{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:39:58Z","timestamp":1778168398804,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Fonds de Recherche du Quebec - Nature et Technologies"},{"name":"Conselho Nacional de Desenvolvimento Cientifico e Tecnoligico"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2021,1,1]]},"DOI":"10.1109\/taffc.2018.2858255","type":"journal-article","created":{"date-parts":[[2018,7,23]],"date-time":"2018-07-23T22:30:43Z","timestamp":1532385043000},"page":"177-188","source":"Crossref","is-referenced-by-count":50,"title":["Feature Pooling of Modulation Spectrum Features for Improved Speech Emotion Recognition in the Wild"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-5116","authenticated-orcid":false,"given":"Anderson R.","family":"Avila","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5026-5416","authenticated-orcid":false,"given":"Zahid","family":"Akhtar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3934-3943","authenticated-orcid":false,"given":"Joao F.","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0110-2346","authenticated-orcid":false,"given":"Douglas","family":"OShaughnessy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5739-2514","authenticated-orcid":false,"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume":"28","author":"pascanu","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref38","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637842"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5772\/4754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4018\/jse.2010101605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/2.485891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref34","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"2000","journal-title":"Proc Autom Speech Recognit Challenges New Millenium ISCA Tutorial Res Workshop (ITRW)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009578"},{"key":"ref40","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv preprint arXiv 1308 0850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PCTHEALTH.2008.4571041"},{"key":"ref12","article-title":"Recent developments and results of ASC-inclusion: An integrated internet-based environment for social inclusion of children with autism spectrum conditions","author":"schuller","year":"2015","journal-title":"Proc 3rd Int Workshop Intell Digital Games Empowerment Inclusion 20th ACM Int Conf Intell User Interfaces"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","article-title":"Survey on speech emotion recognition: Features, classification schemes, and databases","volume":"44","author":"mohamed","year":"2011","journal-title":"Pattern Recognit"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-998"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967306"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0047279"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.1288665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139046855.020"},{"key":"ref27","article-title":"An efficient implementation of the patterson-holdsworth auditory filter bank","volume":"35","author":"slaney","year":"0","journal-title":"Apple Comput Perception Group Cupertino CA 1993"},{"key":"ref3","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2009.2024697"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(03)00052-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5772\/4754"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367261"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/838790"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1132"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"255","DOI":"10.2307\/2532051","article-title":"A concordance correlation coefficient to evaluate reproducibility","volume":"45","author":"lawrence","year":"1989","journal-title":"Biometrics"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"312","DOI":"10.21437\/Interspeech.2009-103","article-title":"The interspeech 2009 emotion challenge","volume":"2009","author":"schuller","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883177"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/838790"},{"key":"ref42","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv preprint arXiv 1207 0580"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2023679"},{"key":"ref41","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref44","first-page":"281","article-title":"Support vector method for function approximation, regression estimation, and signal processing","author":"vapnik","year":"1997","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602930"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967306"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9364368\/08417917.pdf?arnumber=8417917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,28]],"date-time":"2022-08-28T02:46:01Z","timestamp":1661654761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8417917\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,1]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2018.2858255","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,1]]}}}