{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T23:31:48Z","timestamp":1775086308436,"version":"3.50.1"},"reference-count":159,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Research and Development Program of Hainan Province","award":["ZDYF2021GXJS017"],"award-info":[{"award-number":["ZDYF2021GXJS017"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82160345"],"award-info":[{"award-number":["82160345"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201571"],"award-info":[{"award-number":["62201571"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Science and Technology Plan Project of Haikou","award":["2021-016"],"award-info":[{"award-number":["2021-016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3289312","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:48:02Z","timestamp":1687805282000},"page":"2534-2547","source":"Crossref","is-referenced-by-count":15,"title":["Music Theory-Inspired Acoustic Representation for Speech Emotion Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8958-0341","authenticated-orcid":false,"given":"Xingfeng","family":"Li","sequence":"first","affiliation":[{"name":"Graduate School of Computer Science and Technology, Hainan University, Haikou, China"}]},{"given":"Xiaohan","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Information Science, Nagoya University, Nagoya, Japan"}]},{"given":"Desheng","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Information and Computer, Taiyuan University of Technology, Taiyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7799-366X","authenticated-orcid":false,"given":"Yongwei","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5525-687X","authenticated-orcid":false,"given":"Qingchen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Graduate School of Computer Science and Technology, Hainan University, Haikou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9366-6586","authenticated-orcid":false,"given":"Zhengxia","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[{"name":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-6754","authenticated-orcid":false,"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[{"name":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The Nature of Emotion: Fundamental Questions","author":"Ekman","year":"1994"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195096736.001.0001"},{"key":"ref3","volume-title":"Psychology","volume":"10010","author":"Schacter","year":"2009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.so.15.080189.001533"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.55.090902.141954"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/e634112013-014"},{"key":"ref7","volume-title":"Feelings as Information: Informational and Motivational Functions of Affective States","author":"Schwarz","year":"1990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/0278-6133.20.4.243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0149-7634(01)00056-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-83602-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10943-004-4302-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1176\/ajp.141.6.725"},{"key":"ref13","volume-title":"Mind and Body: Psychology of Emotion and Stress","author":"Mandler","year":"1984"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511816826.023"},{"key":"ref15","volume-title":"Clinical Neuropsychology of Emotion","author":"Suchy","year":"2011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.12987\/9780300177879"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10984-013-9125-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.08.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/11304-033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_125"},{"key":"ref22","article-title":"Personalized federated deep learning for pain estimation from face images","author":"Rudovic","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198529620.001.0001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946939"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85099-1_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3114123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2021.107876"},{"issue":"47","key":"ref29","first-page":"1","article-title":"Identification of attention deficit hyperactivity disorder patients using wavelet-based features of EEG signals","volume":"12","author":"Shahraki","year":"2021","journal-title":"J. Intell. Procedures Elect. Technol."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.12324"},{"key":"ref31","volume-title":"Heart of the Machine: Our Future in a World of Artificial Emotional Intelligence","author":"Yonck","year":"2020"},{"key":"ref32","article-title":"Affective videogames and modes of affective gaming: Assist me, challenge me, emote me","author":"Gilleade","year":"2005","journal-title":"DiGRA 2005: Changing ViewsWorlds in Play."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-011-9107-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICVES.2019.8906392"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/1754073919897295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2019.08.007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app11041890"},{"key":"ref39","article-title":"The role of phonetic units in speech emotion recognition","author":"Yuan","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.129.5.770"},{"key":"ref41","article-title":"Voices of power, passion, and personality","volume-title":"Proc. INTERSPEECH","author":"Scherer","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3494987"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120585"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.14"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2006.03.002"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-484"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2016.01565"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5427"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.233"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-801"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-86"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-104"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-129"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053648"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/s21051579"},{"key":"ref64","first-page":"3390","article-title":"Stochastic process regression for cross-cultural speech emotion recognition","volume-title":"Proc. Interspeech","author":"Kumar","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.04.004"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1097\/00000441-195610000-00024"},{"key":"ref68","volume-title":"The Unanswered Question: Six Talks at Harvard","volume":"33","author":"Bernstein","year":"1976"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.99.2.143"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195126013.003.0026"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2820691"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195123753.001.0001"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00123"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1177\/2059204318762650"},{"key":"ref75","volume-title":"Sound Sentiment: An Essay on the Musical Emotions, Including the Complete Text of the Corded Shell","author":"Kivy","year":"1989"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-8917-0_5"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1121\/1.5002886"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(05)80231-0"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780198722946.013.24"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1177\/10298649020050S103"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-835X.2012.02081.x"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1348\/000712610X506831"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0703140104"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1121\/1.3478785"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1177\/1754073919898522"},{"key":"ref87","volume-title":"Sound Color","author":"Slawson","year":"1985"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1080\/07494468708567056"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199230143.001.0001"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1037\/a0036858"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.4324\/9781315648026"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.4324\/9780203402894"},{"key":"ref93","article-title":"Impact of intervals on the emotional effect in western music","author":"Kaygusuz","year":"2018"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.4.1.46"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.2307\/40285445"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1177\/0305735698262003"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0001470"},{"key":"ref98","article-title":"On the role of pitch intervals in the perception of emotional speech","volume-title":"Proc. ISCA IEEE Workshop Spontaneous Speech Process. Recognit.","author":"Fujisawa","year":"2003"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.09.009"},{"key":"ref100","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/12513.001.0001","volume-title":"A Generative Theory of Tonal Music, Reissue, With a New Preface","author":"Lerdahl","year":"1996"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2008.09.005"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.97.22.11765"},{"key":"ref103","volume-title":"The Origins of Music","author":"Wallin","year":"2000"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.2001.tb05745.x"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.00075"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-8917-0"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-9452(74)80017-1"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1080\/0929821042000317831"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1360.007"},{"key":"ref110","volume-title":"The Speech Chain","author":"Denes","year":"1993"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2977776"},{"key":"ref112","article-title":"Music embedding: A tool for incorporating music theory into computational music applications","author":"HekmatiAthar","year":"2021"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1080\/02699930701503567"},{"key":"ref114","article-title":"YM2413-MDB: A multi-instrumental FM video game music dataset with emotion annotations","author":"Choi","year":"2022"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3032373"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2010.06.006"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2011-519"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2012.01217.x"},{"key":"ref119","article-title":"1.0 detailed specification","year":"1996","journal-title":"MIDI Manufacturers Assoc. Inc"},{"key":"ref120","article-title":"Dynamics. grove music online","author":"Thiemel","year":"2001"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1121\/1.4978245"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115702"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319457"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139105651"},{"key":"ref125","volume-title":"Dictionary of Music and Musicians","author":"Sadie","year":"2001"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-65615-8"},{"key":"ref127","article-title":"Sonancia: Una clarificacin conceptual","author":"i Vallet","year":"2016"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1590\/S1806-11173812105"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.2307\/935312"},{"key":"ref130","volume-title":"Musical Form and Analysis: Time, Pattern, Proportion","author":"Spring","year":"2013"},{"key":"ref131","volume-title":"On the Musical Scales of Various Nations","author":"Ellis","year":"1885"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.3758\/BF03195786"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811722"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44342-2_21"},{"key":"ref135","article-title":"Mathematical harmony analysis","author":"Ryan","year":"2016"},{"key":"ref136","volume-title":"Psychoacoustics: Facts and Models","volume":"22","author":"Zwicker","year":"2013"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041394"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014171"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.03.005"},{"key":"ref142","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jozefowicz","year":"2015"},{"key":"ref143","article-title":"Network in network","author":"Lin","year":"2013"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-785"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054580"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746155"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01950"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1080\/0929821042000317813"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1027\/1015-5759\/a000589"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref157","first-page":"325","article-title":"Deep multilayer perceptrons for dimensional speech emotion recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Atmaja","year":"2020"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.11.003"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10163251.pdf?arnumber=10163251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:59:31Z","timestamp":1710385171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10163251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":159,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3289312","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}