{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T22:33:26Z","timestamp":1789079606019,"version":"build-2803163510"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/taffc.2022.3188223","type":"journal-article","created":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T20:04:16Z","timestamp":1656965056000},"page":"1892-1905","source":"Crossref","is-referenced-by-count":19,"title":["Quality-Aware Bag of Modulation Spectrum Features for Robust Speech Emotion Recognition"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7191-4251","authenticated-orcid":false,"given":"Shruti Rajendra","family":"Kshirsagar","sequence":"first","affiliation":[{"name":"Telecommunications, INRS Energy Materials and Telecommunications Research Centre Montreal, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiago Henrik","family":"Falk","sequence":"additional","affiliation":[{"name":"Telecommunications, INRS Energy Materials and Telecommunications Research Centre Montreal, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Bag-of-audio-words based on autoencoder codebook for continuous emotion prediction","author":"senoussaoui","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461963"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357692"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266313"},{"key":"ref34","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-484"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953217"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.14786\/flr.v6i3.371"},{"key":"ref63","first-page":"216","article-title":"Evaluation of the reverberation decay quality in rooms using the autocorrelation function and the cepstrum analysis","volume":"80","author":"?rodecki","year":"1994","journal-title":"Acustica United with Acta Acustica"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-022-02156-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref2","first-page":"137","article-title":"Psychological models of emotion","volume":"137","author":"scherer","year":"2000","journal-title":"The Neuropsychology of Emotion"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886310"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-336","article-title":"High-level feature representation using RNN for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"Dawn of the transformer era in speech emotion recognition: Closing the valence gap","author":"wagner","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2636"},{"key":"ref24","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1238"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2018-5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/PRML52754.2021.9520692"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133946"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3149"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133952"},{"key":"ref53","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.70.3.614"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref40","article-title":"Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video","author":"knyazev","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-801"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2858255"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0057-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1124"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2023679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.97.3.412"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref9","first-page":"221","article-title":"Vocal correlates of emotional states","author":"williams","year":"1981","journal-title":"Speech Evaluation in Psychiatry"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953337"},{"key":"ref45","first-page":"3370","article-title":"OpenXBOW: Introducing the passau open-source crossmodal bag-of-words toolkit","volume":"18","author":"schmitt","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref48","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 Millenium ISCA Tutorial Res Workshop"},{"key":"ref47","article-title":"SEWA DB: A rich database for audio-visual emotion and sentiment research in the wild","author":"kossaifi","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2009.2024697"},{"key":"ref44","first-page":"295","article-title":"A text retrieval approach to content-based audio retrieval","author":"riley","year":"2008","journal-title":"Proc Int Symp Musical Information Retrieval"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4018\/jdet.2013040106"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9964459\/09813563.pdf?arnumber=9813563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T12:38:26Z","timestamp":1727527106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9813563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":63,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2022.3188223","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}