{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:17:17Z","timestamp":1768342637092,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/asru.2013.6707732","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:07:23Z","timestamp":1389366443000},"page":"216-221","source":"Crossref","is-referenced-by-count":68,"title":["Emotion recognition from spontaneous speech using Hidden Markov models with deep belief networks"],"prefix":"10.1109","author":[{"given":"Duc","family":"Le","sequence":"first","affiliation":[]},{"given":"Emily Mower","family":"Provost","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2129510"},{"key":"33","first-page":"22252228","article-title":"Using neutral speech models for emotional speech analysis","author":"busso","year":"2007","journal-title":"Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech"},{"key":"15","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc of the 26th Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"14","first-page":"1055","article-title":"Deep networks for robust visual recognition","author":"tang","year":"2010","journal-title":"Proc 24th Annual International Conference on Machine Learning (ICML'07)"},{"key":"11","author":"hinton","year":"2010","journal-title":"A practical guide to training restricted Boltzmann Machines"},{"key":"12","article-title":"Sparse deep belief net model for visual area v2","author":"lee","year":"2008","journal-title":"Proc of the 22nd Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"21","article-title":"Likability classification - A not so deep neural network approach","author":"brueckner","year":"2012","journal-title":"12th Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082328"},{"key":"22","article-title":"Deep learning for robust feature generation in audio-visual emotion recognition","author":"kim","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"23","article-title":"The interspeech 2012 speaker trait challenge","author":"schuller","year":"2012","journal-title":"10th Annual Conference of the International Speech Communication Association InterSpeech"},{"key":"24","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: A CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference"},{"key":"25","first-page":"801","article-title":"Incremental acoustic valence recognition: An inter-corpus perspective on features, matching, and performance in a gating paradigm","author":"schuller","year":"2010","journal-title":"Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947464"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946960"},{"key":"28","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"29","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"opitz","year":"1999","journal-title":"Journal of Artificial Intelligence Research"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639126"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"1","author":"steidl","year":"2009","journal-title":"Automatic Classification of Emotion-Related User States in Spontaneous Children's Speech"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1004813"},{"key":"6","first-page":"348","article-title":"Brno university of technology system for interspeech 2009 emotion challenge","author":"kockmann","year":"2009","journal-title":"Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech"},{"key":"5","first-page":"312","article-title":"The interspeech 2009 emotion challenge","author":"schuller","year":"2009","journal-title":"Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2011.941079"},{"key":"4","article-title":"Combining ranking and classification to improve emotion recognition in spontaneous speech","author":"cao","year":"2012","journal-title":"12th Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2255278"}],"event":{"name":"2013 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","location":"Olomouc, Czech Republic","start":{"date-parts":[[2013,12,8]]},"end":{"date-parts":[[2013,12,12]]}},"container-title":["2013 IEEE Workshop on Automatic Speech Recognition and Understanding"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6695806\/6707689\/06707732.pdf?arnumber=6707732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,13]],"date-time":"2020-08-13T21:40:16Z","timestamp":1597354816000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6707732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru.2013.6707732","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}