"],"prefix":"10.1109","author":[{"given":"Pablo","family":"Barros","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0120344"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2014.07.005"},{"key":"ref33","first-page":"398","article-title":"Machine Audition: Principles, Algorithms and Systems","author":"haq","year":"2010","journal-title":"Multimodal Emotion Recognition"},{"key":"ref32","first-page":"62","article-title":"Evaluation of unsupervised emotion models to textual affect recognition","author":"kim","year":"2010","journal-title":"Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495984"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIPA.2009.5478635"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854949"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICAPR.2015.7050714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666271"},{"key":"ref40","article-title":"Noise analysis in audio-visual emotion recognition","author":"banda","year":"2011","journal-title":"Proc Int Conf Multimodal Interact (ICMI)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14442-9_52"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref15","article-title":"Automatic musical pattern feature extraction using convolutional neural network","author":"li","year":"2010","journal-title":"Proc Int Conf Data Mining and Applications"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.09.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363421"},{"key":"ref28","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-62604-2.00003-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5430\/air.v4n2p61"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2004.1442120"},{"key":"ref6","first-page":"433","article-title":"Vocal expression of emotion","author":"scherer","year":"2003","journal-title":"Handbook of Affective Sciences"},{"key":"ref29","first-page":"37","article-title":"Exploring hierarchical speech representations with a deep convolutional neural network","author":"hau","year":"0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0376-6357(02)00078-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-735854"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/2813524.2813534","article-title":"Learning combinations of multiple feature representations for music emotion prediction","author":"madsen","year":"2015","journal-title":"Proceedings of the 1st International Workshop on Affect & Sentiment in Multimedia ser ASM '15"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2009.02400.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMI.2002.1167051"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1959.sp006308"},{"key":"ref21","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref42","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"2009","journal-title":"AVSPN"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5121\/ijnlc.2013.2503"},{"key":"ref23","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume":"15","author":"glorot","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11)"},{"key":"ref44","first-page":"543","article-title":"Combining modality specific deep neural networks for emotion recognition in video","author":"kahou","year":"2013","journal-title":"Proceedings of the 15th ACM on International Conference on Multimodal Interaction"},{"key":"ref26","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666274"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"}],"event":{"name":"2016 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2016,7,24]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2016,7,29]]}},"container-title":["2016 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7593175\/7726591\/07727297.pdf?arnumber=7727297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T17:39:19Z","timestamp":1657647559000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7727297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2016.7727297","relation":{},"subject":[],"published":{"date-parts":[[2016,7]]}}}