{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:06:37Z","timestamp":1784390797253,"version":"3.55.0"},"reference-count":50,"publisher":"Informa UK Limited","issue":"1","license":[{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Basic Public Welfare Research Project of Zhejiang Province","award":["LGG22F020014"],"award-info":[{"award-number":["LGG22F020014"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072410"],"award-info":[{"award-number":["62072410"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Connection Science"],"published-print":{"date-parts":[[2023,12,31]]},"DOI":"10.1080\/09540091.2023.2189217","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T22:37:45Z","timestamp":1682635065000},"update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":14,"title":["Multi-branch feature learning based speech emotion recognition using SCAR-NET"],"prefix":"10.1080","volume":"35","author":[{"given":"Keji","family":"Mao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ligang","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiefan","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanglin","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Aftab A. Morsali A. Ghaemmaghami S. & Champagne B. (2022). Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition. In ICASSP 2022\u20132022 IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 6912\u20136916). IEEE.","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"e_1_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Alaparthi V. S. Pasam T. R. Inagandla D. A. Prakash J. & Singh P. K. (2022). ScSer: Supervised contrastive learning for speech emotion recognition using transformers. In 2022 15th international conference on human system interaction (HSI) (pp. 1\u20137). IEEE.","DOI":"10.1109\/HSI55341.2022.9869453"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20185212"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.3991\/ijoe.v16i04.11870"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0960-9"},{"key":"e_1_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Burkhardt F. Paeschke A. Rolfes M. Sendlmeier W. F. & Weiss B. (2005). A database of German emotional speech. In Interspeech (Vol 5 pp. 1517\u20131520). ISCA.","DOI":"10.21437\/Interspeech.2005-446"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca"},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.97"},{"key":"e_1_3_2_11_1","unstructured":"Daniel N. Kjell E. & Kornel L. (2006). Emotion recognition in spontaneous speech using GMMs. In Proceedings of the 9th isca international conference on spoken language processing . IEEE."},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2009.0190"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2016.2623677"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"e_1_3_2_15_1","doi-asserted-by":"crossref","unstructured":"He K. Zhang X. Ren S. & Sun J. (2016). Deep residual learning for image recognition. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 770\u2013778). IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2339834"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.2478\/v10177-012-0024-4"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-016-0099-4"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2888882"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2874996"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20010183"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/math8122133"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.v36.9"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114177"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22218152"},{"key":"e_1_3_2_26_1","unstructured":"Lin M. Chen Q. & Yan S. (2013). Network in network. arXiv preprint arXiv:1312.4400."},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12010327"},{"key":"e_1_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Ma X. Wu Z. Jia J. Xu M. Meng H. & Cai L. (2018). Emotion recognition from variable-length speech segments using deep learning on spectrograms. In Interspeech (pp. 3683\u20133687). ISCA.","DOI":"10.21437\/Interspeech.2018-2228"},{"key":"e_1_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Mirsamadi S. Barsoum E. & Zhang C. (2017). Automatic speech emotion recognition using recurrent neural networks with local attention. In 2017 IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 2227\u20132231). IEEE.","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2021.015070"},{"key":"e_1_3_2_32_1","unstructured":"Nguyen D. Sridharan S. Nguyen D. T. Denman S. Tran S. N. Zeng R. & Fookes C. (2020). Joint deep cross-domain transfer learning for emotion recognition. arXiv preprint arXiv:2003.11136."},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2874986"},{"key":"e_1_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9396-2"},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"e_1_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2550528"},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3001054"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639"},{"key":"e_1_3_2_40_1","doi-asserted-by":"crossref","unstructured":"Schuller B. Vlasenko B. Eyben F. Rigoll G. & Wendemuth A. (2009). Acoustic emotion recognition: A benchmark comparison of performances. In 2009 IEEE workshop on automatic speech recognition & understanding (pp. 552\u2013557). IEEE.","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"e_1_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Shinde A. S. Patil V. V. Khadse K. R. Jadhav N. Joglekar S. & Hatwalne M. (2022). ML based speech emotion recognition framework for music therapy suggestion system. In 2022 6th international conference on computing communication control and automation (ICCUBEA) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICCUBEA54992.2022.10011091"},{"key":"e_1_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-016-0794-2"},{"key":"e_1_3_2_43_1","doi-asserted-by":"crossref","unstructured":"Sowmya G. Naresh K. Sri J. D. Sai K. P. & Indira D. V. (2022). Speech2Emotion: Intensifying emotion detection using MLP through RAVDESS dataset. In 2022 international conference on electronics and renewable systems (ICEARS) (pp. 1\u20133). IEEE.","DOI":"10.1109\/ICEARS53579.2022.9752022"},{"key":"e_1_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Szegedy C. Vanhoucke V. Ioffe S. Shlens J. & Wojna Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 2818\u20132826). IEEE.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"12","key":"e_1_3_2_45_1","first-page":"380","article-title":"Comparative analysis of emotion recognition system","volume":"6","author":"Thakare C.","year":"2019","unstructured":"Thakare, C., Chaurasia, N. K., Rathod, D., Joshi, G., & Gudadhe, S. (2019). Comparative analysis of emotion recognition system. International Research Journal of Engineering and Technology, 6(12), 380\u2013384.","journal-title":"International Research Journal of Engineering and Technology"},{"key":"e_1_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Trigeorgis G. Ringeval F. Brueckner R. Marchi E. Nicolaou M. A. Schuller B. & Zafeiriou S. (2016). Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In 2016 IEEE international conference on acoustics speech and signal processing (ICASSP) (pp. 5200\u20135204). ISCA.","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"e_1_3_2_47_1","volume-title":"Machine audition: Principles, algorithms and systems:\u00a0principles, algorithms and systems","author":"Wang W.","year":"2010","unstructured":"Wang, W. (2010). Machine audition: Principles, algorithms and systems:\u00a0principles, algorithms and systems. IGI Global."},{"key":"e_1_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3140238"},{"key":"e_1_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.1800508"},{"key":"e_1_3_2_50_1","doi-asserted-by":"crossref","unstructured":"Yenigalla P. Kumar A. Tripathi S. Singh C. Kar S. & Vepa J. (2018). Speech emotion recognition using spectrogram & phoneme embedding. In Interspeech (Vol. 2018 pp. 3688\u20133692). ISCA.","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"e_1_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"}],"container-title":["Connection Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/09540091.2023.2189217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T07:52:35Z","timestamp":1703749955000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/09540091.2023.2189217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,27]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,12,31]]}},"alternative-id":["10.1080\/09540091.2023.2189217"],"URL":"https:\/\/doi.org\/10.1080\/09540091.2023.2189217","relation":{},"ISSN":["0954-0091","1360-0494"],"issn-type":[{"value":"0954-0091","type":"print"},{"value":"1360-0494","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,27]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=ccos20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2022-12-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2189217"}}