{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T08:28:14Z","timestamp":1786350494861,"version":"build-2736575974"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":48,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00336286"],"award-info":[{"award-number":["RS-2024-00336286"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Inha University research grant"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s44443-026-00938-6","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T12:25:15Z","timestamp":1782217515000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatio-spectral modeling of dynamic emotion flow with multi-scale wavelets for emotion recognition in conversation"],"prefix":"10.1007","volume":"38","author":[{"given":"Han","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deok-Hwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"938_CR1","doi-asserted-by":"crossref","unstructured":"Alhussein G, Alkhodari M, Khandoker A, Hadjileontiadis LJ (2022) Emotional climate recognition in interactive conversational speech using deep learning. 2022 IEEE International Conference on Digital Health (ICDH). IEEE, pp 96\u2013103","DOI":"10.1109\/ICDH55609.2022.00023"},{"key":"938_CR2","doi-asserted-by":"crossref","unstructured":"Barsoum E, Zhang C, Ferrer CC, Zhang Z (2016) Training deep networks for facial expression recognition with crowd-sourced label distribution. In: Proceedings of the 18th ACM international conference on multimodal interaction, pp 279\u2013283","DOI":"10.1145\/2993148.2993165"},{"key":"938_CR3","unstructured":"Bresson R, Nikolentzos G, Panagopoulos G, Chatzianastasis M, Pang J, Vazirgiannis M (2025) KAGNNs: Kolmogorov-arnold networks meet graph learning. Transactions on Machine Learning Research. https:\/\/openreview.net\/forum?id=03UB1MCAMr"},{"key":"938_CR4","doi-asserted-by":"crossref","unstructured":"Busso C, Bulut M, Lee C-C, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) Iemocap: Interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335\u2013359","DOI":"10.1007\/s10579-008-9076-6"},{"key":"938_CR5","doi-asserted-by":"crossref","unstructured":"Chen F, Shao J, Zhu S, Shen HT (2023a) Multivariate, multi-frequency and multimodal: Rethinking graph neural networks for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10761\u201310770","DOI":"10.1109\/CVPR52729.2023.01036"},{"issue":"3","key":"938_CR6","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TAFFC.2023.3315752","volume":"15","author":"T Chen","year":"2023","unstructured":"Chen T, Shen Y, Chen X, Zhang L (2023) Zhao S Mpeg: A multi-perspective enhanced graph attention network for causal emotion entailment in conversations. IEEE Trans Affect Comput 15(3):1004\u20131017","journal-title":"IEEE Trans Affect Comput"},{"key":"938_CR7","doi-asserted-by":"crossref","unstructured":"Cho K, Van\u00a0Merri\u00ebnboer B, Gul\u00e7ehre \u00c7, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation","DOI":"10.3115\/v1\/D14-1179"},{"issue":"10","key":"938_CR8","doi-asserted-by":"publisher","first-page":"9910","DOI":"10.1109\/TCSVT.2024.3405406","volume":"34","author":"Y Dai","year":"2024","unstructured":"Dai Y, Li Y, Chen D, Li J (2024) Lu G Multimodal decoupled distillation graph neural network for emotion recognition in conversation. IEEE Trans Circuits Syst Video Technol 34(10):9910\u20139924","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"938_CR9","doi-asserted-by":"crossref","unstructured":"Simone D, Greco G, Saggese L, Vento A, M (2025) Multimodal audio-visual emotion recognition for social robotics. International conference on computer analysis of images and patterns. Springer, pp 245\u2013255","DOI":"10.1007\/978-3-032-05060-1_21"},{"issue":"4","key":"938_CR10","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.neunet.2005.03.007","volume":"18","author":"L Devillers","year":"2005","unstructured":"Devillers L, Vidrascu L (2005) Lamel L (2005) Challenges in real-life emotion annotation and machine learning based detection. Neural Netw 18(4):407\u2013422","journal-title":"Neural Netw"},{"key":"938_CR11","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. Proceedings of the 18th ACM international conference on multimedia. pp 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"938_CR12","unstructured":"Fang T, Gao T, Wang C, YihaoShang, Chow W, Chen L, Yang Y (2025) KAA: Kolmogorov-arnold attention for enhancing attentive graph neural networks. In: The 13th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=atXCzVSXTJ"},{"issue":"16","key":"938_CR13","doi-asserted-by":"publisher","first-page":"7165","DOI":"10.3390\/app14167165","volume":"14","author":"RA Garc\u00eda-Hern\u00e1ndez","year":"2024","unstructured":"Garc\u00eda-Hern\u00e1ndez RA, Luna-Garc\u00eda H, Celaya-Padilla JM, Garc\u00eda-Hern\u00e1ndez A, Reveles-G\u00f3mez LC, Flores-Chaires LA, Delgado-Contreras JR, Rondon D, Villalba-Condori KO (2024) A systematic literature review of modalities, trends, and limitations in emotion recognition, affective computing, and sentiment analysis. Appl Sci 14(16):7165","journal-title":"Appl Sci"},{"key":"938_CR14","doi-asserted-by":"crossref","unstructured":"Genet R, Inzirillo H (2025) TKAN: Temporal Kolmogorov-Arnold Networks.arXiv:2405.07344 Preprint at","DOI":"10.2139\/ssrn.4825654"},{"key":"938_CR15","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Poria S, Chhaya N, Gelbukh A (2019) Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). pp 154\u2013164","DOI":"10.18653\/v1\/D19-1015"},{"key":"938_CR16","doi-asserted-by":"crossref","unstructured":"Hazarika D, Poria S, Mihalcea R, Cambria E, Zimmermann R (2018) Icon: Interactive conversational memory network for multimodal emotion detection. Proceedings of the 2018 conference on empirical methods in natural language processing. pp 2594\u20132604","DOI":"10.18653\/v1\/D18-1280"},{"issue":"5","key":"938_CR17","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik K, Stinchcombe M (1989) White H Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359\u2013366","journal-title":"Neural Netw"},{"key":"938_CR18","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"938_CR19","doi-asserted-by":"crossref","unstructured":"Hu J, Liu Y, Zhao J, Jin Q (2021) Mmgcn: Multimodal fusion via deep graph convolution network for emotion recognition in conversation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 5666\u20135675","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"938_CR20","doi-asserted-by":"crossref","unstructured":"Hu D, Hou X, Wei L, Jiang L, Mo Y (2022a) Mm-dfn: Multimodal dynamic fusion network for emotion recognition in conversations. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7037\u20137041. IEEE","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"938_CR21","doi-asserted-by":"crossref","unstructured":"Hu G, Lin T-E, Zhao Y, Lu G, Wu Y, Li Y (2022b) Unimse: Towards unified multimodal sentiment analysis and emotion recognition. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 7837\u20137851","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"issue":"3","key":"938_CR22","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s11042-026-21428-x","volume":"85","author":"C Jannu","year":"2026","unstructured":"Jannu C, Burra M, Vanambathina SD (2026) Parisae V Speech enhancement using neural free attention with multi-stage squeeze temporal convolutional networks. Multimedia Tools and Applications 85(3):195","journal-title":"Multimedia Tools and Applications"},{"key":"938_CR23","doi-asserted-by":"crossref","unstructured":"Jannu C, Bharath D, Sanjay VN, Kothakotamaana H, Adapa S, Parisae V (2025) Deep learning-based speech emotion recognition: Evaluating cnn, clstm, and lstm models. 2025 9th International Conference on Inventive Systems and Control (ICISC). IEEE, pp 108\u2013115","DOI":"10.1109\/ICISC65841.2025.11188229"},{"key":"938_CR24","doi-asserted-by":"crossref","unstructured":"Joshi A, Bhat A, Jain A, Singh A, Modi A (2022) Cogmen: Contextualized gnn based multimodal emotion recognition. Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies. pp 4148\u20134164","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"938_CR25","doi-asserted-by":"crossref","unstructured":"Kendall A, Gal Y, Cipolla R (2017) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, pp 7482\u20137491. https:\/\/api.semanticscholar.org\/CorpusID:4800342","DOI":"10.1109\/CVPR.2018.00781"},{"key":"938_CR26","doi-asserted-by":"crossref","unstructured":"Khan M, Ishaq M, Swain M, Kwon S (2023) Advanced sequence learning approaches for emotion recognition using speech signals. In: Intelligent multimedia signal processing for smart ecosystems. Springer, pp 307\u2013325","DOI":"10.1007\/978-3-031-34873-0_13"},{"key":"938_CR27","doi-asserted-by":"publisher","first-page":"86220","DOI":"10.1109\/ACCESS.2024.3413136","volume":"12","author":"M Khan","year":"2024","unstructured":"Khan M, El Saddik A, Deriche M (2024) Gueaieb W Stt-net: Simplified temporal transformer for emotion recognition. IEEE Access 12:86220\u201386231","journal-title":"IEEE Access"},{"issue":"1","key":"938_CR28","first-page":"697","volume":"18","author":"G Kondal","year":"2026","unstructured":"Kondal G, Singh H (2026) Srivastava S Hybrid semantic-contextual embedding framework for emotion-aware sentiment analysis. Int J Inf Technol 18(1):697\u2013704","journal-title":"Int J Inf Technol"},{"key":"938_CR29","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TMM.2023.3260635","volume":"26","author":"J Li","year":"2023","unstructured":"Li J, Wang X, Lv G (2023) Zeng Z Graphcfc: A directed graph based cross-modal feature complementation approach for multimodal conversational emotion recognition. IEEE Trans Multimedia 26:77\u201389","journal-title":"IEEE Trans Multimedia"},{"key":"938_CR30","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.neucom.2021.05.017","volume":"454","author":"Z Lian","year":"2021","unstructured":"Lian Z, Liu B, Tao J (2021) Decn: Dialogical emotion correction network for conversational emotion recognition. Neurocomputing 454:483\u2013495","journal-title":"Neurocomputing"},{"key":"938_CR31","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2020) RoBERTa: A Robustly Optimized BERT Pretraining Approach. https:\/\/openreview.net\/forum?id=SyxS0T4tvS"},{"key":"938_CR32","unstructured":"Liu Z, Ma P, Wang Y et\u00a0al (2024) KAN 2.0: Kolmogorov-Arnold Networks Meet Science. Preprint at arXiv:2408.10205"},{"key":"938_CR33","unstructured":"Liu Z, Wang Y, Vaidya S, Ruehle F, Halverson J, Soljacic M, Hou TY, Tegmark M (2025a) KAN: Kolmogorov\u2013arnold networks. In: The 13th international conference on learning representations. https:\/\/openreview.net\/forum?id=Ozo7qJ5vZi"},{"key":"938_CR34","unstructured":"Liu N, He X, Laurent T, Giovanni FD, Bronstein MM, Bresson X (2025b) A general graph spectral wavelet convolution via chebyshev order decomposition. In: Forty-second international conference on machine learning. https:\/\/openreview.net\/forum?id=UTvdB2WPSp"},{"issue":"9\u201310","key":"938_CR35","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1016\/j.specom.2011.01.006","volume":"53","author":"R L\u00f3pez-C\u00f3zar","year":"2011","unstructured":"L\u00f3pez-C\u00f3zar R, Silovsky J (2011) Kroul M Enhancement of emotion detection in spoken dialogue systems by combining several information sources. Speech Commun 53(9\u201310):1210\u20131228","journal-title":"Speech Commun"},{"key":"938_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127467","volume":"580","author":"N Lu","year":"2024","unstructured":"Lu N, Tan Z, Qian J (2024) Mrsln: A multimodal residual speaker-lstm network to alleviate the over-smoothing issue for emotion recognition in conversation. Neurocomputing 580:127467","journal-title":"Neurocomputing"},{"key":"938_CR37","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(86):2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html"},{"key":"938_CR38","doi-asserted-by":"publisher","first-page":"6818","DOI":"10.1609\/aaai.v33i01.33016818","volume":"33","author":"N Majumder","year":"2019","unstructured":"Majumder N, Poria S, Hazarika D, Mihalcea R, Gelbukh A, Cambria E (2019) Dialoguernn: An attentive rnn for emotion detection in conversations. Proceedings of the AAAI conference on artificial intelligence 33:6818\u20136825","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"issue":"1","key":"938_CR39","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s10844-025-01005-8","volume":"64","author":"J Min","year":"2026","unstructured":"Min J, Huang X, Cheng Y (2026) Cmkf: Multimodal emotion recognition in conversations based on comamba and kan-fuse. J Intell Inf Syst 64(1):379\u2013402","journal-title":"J Intell Inf Syst"},{"key":"938_CR40","unstructured":"Mustaqeem M, Kwon S (2021) Speech emotion recognition based on deep networks: A review. Annual Conference of KIPS. Korea Information Processing Society, pp 331\u2013334"},{"key":"938_CR41","doi-asserted-by":"crossref","unstructured":"Mu J, Yang S, Li W (2026) Etce-net: Emotion transition and causal emotion entailment network for dialogue emotion recognition. Neurocomputing 669:132536. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231225032084","DOI":"10.1016\/j.neucom.2025.132536"},{"key":"938_CR42","doi-asserted-by":"publisher","first-page":"100943","DOI":"10.1109\/ACCESS.2019.2929050","volume":"7","author":"S Poria","year":"2019","unstructured":"Poria S, Majumder N, Mihalcea R (2019) Hovy E Emotion recognition in conversation: Research challenges, datasets, and recent advances. IEEE access 7:100943\u2013100953","journal-title":"IEEE access"},{"key":"938_CR43","doi-asserted-by":"crossref","unstructured":"Poria S, Hazarika D, Majumder N, Naik G, Cambria E, Mihalcea R (2019b) Meld: A multimodal multi-party dataset for emotion recognition in conversations. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 527\u2013536","DOI":"10.18653\/v1\/P19-1050"},{"key":"938_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128646","volume":"611","author":"X Qi","year":"2025","unstructured":"Qi X, Wen Y, Zhang P (2025) Huang H Mfgcn: Multimodal fusion graph convolutional network for speech emotion recognition. Neurocomputing 611:128646","journal-title":"Neurocomputing"},{"issue":"6","key":"938_CR45","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1037\/h0042519","volume":"65","author":"F Rosenblatt","year":"1958","unstructured":"Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386","journal-title":"Psychol Rev"},{"key":"938_CR46","doi-asserted-by":"crossref","unstructured":"Shah AK, Kadyan V, Kane L (2025) A comprehensive review of emotion recognition using multimedia parameters: challenges, computational intelligence and applications. SN Computer Science 6(5):455","DOI":"10.1007\/s42979-025-03861-1"},{"key":"938_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121393","volume":"686","author":"J Shi","year":"2025","unstructured":"Shi J, Li M, Chen Y, Cui L (2025) Bai L Multimodal graph learning with framelet-based stochastic configuration networks for emotion recognition in conversation. Inf Sci 686:121393","journal-title":"Inf Sci"},{"key":"938_CR48","first-page":"249","volume-title":"Enhancing cloud security through ai-driven intrusion detection utilizing deep learning methods and autoencoder technology","author":"P Sivarambabu","year":"2025","unstructured":"Sivarambabu P, Agrawal R, Tirumala A, Subani SM, Parisae V, Nukala SS (2025) Enhancing cloud security through ai-driven intrusion detection utilizing deep learning methods and autoencoder technology. Concepts and Applications, Generative Artificial Intelligence, pp 249\u2013264"},{"key":"938_CR49","doi-asserted-by":"crossref","unstructured":"Tan X, Gong Z, Gan M, Xie W, Wang W (2025) Graph convolutional network model with a feature compensation module and dual-channel second-order pooling module for multimodal emotion recognition in conversation. J King Saud Univ Comput Inf Sci 37(5):93","DOI":"10.1007\/s44443-025-00091-6"},{"key":"938_CR50","doi-asserted-by":"crossref","unstructured":"Yao B, Shi W (2024) Speaker-centric multimodal fusion networks for emotion recognition in conversations. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 8441\u20138445. IEEE","DOI":"10.1109\/ICASSP48485.2024.10447720"},{"key":"938_CR51","doi-asserted-by":"crossref","unstructured":"Zhang T, Tan Z (2025) Ecerc: evidence-cause attention network for multi-modal emotion recognition in conversation. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 2064\u20132077","DOI":"10.18653\/v1\/2025.acl-long.102"},{"key":"938_CR52","doi-asserted-by":"crossref","unstructured":"Zhang D, Chen F, Chen X (2023) Dualgats: Dual graph attention networks for emotion recognition in conversations. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 7395\u20137408","DOI":"10.18653\/v1\/2023.acl-long.408"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00938-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00938-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00938-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T07:35:11Z","timestamp":1786347311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00938-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":52,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["938"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00938-6","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"30 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"544"}}