{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T01:44:50Z","timestamp":1790646290736,"version":"4.1.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Data61"},{"DOI":"10.13039\/501100000943","name":"Commonwealth Scientific and Industrial Research Organisation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000943","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2020,10,1]]},"DOI":"10.1109\/taffc.2018.2821135","type":"journal-article","created":{"date-parts":[[2018,4,4]],"date-time":"2018-04-04T18:10:59Z","timestamp":1522865459000},"page":"653-668","source":"Crossref","is-referenced-by-count":15,"title":["An Investigation of Partition-Based and Phonetically-Aware Acoustic Features for Continuous Emotion Prediction from Speech"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7915-6790","authenticated-orcid":false,"given":"Zhaocheng","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6624-5551","authenticated-orcid":false,"given":"Julien","family":"Epps","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"tipping","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1093\/applin\/11.1.90"},{"key":"ref71","first-page":"1179","article-title":"Unveiling the acoustic properties that describe the valence dimension","author":"busso","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref70","first-page":"2253","article-title":"The relevance of feature type for the automatic classification of emotional user states: Low level descriptors and functionals","author":"schuller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref39","first-page":"3","article-title":"AVEC 2016 – depression, mood, and emotion recognition workshop and challenge","author":"valstar","year":"2016","journal-title":"Proc AVEC International Workshop"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-015-9300-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref32","first-page":"737","article-title":"Recognizing emotions in dialogues with disfluencies and non-verbal vocalisations","author":"tian","year":"2015","journal-title":"Int Conf Affective Comput Intell Interact"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1124"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344561"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593944"},{"key":"ref62","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":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.08.018"},{"key":"ref63","first-page":"3","article-title":"AV+EC 2015 – The first affect recognition challenge bridging across audio, video, and physiological data","author":"ringeval","year":"2015","journal-title":"Proc AVEC International Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3005-5_54"},{"key":"ref64","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.11.003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009752403260"},{"key":"ref66","author":"rabiner","year":"1978","journal-title":"Digital Processing of Speech Signals"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997629"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2326393"},{"key":"ref68","first-page":"1","article-title":"Fast marginal likelihood maximisation for sparse Bayesian models","author":"tipping","year":"0","journal-title":"Proc 9th Int Workshop Artif Intell Statist"},{"key":"ref69","first-page":"383","article-title":"Analysis of sparse Bayesian learning","author":"faul","year":"0","journal-title":"Proc 14th Int Conf Neural Inf Process Syst Natural Synthetic"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"ref1","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494893"},{"key":"ref22","first-page":"27","article-title":"Say cheese versus smile: Reducing speech-related variability for facial emotion recognition","author":"kim","year":"0","journal-title":"Proc ACM Int Conf Multimedia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553752"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70872-8_19"},{"key":"ref23","first-page":"312","article-title":"The INTERSPEECH 2009 emotion challenge","author":"schuller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/162093"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.012"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TPAMI.2014.16","article-title":"Dynamic probabilistic CCA for analysis of affective behavior and fusion of continuous annotations","volume":"36","author":"nicolaou","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.12.005"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388783"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2334294"},{"key":"ref56","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref55","article-title":"Phoneme recognition based on long temporal context","author":"schwarz","year":"2008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988264"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424235"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472787"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953137"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.02.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.008"},{"key":"ref18","first-page":"1","article-title":"Affect-robust speech recognition by dynamic emotional adaptation","author":"schuller","year":"0","journal-title":"Proc Speech Prosody"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.011"},{"key":"ref6","first-page":"889","article-title":"Emotion recognition based on phoneme classes","author":"lee","year":"2004","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref5","first-page":"617","article-title":"Phonetic and speaker variations in automatic emotion classification","author":"sethu","year":"2008","journal-title":"Proc 9th Annu Conf Int Speech Commun Assoc"},{"key":"ref8","first-page":"1575","article-title":"Emotion dimensions and formant position","author":"goudbeek","year":"2009","journal-title":"Proc 10th Annu Conf Int Speech Commun Assoc"},{"key":"ref7","first-page":"1577","article-title":"Vowel formants analysis allows straightforward detection of high arousal acted and spontaneous emotions","author":"vlasenko","year":"2011","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_12"},{"key":"ref9","first-page":"804","article-title":"Investigating the role of phoneme-level modifications in emotional speech resynthesis","author":"murtaza","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2420092"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953160"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2008.14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2808196.2811640"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704310024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.11.007"},{"key":"ref44","article-title":"Frame-level features conveying phonetic information for language and speaker recognition","author":"s\u00e1nchez","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0100795"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/9259273\/08331122.pdf?arnumber=8331122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:13:29Z","timestamp":1651079609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8331122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,1]]},"references-count":75,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2018.2821135","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,1]]}}}