{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T23:26:33Z","timestamp":1784935593050,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1453781"],"award-info":[{"award-number":["IIS-1453781"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2019,10,1]]},"DOI":"10.1109\/taffc.2017.2736999","type":"journal-article","created":{"date-parts":[[2017,8,7]],"date-time":"2017-08-07T18:12:24Z","timestamp":1502129544000},"page":"471-483","source":"Crossref","is-referenced-by-count":274,"title":["Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings"],"prefix":"10.1109","volume":"10","author":[{"given":"Reza","family":"Lotfian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4075-4072","authenticated-orcid":false,"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.010"},{"key":"ref38","author":"fischer","year":"2002","journal-title":"Zur Messung von Emotionen in der angewandten Forschung"},{"key":"ref33","year":"2016"},{"key":"ref32","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","author":"cieri","year":"0","journal-title":"presented at the First Int Conf Language Resources Eval"},{"key":"ref31","first-page":"238","article-title":"Building a naturalistic emotional speech corpus by retrieving expressive behaviors from existing speech corpora","author":"mariooryad","year":"2014","journal-title":"InterSpeech"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953216"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178867"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.414997"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.21437\/Interspeech.2008-644","article-title":"Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis","author":"kim","year":"2008","journal-title":"InterSpeech"},{"key":"ref34","first-page":"1544","article-title":"Speech activity detection for NASA Apollo space missions: Challenges and solutions","author":"ziaei","year":"2014","journal-title":"InterSpeech"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102369"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref61","first-page":"203","article-title":"Support vector regression","volume":"11","author":"basak","year":"2007","journal-title":"Neural Inform Process Lett Rev"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74889-2_42"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.21437\/Interspeech.2012-124","article-title":"Unveiling the acoustic properties that describe the valence dimension","author":"busso","year":"2012","journal-title":"InterSpeech"},{"key":"ref27","first-page":"17","article-title":"Recording audio-visual emotional databases from actors: A closer look","author":"busso","year":"2008","journal-title":"Proc 2nd Int Workshop Emotion Corpora Res Emotion Affect Int Conf Language Resources Eval"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1494"},{"key":"ref29","first-page":"6","article-title":"A framework for eliciting emotional speech: Capitalizing on the actor's process","author":"enos","year":"2006","journal-title":"Proc 1st Int Workshop Emotion Corpora Res Emotion Affect (Int Conf Language Resources Eval"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195387643.003.0008"},{"key":"ref20","article-title":"Joint processing of audio-visual information for the recognition of emotional expressions in human-computer interaction","author":"chen","year":"2000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.02.013"},{"key":"ref21","first-page":"15","article-title":"GEMEP - Geneva multimodal emotion portrayals: A corpus for the study of multimodal emotional expressions","author":"b\u00e4nziger","year":"2006","journal-title":"Proc 1st Int Workshop Emotion Corpora Res Emotion Affect (Int Conf Language Resources Eval"},{"key":"ref24","first-page":"813","article-title":"Multimodal databases of everyday emotion: Facing up to complexity","author":"douglas-cowie et","year":"2005","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.002"},{"key":"ref26","first-page":"195","article-title":"Desperately seeking emotions or: Actors, wizards and human beings","author":"batliner","year":"2000","journal-title":"Proc ISCA Tutorial Res Workshop Speech Emotion"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/j.0824-7935.2004.00233.x"},{"key":"ref51","author":"f\u00fcrnkranz","year":"2010","journal-title":"Preference Learning"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150429"},{"key":"ref58","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991091"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953107"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.01.003"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"358","DOI":"10.21437\/Interspeech.2012-116","article-title":"Combining ranking and classification to improve emotion recognition in spontaneous speech","author":"cao","year":"2012","journal-title":"InterSpeech"},{"key":"ref53","first-page":"80","article-title":"Learning preference relations for information retrieval","author":"herbrich","year":"1998","journal-title":"Proc Workshop on Learning for Text Categorization"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2352268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349500"},{"key":"ref12","first-page":"1","article-title":"The sensitive artificial listener: An induction technique for generating emotionally coloured conversation","author":"douglas-cowie","year":"2008","journal-title":"Proc 2nd Int Workshop Emotion Corpora Res Emotion Affect Int Conf Language Resources Eval"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref14","article-title":"Automatic classification of emotion-related user states in spontaneous children's speech","author":"steidl","year":"2009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607572"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289072"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00070-5"},{"key":"ref3","first-page":"109","article-title":"A state of the art review on emotional speech databases","author":"ververidis","year":"2003","journal-title":"Proc 1st Int Workshop Interactive Rich Media Content Prod"},{"key":"ref6","first-page":"1517","article-title":"A database of German emotional speech","author":"burkhardt","year":"2005","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref5","article-title":"Emotional prosody speech and transcripts LDC2002S28","author":"liberman","year":"2002"},{"key":"ref8","first-page":"801","article-title":"Real-life emotions detection with lexical and paralinguistic cues on human-human call center dialogs","author":"devillers","year":"2006","journal-title":"Proc Int Conf Spoken Language"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","article-title":"Toward detecting emotions in spoken dialogs","volume":"13","author":"lee","year":"2005","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2508454"},{"key":"ref9","first-page":"39","article-title":"A new emotion database: Considerations, sources and scope","author":"douglas-cowie","year":"2000","journal-title":"Proc Speech and Emotion ISCA Tutorial and Research Workshop (ITRW)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-006-0025-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472670"},{"key":"ref47","first-page":"148","article-title":"The INTERSPEECH 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"2013","journal-title":"InterSpeech"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-429"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1052"},{"key":"ref44","first-page":"4898","article-title":"Speech emotion recognition based on HMM and SVM","author":"lin","year":"2005","journal-title":"Proc Int Conf Mach Learn Cybern"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593944"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/8911290\/08003425.pdf?arnumber=8003425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T01:25:02Z","timestamp":1719365102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8003425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2017.2736999","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,1]]}}}