{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:09:00Z","timestamp":1780636140567,"version":"3.54.1"},"reference-count":101,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100018525","name":"Key Research and Development Program of Sichuan Province","doi-asserted-by":"publisher","award":["24ZDYF0199"],"award-info":[{"award-number":["24ZDYF0199"]}],"id":[{"id":"10.13039\/501100018525","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Sichuan Provincial Natural Science Foundation","award":["25ZNSFSC0022"],"award-info":[{"award-number":["25ZNSFSC0022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072419"],"award-info":[{"award-number":["62072419"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00530-025-01871-w","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T03:11:54Z","timestamp":1749006714000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A survey on music emotion recognition using learning models"],"prefix":"10.1007","volume":"31","author":[{"given":"Yixin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xujian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanpeng","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxin","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiquan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuebo","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"1871_CR1","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/MSP.2021.3106232","volume":"38","author":"J Ca\u00f1\u00f3n","year":"2021","unstructured":"Ca\u00f1\u00f3n, J., Cano, E., Eerola, T., Herrera, P., Hu, X., Yang, Y., G\u00f3mez, E.: Music emotion recognition: Toward new, robust standards in personalized and context-sensitive applications. IEEE Signal Process. Mag. 38, 106\u2013114 (2021)","journal-title":"IEEE Signal Process. Mag."},{"key":"1871_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Shen, J., Zhu, L., Kankanhalli, M.S., Nie, L.: Exploiting music play sequence for music recommendation. In: Sierra, C. (ed.) IJCAI, pp. 3654\u20133660 (2017)","DOI":"10.24963\/ijcai.2017\/511"},{"key":"1871_CR3","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.cogr.2022.06.001","volume":"2","author":"C Yu","year":"2022","unstructured":"Yu, C., Wang, M.: Survey of emotion recognition methods using eeg information. Cognit. Robot. 2, 132\u2013146 (2022)","journal-title":"Cognit. Robot."},{"issue":"2","key":"1871_CR4","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1109\/TASL.2007.911513","volume":"16","author":"Y Yang","year":"2008","unstructured":"Yang, Y., Lin, Y., Su, Y., Chen, H.H.: A regression approach to music emotion recognition. IEEE Trans. Speech Audio Process. 16(2), 448\u2013457 (2008)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"1871_CR5","doi-asserted-by":"crossref","unstructured":"Li, X., Xianyu, H., Tian, J., Chen, W., Meng, F., Xu, M., Cai, L.: A deep bidirectional long short-term memory based multi-scale approach for music dynamic emotion prediction. In: ICASSP, pp. 544\u2013548 (2016)","DOI":"10.1109\/ICASSP.2016.7471734"},{"key":"1871_CR6","doi-asserted-by":"crossref","unstructured":"Weninger, F., Eyben, F., Schuller, B.W.: On-line continuous-time music mood regression with deep recurrent neural networks. In: ICASSP, pp. 5412\u20135416 (2014)","DOI":"10.1109\/ICASSP.2014.6854637"},{"key":"1871_CR7","doi-asserted-by":"publisher","first-page":"246","DOI":"10.2307\/1415746","volume":"48","author":"K Hevner","year":"1936","unstructured":"Hevner, K.: Experimental studies of the elements of expression in music. Am. J. Psychol. 48, 246\u2013268 (1936)","journal-title":"Am. J. Psychol."},{"key":"1871_CR8","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1017\/S0954579405050340","volume":"17","author":"J Posner","year":"2005","unstructured":"Posner, J., Russell, J.A., Peterson, B.S.: The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology. Dev. Psychopathol. 17, 715\u2013734 (2005)","journal-title":"Dev. Psychopathol."},{"issue":"4","key":"1871_CR9","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1111\/1467-9280.00157","volume":"10","author":"A Tellegen","year":"1999","unstructured":"Tellegen, A., Watson, D., Clark, L.A.: On the dimensional and hierarchical structure of affect. Psychol. Sci. 10(4), 297\u2013303 (1999)","journal-title":"Psychol. Sci."},{"key":"1871_CR10","unstructured":"Liu, X.-n.: A music emotion classifier construction algorithm of neural network based on relevant feedback. J.  Northwest Univ. 71(33), 267\u2013282 (2012)"},{"key":"1871_CR11","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Wang, H., Jeng, S.: The acoustic emotion gaussians model for emotion-based music annotation and retrieval. In: Babaguchi, N., Aizawa, K., Smith, J.R., Satoh, S., Plagemann, T., Hua, X., Yan, R. (eds.) ACM MM, pp. 89\u201398 (2012)","DOI":"10.1145\/2393347.2393367"},{"key":"1871_CR12","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhong, E., Horner, A., Yang, Q.: Music emotion recognition by multi-label multi-layer multi-instance multi-view learning. In: Hua, K.A., Rui, Y., Steinmetz, R., Hanjalic, A., Natsev, A., Zhu, W. (eds.) ACM MM, pp. 117\u2013126 (2014)","DOI":"10.1145\/2647868.2654904"},{"key":"1871_CR13","doi-asserted-by":"crossref","unstructured":"Xianyu, H., Li, X., Chen, W., Meng, F., Tian, J., Xu, M., Cai, L.: SVR based double-scale regression for dynamic emotion prediction in music. In: ICASSP, pp. 549\u2013553 (2016)","DOI":"10.1109\/ICASSP.2016.7471735"},{"key":"1871_CR14","unstructured":"Lartillot, O., Toiviainen, P.: MIR in matlab (II): A toolbox for musical feature extraction from audio. In: ISMIR, pp. 127\u2013130 (2007)"},{"key":"1871_CR15","unstructured":"Mathieu, B., Essid, S., Fillon, T., Prado, J., Richard, G.: Yaafe, an easy to use and efficient audio feature extraction software. In: ISMIR, pp. 441\u2013446 (2010)"},{"key":"1871_CR16","unstructured":"Wen, H.: Review on speech emotion recognition. J. Softw. 25(1), 37\u201350 (2014)"},{"key":"1871_CR17","doi-asserted-by":"crossref","unstructured":"Chen, P., Zhao, L., Xin, Z., Qiang, Y., Zhang, M., Li, T.: A scheme of MIDI music emotion classification based on fuzzy theme extraction and neural network. In: CIS, pp. 323\u2013326 (2016)","DOI":"10.1109\/CIS.2016.0079"},{"key":"1871_CR18","doi-asserted-by":"crossref","unstructured":"Barthet, M., Fazekas, G., Sandler, M.: Multidisciplinary perspectives on music emotion recognition: Implications for content and context-based models (2012)","DOI":"10.1007\/978-3-642-41248-6_13"},{"key":"1871_CR19","unstructured":"Hu, X., Downie, J.S., Ehmann, A.F.: Lyric text mining in music mood classification. In: ISMIR, pp. 411\u2013416 (2009)"},{"key":"1871_CR20","unstructured":"Hu, Y., Chen, X., Yang, D.: Lyric-based song emotion detection with affective lexicon and fuzzy clustering method. In: ISMIR, pp. 123\u2013128 (2009)"},{"key":"1871_CR21","doi-asserted-by":"crossref","unstructured":"Dakshina, K., Sridhar, R.: LDA Based Emotion Recognition from Lyrics, pp. 187\u2013194 (2014)","DOI":"10.1007\/978-3-319-07353-8_22"},{"key":"1871_CR22","doi-asserted-by":"crossref","unstructured":"Thammasan, N., Fukui, K., Numao, M.: Application of deep belief networks in eeg-based dynamic music-emotion recognition. In: IJCNN, pp. 881\u2013888 (2016)","DOI":"10.1109\/IJCNN.2016.7727292"},{"key":"1871_CR23","unstructured":"Hu, X., Li, F., Ng, T.J.: On the relationships between music-induced emotion and physiological signals. In: ISMIR, pp. 362\u2013369 (2018)"},{"key":"1871_CR24","doi-asserted-by":"crossref","unstructured":"Nawa, N.E., Callan, D.E., Mokhtari, P., Ando, H., Iversen, J.R.: Decoding music-induced experienced emotions using functional magnetic resonance imaging - preliminary results. In: IJCNN, pp. 1\u20137 (2018)","DOI":"10.1109\/IJCNN.2018.8489752"},{"key":"1871_CR25","doi-asserted-by":"crossref","unstructured":"Chen, Y.-A., Wang, J.-C., Yang, Y.-H., Chen, H.: Linear regression-based adaptation of music emotion recognition models for personalization. In: (ICASSP), pp. 2149\u20132153 (2014)","DOI":"10.1109\/ICASSP.2014.6853979"},{"key":"1871_CR26","doi-asserted-by":"crossref","unstructured":"Chiang, W.C., Wang, J.S., Hsu, Y.L.: A music emotion recognition algorithm with hierarchical svm based classifiers. In: 2014 International Symposium on Computer, Consumer and Control, pp. 1249\u20131252 (2014)","DOI":"10.1109\/IS3C.2014.323"},{"key":"1871_CR27","doi-asserted-by":"crossref","unstructured":"Soleymani, M., Aljanaki, A., Yang, Y., Caro, M.N., Eyben, F., Markov, K., Schuller, B.W., Veltkamp, R.C., Weninger, F., Wiering, F.: Emotional analysis of music: A comparison of methods. In: ACM MM, pp. 1161\u20131164 (2014)","DOI":"10.1145\/2647868.2655019"},{"key":"1871_CR28","doi-asserted-by":"crossref","unstructured":"Fukayama, S., Goto, M.: Music emotion recognition with adaptive aggregation of gaussian process regressors. In: ICASSP, pp. 71\u201375 (2016)","DOI":"10.1109\/ICASSP.2016.7471639"},{"key":"1871_CR29","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TASLP.2017.2693565","volume":"25","author":"Y Chen","year":"2017","unstructured":"Chen, Y., Wang, J., Yang, Y., Chen, H.H.: Component tying for mixture model adaptation in personalization of music emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 25, 1409\u20131420 (2017)","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"1871_CR30","unstructured":"Markov, K., Iwata, M., Matsui, T.: Music emotion recognition using gaussian processes. In: Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop, Barcelona, Spain, October 18-19, 2013, vol. 1043 (2013)"},{"key":"1871_CR31","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/TAFFC.2016.2598569","volume":"9","author":"R Malheiro","year":"2018","unstructured":"Malheiro, R., Panda, R., Gomes, P., Paiva, R.P.: Emotionally-relevant features for classification and regression of music lyrics. IEEE Trans. Affect. Comput. 9, 240\u2013254 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1871_CR32","doi-asserted-by":"crossref","unstructured":"Chen, S., Lee, Y., Hsieh, W., Wang, J.: Music emotion recognition using deep gaussian process. In: APSIPA, pp. 495\u2013498 (2015)","DOI":"10.1109\/APSIPA.2015.7415321"},{"key":"1871_CR33","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1109\/TAFFC.2015.2396151","volume":"6","author":"Y Liu","year":"2015","unstructured":"Liu, Y., Liu, Y., Zhao, Y., Hua, K.A.: What strikes the strings of your heart? - feature mining for music emotion analysis. IEEE Trans. Affect. Comput. 6, 247\u2013260 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1871_CR34","unstructured":"Liu, X., Chen, Q., Wu, X., Liu, Y., Liu, Y.: CNN based music emotion classification. CoRR abs\/1704.05665 (2017)"},{"key":"1871_CR35","doi-asserted-by":"crossref","unstructured":"Keelawat, P., Thammasan, N., Kijsirikul, B., Numao, M.: Subject-independent emotion recognition during music listening based on eeg using deep convolutional neural networks. In: CSPA, pp. 21\u201326 (2019)","DOI":"10.1109\/CSPA.2019.8696054"},{"key":"1871_CR36","doi-asserted-by":"crossref","unstructured":"Liu, H., Fang, Y., Huang, Q.: Music emotion recognition using a variant of recurrent neural network. In: Proceedings of the 2018 International Conference on Mathematics, Modeling, Simulation and Statistics Application (MMSSA 2018) (2019)","DOI":"10.2991\/mmssa-18.2019.4"},{"key":"1871_CR37","unstructured":"Chowdhury, S., Vall, A., Haunschmid, V., Widmer, G.: Towards explainable music emotion recognition: The route via mid-level features. In: ISMIR, pp. 237\u2013243 (2019)"},{"key":"1871_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, J., Yoshii, K.: Multimodal multifaceted music emotion recognition based on self-attentive fusion of psychology-inspired symbolic and acoustic features. In: APSIPA ASC, pp. 1641\u20131645 (2023)","DOI":"10.1109\/APSIPAASC58517.2023.10317539"},{"key":"1871_CR39","unstructured":"Silva, A.C.M., Silva, D.F., Marcacini, R.M.: Heterogeneous graph neural network for music emotion recognition. In: ISMIR, pp. 667\u2013674 (2022)"},{"key":"1871_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, K., Zhang, X., Wang, J., Cheng, N., Xiao, J.: Symbolic and acoustic: Multi-domain music emotion modeling for instrumental music. In: ADMA, vol. 14179, pp. 168\u2013181 (2023)","DOI":"10.1007\/978-3-031-46674-8_12"},{"key":"1871_CR41","doi-asserted-by":"crossref","unstructured":"Yang, P., Kuang, S., Wu, C., Hsu, J.: Predicting music emotion by using convolutional neural network. In: HCIBGO, vol. 12204, pp. 266\u2013275 (2020)","DOI":"10.1007\/978-3-030-50341-3_21"},{"key":"1871_CR42","doi-asserted-by":"publisher","first-page":"5017","DOI":"10.1007\/s11042-021-11584-7","volume":"81","author":"R Orjesek","year":"2022","unstructured":"Orjesek, R., Jarina, R., Chmulik, M.: End-to-end music emotion variation detection using iteratively reconstructed deep features. Multimedia Tools and Applications 81, 5017\u20135031 (2022)","journal-title":"Multimedia Tools and Applications"},{"key":"1871_CR43","doi-asserted-by":"crossref","unstructured":"Li, X., Tian, J., Xu, M., Ning, Y., Cai, L.: Dblstm-based multi-scale fusion for dynamic emotion prediction in music. In: ICME, pp. 1\u20136 (2016)","DOI":"10.1109\/ICME.2016.7552956"},{"key":"1871_CR44","unstructured":"Kumar, V.B., Kathiravan, M.: Emotion recognition from midi musical file using enhanced residual gated recurrent unit architecture. Frontiers in Computer Science (2023)"},{"key":"1871_CR45","unstructured":"Chang, X., Zhang, X., Zhang, H., Ran, Y.: Music emotion prediction using recurrent neural networks. ArXiv abs\/2405.06747 (2024)"},{"key":"1871_CR46","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1109\/TMM.2019.2918739","volume":"21","author":"Y Dong","year":"2019","unstructured":"Dong, Y., Yang, X., Zhao, X., Li, J.: Bidirectional convolutional recurrent sparse network (BCRSN): an efficient model for music emotion recognition. IEEE Trans. Multimedia 21, 3150\u20133163 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"1871_CR47","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1016\/j.jestch.2020.10.009","volume":"24","author":"S Hizlisoy","year":"2021","unstructured":"Hizlisoy, S., Yildirim, S., Tufekci, Z.: Music emotion recognition using convolutional long short term memory deep neural networks. Engineering Science and Technology, an International Journal 24, 760\u2013767 (2021)","journal-title":"Engineering Science and Technology, an International Journal"},{"key":"1871_CR48","doi-asserted-by":"crossref","unstructured":"Yakovyna, V.S., Korniienko, V.V.: Music emotion classification using a hybrid cnn-lstm model. Applied Aspects of Information Technology (2023)","DOI":"10.15276\/aait.06.2023.28"},{"key":"1871_CR49","unstructured":"Chaki, S., Doshi, P., Patnaik, P., Bhattacharya, S.: Attentive rnns for continuous-time emotion prediction in music clips. In: AAAI, vol. 2614, pp. 36\u201346 (2020)"},{"key":"1871_CR50","doi-asserted-by":"crossref","unstructured":"Ma, Y., Li, X., Xu, M., Jia, J., Cai, L.: Multi-scale context based attention for dynamic music emotion prediction. In: ACM MM, pp. 1443\u20131450 (2017)","DOI":"10.1145\/3123266.3123408"},{"key":"1871_CR51","doi-asserted-by":"crossref","unstructured":"Agrawal, Y., Shanker, R.G.R., Alluri, V.: Transformer-based approach towards music emotion recognition from lyrics. In: ECIR, vol. 12657, pp. 167\u2013175 (2021)","DOI":"10.1007\/978-3-030-72240-1_12"},{"key":"1871_CR52","unstructured":"Qiu, J., Chen, C.L.P., Zhang, T.: A novel multi-task learning method for symbolic music emotion recognition. CoRR abs\/2201.05782 (2022)"},{"key":"1871_CR53","doi-asserted-by":"publisher","first-page":"7319","DOI":"10.1007\/s11042-022-13577-6","volume":"82","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Zhu, Y., Zhang, W., Zhu, Y., Feng, T.: Modularized composite attention network for continuous music emotion recognition. MMultimedia Tools and Applications 82, 7319\u20137341 (2023)","journal-title":"MMultimedia Tools and Applications"},{"key":"1871_CR54","doi-asserted-by":"crossref","unstructured":"Chang, W., Li, J., Lin, Y., Lee, C.: A genre-affect relationship network with task-specific uncertainty weighting for recognizing induced emotion in music. In: ICME, pp. 1\u20136 (2018)","DOI":"10.1109\/ICME.2018.8486570"},{"key":"1871_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Cai, D., Zhang, D.: Application and algorithm optimization of music emotion recognition in piano performance evaluation. Environ. Soc. Psychol. 9(4), 1\u201316 (2024)","DOI":"10.54517\/esp.v9i4.2344"},{"key":"1871_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110200","volume":"148","author":"P-C Chang","year":"2024","unstructured":"Chang, P.-C., Chen, Y.-S., Lee, C.-H.: Iiof: Intra- and inter-feature orthogonal fusion of local and global features for music emotion recognition. Pattern Recogn. 148, 110200 (2024)","journal-title":"Pattern Recogn."},{"key":"1871_CR57","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112034","volume":"164","author":"X Han","year":"2024","unstructured":"Han, X., Chen, F., Ban, J.: A gai-based multi-scale convolution and attention mechanism model for music emotion recognition and recommendation from physiological data. Appl. Soft Comput. 164, 112034 (2024)","journal-title":"Appl. Soft Comput."},{"issue":"4","key":"1871_CR58","first-page":"224","volume":"15","author":"S Ma","year":"2024","unstructured":"Ma, S., Zhou, R.: Violin music emotion recognition with fusion of cnn-bigru and attention mechanism. Inf. 15(4), 224 (2024)","journal-title":"Inf."},{"key":"1871_CR59","doi-asserted-by":"crossref","unstructured":"Huang, M., Rong, W., Arjannikov, T., Jiang, N., Xiong, Z.: Bi-modal deep boltzmann machine based musical emotion classification. In: ICANN, vol. 9887, pp. 199\u2013207 (2016)","DOI":"10.1007\/978-3-319-44781-0_24"},{"key":"1871_CR60","unstructured":"Delbouys, R., Hennequin, R., Piccoli, F., Royo-Letelier, J., Moussallam, M.: Music mood detection based on audio and lyrics with deep neural net. In: ISMIR, pp. 370\u2013375 (2018)"},{"key":"1871_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, J., Chen, X., Yang, D.: Multimodel Music Emotion Recognition Using Unsupervised Deep Neural Networks, pp. 27\u201339 (2019)","DOI":"10.1007\/978-981-13-8707-4_3"},{"key":"1871_CR62","first-page":"1","volume":"2020","author":"C Chen","year":"2020","unstructured":"Chen, C., Li, Q.: A multimodal music emotion classification method based on multifeature combined network classifier. Math. Probl. Eng. 2020, 1\u201311 (2020)","journal-title":"Math. Probl. Eng."},{"key":"1871_CR63","doi-asserted-by":"publisher","first-page":"355","DOI":"10.11591\/eei.v12i1.4231","volume":"12","author":"AS Sams","year":"2023","unstructured":"Sams, A.S., Zahra, A.: Multimodal music emotion recognition in indonesian songs based on CNN-LSTM, XLNet transformers. Bulletin of Electrical Engineering and Informatics 12, 355\u2013364 (2023)","journal-title":"Bulletin of Electrical Engineering and Informatics"},{"key":"1871_CR64","first-page":"13","volume":"2022","author":"G Tong","year":"2022","unstructured":"Tong, G., Ding, B.: Multimodal music emotion recognition method based on the combination of knowledge distillation and transfer learning 2022, 13 (2022)","journal-title":"Multimodal music emotion recognition method based on the combination of knowledge distillation and transfer learning"},{"key":"1871_CR65","doi-asserted-by":"crossref","unstructured":"Shi, X., Li, X., Toda, T.: Multimodal fusion of music theory-inspired and self-supervised representations for improved emotion recognition. In: Annual Conference of the International Speech Communication Association, pp. 2024\u20132350 (2024)","DOI":"10.21437\/Interspeech.2024-2350"},{"key":"1871_CR66","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s44196-024-00489-6","volume":"17","author":"J Wang","year":"2024","unstructured":"Wang, J., Sharifi, A., Gadekallu, T.R., Shankar, A.: Mmd-mii model: A multilayered analysis and multimodal integration interaction approach revolutionizing music emotion classification. Int. J. Comput. Intell. Syst. 17, 99 (2024)","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"1871_CR67","first-page":"9","volume":"2022","author":"X Jia","year":"2022","unstructured":"Jia, X., Bhardwaj, A.: Music emotion classification method based on deep learning and explicit sparse attention network. Comput. Intell. Neurosci. 2022, 9 (2022)","journal-title":"Comput. Intell. Neurosci."},{"key":"1871_CR68","doi-asserted-by":"crossref","unstructured":"Guo, G., Gao, P., Zheng, X., Ji, C.: Multimodal emotion recognition using CNN-SVM with data augmentation. In: BIBM, pp. 3008\u20133014 (2022)","DOI":"10.1109\/BIBM55620.2022.9994936"},{"key":"1871_CR69","doi-asserted-by":"crossref","unstructured":"Zhao, J., Ru, G., Yu, Y., Wu, Y., Li, D., Li, W.: Multimodal music emotion recognition with hierarchical cross-modal attention network. In: ICME, pp. 1\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859812"},{"key":"1871_CR70","doi-asserted-by":"crossref","unstructured":"Turnbull, D., Barrington, L., Torres, D.A., Lanckriet, G.R.G.: Towards musical query-by-semantic-description using the CAL500 data set. In: Kraaij, W., Vries, A.P., Clarke, C.L.A., Fuhr, N., Kando, N. (eds.) SIGIR, pp. 439\u2013446 (2007)","DOI":"10.1145\/1277741.1277817"},{"key":"1871_CR71","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, J., Yang, Y., Wang, H.: Towards time-varying music auto-tagging based on CAL500 expansion. In: ICME, pp. 1\u20136 (2014)","DOI":"10.1109\/ICME.2014.6890290"},{"key":"1871_CR72","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yang, Y., Wang, J., Chen, H.H.: The AMG1608 dataset for music emotion recognition. In: ICASSP, pp. 693\u2013697 (2015)","DOI":"10.1109\/ICASSP.2015.7178058"},{"key":"1871_CR73","doi-asserted-by":"crossref","unstructured":"Aljanaki, A., Yang, Y.-H., Soleymani, M.: Developing a benchmark for emotional analysis of music. PLoS ONE 12(3), e0173392 (2017)","DOI":"10.1371\/journal.pone.0173392"},{"key":"1871_CR74","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1177\/0305735610362821","volume":"39","author":"T Eerola","year":"2011","unstructured":"Eerola, T., Vuoskoski, J.K.: A comparison of the discrete and dimensional models of emotion in music. Psychol. Music 39, 18\u201349 (2011)","journal-title":"Psychol. Music"},{"key":"1871_CR75","unstructured":"Hung, H., Ching, J., Doh, S., Kim, N., Nam, J., Yang, Y.: EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation. In: ISMIR, pp. 318\u2013325 (2021)"},{"key":"1871_CR76","doi-asserted-by":"crossref","unstructured":"Soleymani, M., Caro, M.N., Schmidt, E.M., Sha, C.-Y., Yang, Y.-H.: 1000 songs for emotional analysis of music. In: CrowdMM \u201913 (2013)","DOI":"10.1145\/2506364.2506365"},{"key":"1871_CR77","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","volume":"3","author":"S Koelstra","year":"2012","unstructured":"Koelstra, S., M\u00fchl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., Nijholt, A., Patras, I.: Deap: A database for emotion analysis; using physiological signals. IEEE Trans. Affect. Comput. 3, 18\u201331 (2012)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1871_CR78","doi-asserted-by":"crossref","unstructured":"Zhao, J., Ru, G., Yu, Y., Wu, Y., Li, D., Li, W.: Multimodal music emotion recognition with hierarchical cross-modal attention network. In: ICME, pp. 1\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9859812"},{"key":"1871_CR79","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"1871_CR80","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) ICML. Proceedings of Machine Learning Research, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"1871_CR81","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., Lample, G.: Llama: Open and efficient foundation language models. CoRR abs\/2302.13971 (2023)"},{"key":"1871_CR82","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.aej.2024.10.059","volume":"113","author":"H Zhao","year":"2025","unstructured":"Zhao, H., Jin, L.: Iot-based approach to multimodal music emotion recognition. Alex. Eng. J. 113, 19\u201331 (2025)","journal-title":"Alex. Eng. J."},{"key":"1871_CR83","doi-asserted-by":"publisher","first-page":"9284","DOI":"10.1016\/j.eswa.2015.08.029","volume":"42","author":"S Deng","year":"2015","unstructured":"Deng, S., Wang, D., Li, X., Xu, G.: Exploring user emotion in microblogs for music recommendation. Expert Syst. Appl. 42, 9284\u20139293 (2015)","journal-title":"Expert Syst. Appl."},{"key":"1871_CR84","doi-asserted-by":"crossref","unstructured":"Niu, N.: Music emotion recognition model using gated recurrent unit networks and multi-feature extraction. Mobile Information Systems (2022)","DOI":"10.1155\/2022\/5732687"},{"key":"1871_CR85","doi-asserted-by":"publisher","DOI":"10.1016\/j.sctalk.2023.100222","volume":"6","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Xu, W., Zhang, W., Jiang, Q.: A music recommendation system based on psychotherapy. Science Talks 6, 100222 (2023)","journal-title":"Science Talks"},{"key":"1871_CR86","doi-asserted-by":"crossref","unstructured":"Ram\u00edrez, R., Planas, J., Escud\u00e9, N., Mercad\u00e9, J.J., Farriols, C.: Eeg-based analysis of the emotional effect of music therapy on palliative care cancer patients. Front. Psychol. 9, 324998 (2018)","DOI":"10.3389\/fpsyg.2018.00254"},{"key":"1871_CR87","doi-asserted-by":"publisher","first-page":"187","DOI":"10.4236\/jbise.2020.138018","volume":"13","author":"A Byrns","year":"2020","unstructured":"Byrns, A., Abdessalem, H., Cuesta, M., Bruneau, M., Belleville, S., Frasson, C.: Eeg analysis of the contribution of music therapy and virtual reality to the improvement of cognition in alzheimers disease. J. Biomed. Sci. Eng. 13, 187\u2013201 (2020)","journal-title":"J. Biomed. Sci. Eng."},{"key":"1871_CR88","unstructured":"Ferreira, L., Whitehead, J.: Learning to generate music with sentiment. In: Flexer, A., Peeters, G., Urbano, J., Volk, A. (eds.) ISMIR, pp. 384\u2013390 (2019)"},{"key":"1871_CR89","first-page":"13","volume":"13","author":"S Nag","year":"2017","unstructured":"Nag, S., Sanyal, S., Banerjee, A., Sengupta, R., Ghosh, D.: Music of brain and music on brain: a novel eeg sonification approach. Cogn. Neurodyn. 13, 13\u201331 (2017)","journal-title":"Cogn. Neurodyn."},{"key":"1871_CR90","doi-asserted-by":"crossref","unstructured":"Li, Y., Zheng, W.: Emotion recognition and regulation based on stacked sparse auto-encoder network and personalized reconfigurable music. Mathematics 9(6), 593 (2021)","DOI":"10.3390\/math9060593"},{"key":"1871_CR91","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Mu, J., Xie, J., Hu, B., Liu, G.: Music emotion recognition based on temporal convolutional attention network using EEG. Front. Hum. Neurosci. 18, 1324897 (2024)","DOI":"10.3389\/fnhum.2024.1324897"},{"key":"1871_CR92","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1007\/s12031-022-02061-3","volume":"72","author":"J Deng","year":"2022","unstructured":"Deng, J., Chen, Y., Zeng, W., Luo, X., Li, Y.: Brain response of major depressive disorder patients to emotionally positive and negative music. J. Mol. Neurosci. 72, 2094\u20132105 (2022)","journal-title":"J. Mol. Neurosci."},{"key":"1871_CR93","doi-asserted-by":"crossref","unstructured":"Su, Y., Liu, Y., Xiao, Y., Ma, J., Li, D.: A review of artificial intelligence methods enabled music-evoked EEG emotion recognition and their applications. Front. Neurosci. 18, 1400444 (2024)","DOI":"10.3389\/fnins.2024.1400444"},{"issue":"2","key":"1871_CR94","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1093\/jmt\/18.2.62","volume":"18","author":"DB Taylor","year":"1981","unstructured":"Taylor, D.B.: Music in general hospital treatment from 1900 to 1950. J. Music Ther. 18(2), 62\u201373 (1981)","journal-title":"J. Music Ther."},{"key":"1871_CR95","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/s10548-012-0254-x","volume":"26","author":"J Fachner","year":"2012","unstructured":"Fachner, J., Gold, C., Erkkil\u00e4, J.: Music therapy modulates fronto-temporal activity in rest-eeg in depressed clients. Brain Topogr. 26, 338\u2013354 (2012)","journal-title":"Brain Topogr."},{"key":"1871_CR96","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1037\/h0094123","volume":"11","author":"R Steinberg","year":"1992","unstructured":"Steinberg, R., Giinther, W., Stiltz, I., Rondot, P.: Eeg-mapping during music stimulation. Psychomusicology: A Journal of Research in Music Cognition 11, 157\u2013170 (1992)","journal-title":"Psychomusicology: A Journal of Research in Music Cognition"},{"key":"1871_CR97","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.physa.2015.10.030","volume":"444","author":"A Banerjee","year":"2016","unstructured":"Banerjee, A., Sanyal, S., Patranabis, A., Banerjee, K., Guhathakurta, T., Sengupta, R., Ghosh, D., Ghose, P.: Study on brain dynamics by non linear analysis of music induced eeg signals. Physica A-statistical Mechanics and Its Applications 444, 110\u2013120 (2016)","journal-title":"Physica A-statistical Mechanics and Its Applications"},{"key":"1871_CR98","doi-asserted-by":"publisher","first-page":"27096","DOI":"10.1007\/s10489-023-04967-w","volume":"53","author":"MJ Lucia-Mulas","year":"2023","unstructured":"Lucia-Mulas, M.J., Revuelta-Sanz, P., Ru\u00edz-Mezcua, B., Gonz\u00e1lez-Carrasco, I.: Automatic music emotion classification model for movie soundtrack subtitling based on neuroscientific premises. Appl. Intell. 53, 27096\u201327109 (2023)","journal-title":"Appl. Intell."},{"key":"1871_CR99","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.patrec.2022.08.014","volume":"166","author":"D Matos","year":"2022","unstructured":"Matos, D., Ramos, W., Silva, M., Romanhol, L., Nascimento, E.R.: A multimodal hyperlapse method based on video and songs\u2019 emotion alignment. Pattern Recognit. Lett. 166, 174\u2013181 (2022)","journal-title":"Pattern Recognit. Lett."},{"issue":"23","key":"1871_CR100","doi-asserted-by":"publisher","first-page":"9284","DOI":"10.1016\/j.eswa.2015.08.029","volume":"42","author":"S Deng","year":"2015","unstructured":"Deng, S., Wang, D., Li, X., Xu, G.: Exploring user emotion in microblogs for music recommendation. Expert Syst. Appl. 42(23), 9284\u20139293 (2015)","journal-title":"Expert Syst. Appl."},{"key":"1871_CR101","unstructured":"Ferreira, L., Whitehead, J.: Learning to generate music with sentiment. In: ISMIR, pp. 384\u2013390 (2019)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01871-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01871-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01871-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:00:41Z","timestamp":1757926841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01871-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":101,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1871"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01871-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"13 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"278"}}