{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:47:20Z","timestamp":1774964840711,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF CAREER 1651740"],"award-info":[{"award-number":["NSF CAREER 1651740"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R34MH100404"],"award-info":[{"award-number":["R34MH100404"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21MH114835"],"award-info":[{"award-number":["R21MH114835"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["UL1TR002240"],"award-info":[{"award-number":["UL1TR002240"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HC Prechter Bipolar Program"},{"name":"Richard Tam Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2021,10,1]]},"DOI":"10.1109\/taffc.2019.2917047","type":"journal-article","created":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T20:15:15Z","timestamp":1558037715000},"page":"1069-1083","source":"Crossref","is-referenced-by-count":12,"title":["Jointly Aligning and Predicting Continuous Emotion Annotations"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2306-3341","authenticated-orcid":false,"given":"Soheil","family":"Khorram","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0375-6247","authenticated-orcid":false,"given":"Melvin G","family":"McInnis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1870-6063","authenticated-orcid":false,"given":"Emily Mower","family":"Provost","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","article-title":"Tensorflow: large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref72","article-title":"Acoustic analysis of laughter","author":"bickley","year":"1992","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-322"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682322"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946939"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1037\/0882-7974.21.1.62"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"ref39","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133952"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1119\/1.1371253"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.11.007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-548"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-94"},{"key":"ref60","article-title":"Mel-generalized cepstral analysis-a unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2015-2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2014-12"},{"key":"ref63","first-page":"183","article-title":"Speech synthesis based on gaussian conditional random fields","author":"khorram","year":"2013","journal-title":"Proc Int Symp Artif Intell Signal Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-605"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00439303"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2355"},{"key":"ref66","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref29","first-page":"43","article-title":"Automatic segmentation of spontaneous data using dimensional labels from multiple coders","author":"nicolaou","year":"0","journal-title":"Proc of LREC Int Workshop Multimodal Corpora Advances in Capturing Coding and Anal Multimodality"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707732"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997626"},{"key":"ref69","volume":"2","author":"mitra","year":"2006","journal-title":"Digital Signal Processing A Computer-Based Approach"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133946"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388783"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2334294"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/380101a0"},{"key":"ref25","author":"b\u00f6ring","year":"1950","journal-title":"A History of Experimental Psychology"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988268"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-837"},{"key":"ref58","article-title":"Voice recognition algorithms using mel frequency cepstral coefficient (mfcc) and dynamic time warping (dtw) techniques","author":"muda","year":"2010","journal-title":"arXiv 1003 4083"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349350"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref55","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"ref53","article-title":"A guide to convolution arithmetic for deep learning","author":"dumoulin","year":"2016","journal-title":"ArXiv 1603 07285"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683190"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3132049"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952656"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195387643.003.0008"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1177\/0165025417690267"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00071-7"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2712143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1494"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-016-0567-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2684799"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2713783"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/emo0000302"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2531664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019533"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136760"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461866"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811641"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266313"},{"key":"ref48","first-page":"441","article-title":"Yaafe, an easy to use and efficient audio feature extraction software","author":"mathieu","year":"2010","journal-title":"Proc ISMIR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266314"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266307"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9626162\/08716568.pdf?arnumber=8716568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:00Z","timestamp":1652194380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8716568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":84,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2019.2917047","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,1]]}}}