{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:44:18Z","timestamp":1785606258845,"version":"3.56.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11042-021-10553-4","type":"journal-article","created":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T04:02:46Z","timestamp":1630123366000},"page":"4897-4907","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Speech emotion recognition based on multi\u2010feature and multi\u2010lingual fusion"],"prefix":"10.1007","volume":"81","author":[{"given":"Chunyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuwei","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiying","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,28]]},"reference":[{"key":"10553_CR1","doi-asserted-by":"publisher","unstructured":"Andr\u00e9 Stuhlsatz, Meyer C, Eyben F et al (2011) Deep neural networks for acoustic emotion recognition: Raising the benchmarks. 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, pp 5688\u20135691. https:\/\/doi.org\/10.1109\/ICASSP.2011.5947651","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"10553_CR2","doi-asserted-by":"publisher","unstructured":"Bertero D, Fung P (2017) A first look into a Convolutional Neural Network for speech emotion detection. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, pp 5115\u20135119. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953131","DOI":"10.1109\/ICASSP.2017.7953131"},{"issue":"4","key":"10553_CR3","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee CC et al (2008) IEMOCAP: interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335\u2013359","journal-title":"Lang Resour Eval"},{"issue":"4","key":"10553_CR4","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"Davis SB (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process 28(4):65\u201374. https:\/\/doi.org\/10.1109\/TASSP.1980.1163420","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"1","key":"10553_CR5","first-page":"23","volume":"8","author":"L Dora","year":"2018","unstructured":"Dora L (2018) Education in professional defense -possibilities of classification of training level with the help of impulse. J Syst Manag Sci 8(1):23\u201344","journal-title":"J Syst Manag Sci"},{"issue":"2","key":"10553_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"SKR EybenF","year":"2015","unstructured":"EybenF SKR, Schuller BW et al (2015) The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for voice research and affective computing. IEEE Trans Affect Comput 7(2):1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2015.2457417","journal-title":"IEEE Trans Affect Comput"},{"issue":"2","key":"10553_CR7","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"SKR EybenF","year":"2016","unstructured":"EybenF SKR, Truong KP et al (2016) The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for speech research and affective computing. IEEE Trans Affect Comput 7(2):190\u2013202. https:\/\/doi.org\/10.1109\/TAFFC.2015.2457417","journal-title":"IEEE Trans Affect Comput"},{"key":"10553_CR8","doi-asserted-by":"publisher","unstructured":"Gemmeke JF, Ellis DPW, Freedman D et al (2017) Audio Set: An ontology and human-labeled dataset for audio events. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, pp 776\u2013780. https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"10553_CR9","doi-asserted-by":"publisher","unstructured":"Huang JT, Li J, Yu D et al (2013) Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp 7304\u20137308. https:\/\/doi.org\/10.1109\/ICASSP.2013.6639081","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"10553_CR10","unstructured":"Jackson P, UlHaq S (2011) Surrey Audio-Visual Expressed Emotion (SAVEE) database. University of Surrey, Guildford"},{"key":"10553_CR11","doi-asserted-by":"publisher","unstructured":"Kandali AB, Routray A, Basu TK (2008) Emotion recognition from Assamese speeches using MFCC features and GMM classifier. TENCON 2008\u20132008 IEEE Region 10 Conference 1\u20135. https:\/\/doi.org\/10.1109\/TENCON.2008.4766487","DOI":"10.1109\/TENCON.2008.4766487"},{"key":"10553_CR12","doi-asserted-by":"publisher","unstructured":"Kim J, Saurous R (2018) Emotion recognition from human speech using temporal information and deep learning. Interspeech 937\u2013940. https:\/\/doi.org\/10.21437\/Interspeech.2018-1132","DOI":"10.21437\/Interspeech.2018-1132"},{"issue":"2","key":"10553_CR13","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"CM Lee","year":"2005","unstructured":"Lee CM, Narayanan SS (2005) Toward detecting emotions in spoken dialogs. IEEE Trans Speech Audio Process 13(2):293\u2013303. https:\/\/doi.org\/10.1109\/TSA.2004.838534","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10553_CR14","doi-asserted-by":"publisher","unstructured":"Lee CM, Narayanan S, Pieraccini R (2001) Recognition of negative emotions from the speech signal. IEEE automatic speech recognition understanding workshop 240\u2013243. https:\/\/doi.org\/10.1109\/ASRU.2001.1034632","DOI":"10.1109\/ASRU.2001.1034632"},{"issue":"6","key":"10553_CR15","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1007\/s12652-016-0406-z","volume":"8","author":"Y Li","year":"2016","unstructured":"Li Y, Tao J, Chao L et al (2016) CHEAVD: a Chinese natural emotional audio\u2013visual database. J Ambient Intell Humaniz Comput 8(6):913\u2013924","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"10553_CR16","unstructured":"Lili F, Yinhong D (2018) Research on internet search data in china\u2019s social problems under the background of big data. J Logist Informat Serv Sci 5(2):55\u201367"},{"key":"10553_CR17","unstructured":"Mao X, Zhang B, Luo YI (2007) Speech emotion recognition based on a hybrid of HMM\/ANN. Proceedings of the 7th Conference on 7th WSEAS International Conference on Applied Informatics and Communications 7:367\u2013370"},{"key":"10553_CR18","doi-asserted-by":"publisher","unstructured":"Mirsamadi S, Barsoum E, Zhang C (2017) Automatic speech emotion recognition using recurrent neural networks with local attention. International conference on acoustics, speech, and signal processing, New Orleans, LA, USA. https:\/\/doi.org\/10.1109\/ICASSP.2017.7952552","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"10553_CR19","doi-asserted-by":"crossref","unstructured":"NedjmaOusidhoum,et al (2019) Multilingual and Multi-Aspect Hate Speech Analysis. International joint conference on natural language processing, pp 4675\u20134684","DOI":"10.18653\/v1\/D19-1474"},{"key":"10553_CR20","doi-asserted-by":"publisher","unstructured":"Pao TL, Chen YT, Yeh JH (2004) Emotion recognition from Mandarin speech signals, 2004 International Symposium on Chinese Spoken Language Processing, pp 301\u2013304. https:\/\/doi.org\/10.1109\/CHINSL.2004.1409646","DOI":"10.1109\/CHINSL.2004.1409646"},{"key":"10553_CR21","doi-asserted-by":"crossref","unstructured":"Petrushin VA (2000) Emotion recognition in speech signal: experimental study, development, and application. Sixth International Conference on Spoken Language Processing, Beijing, China","DOI":"10.21437\/ICSLP.2000-791"},{"key":"10553_CR22","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","volume-title":"Affective Computing","author":"RW Picard","year":"1997","unstructured":"Picard RW (1997) Affective Computing. MIT Press, Google Scholar, Cambridge"},{"issue":"1","key":"10553_CR23","doi-asserted-by":"publisher","first-page":"159","DOI":"10.24818\/18423264\/54.1.20.11","volume":"54","author":"O Voican","year":"2020","unstructured":"Voican O (2020) Using data mining methods to solve classification problems in financial-banking institutions. Econ Comput Econ Cybern Stud Res 54(1):159\u2013176. https:\/\/doi.org\/10.24818\/18423264\/54.1.20.11","journal-title":"Econ Comput Econ Cybern Stud Res"},{"issue":"4","key":"10553_CR24","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1121\/1.1913238","volume":"52","author":"CE Williams","year":"1972","unstructured":"Williams CE, Stevens KN (1972) Emotions and speech: some acoustical correlates. J Acoust Soc Am 52(4):1238\u20131250. https:\/\/doi.org\/10.1121\/1.1913238","journal-title":"J Acoust Soc Am"},{"issue":"1","key":"10553_CR25","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TAFFC.2017.2684799","volume":"10","author":"B Zhang","year":"2019","unstructured":"Zhang B, Mower Provost E, Essl G (2019) Cross-corpus acoustic emotion recognition with multi-task learning: seeking common ground while preserving differences. IEEE Trans Affect Comput 10(1):85\u201399. https:\/\/doi.org\/10.1109\/TAFFC.2017.2684799","journal-title":"IEEE Trans Affect Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10553-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10553-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10553-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:00:03Z","timestamp":1725703203000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10553-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,28]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["10553"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10553-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,28]]},"assertion":[{"value":"3 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}