{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:57:04Z","timestamp":1774724224188,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819947515","type":"print"},{"value":"9789819947522","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-4752-2_9","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T16:02:10Z","timestamp":1690732930000},"page":"101-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Music Emotion Recognition Using Multi-head Self-attention-Based Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8712-8071","authenticated-orcid":false,"given":"Yao","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7587-8306","authenticated-orcid":false,"given":"Haoxin","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xujian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiquan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuebo","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/MSP.2021.3106232","volume":"38","author":"JSG Ca\u00f1\u00f3n","year":"2021","unstructured":"Ca\u00f1\u00f3n, J.S.G., et al.: Music emotion recognition: toward new, robust standards in personalized and context-sensitive applications. IEEE Sig. Process. Mag. 38, 106\u2013114 (2021)","journal-title":"IEEE Sig. Process. Mag."},{"issue":"7","key":"9_CR2","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A.P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn. 30(7), 1145\u20131159 (1997)","journal-title":"Pattern Recogn."},{"key":"9_CR3","unstructured":"Chaki, S., Doshi, P., Patnaik, P., Bhattacharya, S.: Attentive RNNs for continuous-time emotion prediction in music clips. In: Chhaya, N., Jaidka, K., Healey, J., Ungar, L., Sinha, A.R. (eds.) Proceedings of the 3rd Workshop on Affective Content Analysis (AffCon 2020) Co-Located with Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, USA, 7 February 2020. CEUR Workshop Proceedings, vol. 2614, pp. 36\u201346. CEUR-WS.org (2020)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chang, W.H., Li, J.L., Lin, Y.S., Lee, C.C.: A genre-affect relationship network with task-specific uncertainty weighting for recognizing induced emotion in music. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2018)","DOI":"10.1109\/ICME.2018.8486570"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Zhao, J., Wang, S.: Multimodal multi-task learning for dimensional and continuous emotion recognition. In: Proceedings of the 7thAnnual Workshop on Audio\/Visual Emotion Challenge, AVEC 2017, pp. 19\u201326. Association for Computing Machinery, New York (2017)","DOI":"10.1145\/3133944.3133949"},{"key":"9_CR6","unstructured":"Chou, Y.H., Chen, I.C., Chang, C.J., Ching, J., Yang, Y.H.: MidiBERT-Piano: large-scale pre-training for symbolic music understanding. ArXiv abs\/2107.05223 (2021)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lu, X., Li, D., Liu, Y.: Video-based emotion recognition using CNN-RNN and C3D hybrid networks. In: Proceedings of the 18thACM International Conference on Multimodal Interaction, ICMI 2016, pp. 445\u2013450. Association for Computing Machinery, New York (2016)","DOI":"10.1145\/2993148.2997632"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Ferreira, L.N., Lelis, L.H.S., Whitehead, J.: Computer-generated music for tabletop role-playing games. In: Lelis, L., Thue, D. (eds.) Proceedings of the Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2020, Virtual, 19\u201323 October 2020, pp. 59\u201365. AAAI Press (2020)","DOI":"10.1609\/aiide.v16i1.7408"},{"issue":"6","key":"9_CR9","doi-asserted-by":"publisher","first-page":"166335","DOI":"10.1007\/s11704-021-0569-4","volume":"16","author":"D Han","year":"2022","unstructured":"Han, D., Kong, Y., Han, J., Wang, G.: A survey of music emotion recognition. Front. Comput. Sci. 16(6), 166335 (2022)","journal-title":"Front. Comput. Sci."},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y.S., Yang, Y.H.: Pop music transformer: beat-based modeling and generation of expressive pop piano compositions. In: Proceedings of the 28th ACM International Conference on Multimedia, MM 2020, pp. 1180\u20131188. Association for Computing Machinery, New York (2020)","DOI":"10.1145\/3394171.3413671"},{"key":"9_CR11","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: Lee, J.H., et al. (eds.) Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, 7\u201312 November 2021, pp. 318\u2013325 (2021)"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"3707","DOI":"10.1109\/TASLP.2021.3121991","volume":"29","author":"Q Kong","year":"2021","unstructured":"Kong, Q., Li, B., Song, X., Wan, Y., Wang, Y.: High-resolution piano transcription with pedals by regressing onset and offset times. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3707\u20133717 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"9_CR13","unstructured":"Lin, Y., Chen, X., Yang, D.: Exploration of music emotion recognition based on MIDI. In: de Souza Britto Jr., A., Gouyon, F., Dixon, S. (eds.) Proceedings of the 14th International Society for Music Information Retrieval Conference, ISMIR 2013, Curitiba, Brazil, 4\u20138 November 2013, pp. 221\u2013226 (2013)"},{"key":"9_CR14","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings. OpenReview.net (2017)"},{"issue":"4","key":"9_CR15","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1007\/s00521-018-3758-9","volume":"32","author":"S Oore","year":"2020","unstructured":"Oore, S., Simon, I., Dieleman, S., Eck, D., Simonyan, K.: This time with feeling: learning expressive musical performance. Neural Comput. Appl. 32(4), 955\u2013967 (2020)","journal-title":"Neural Comput. Appl."},{"key":"9_CR16","unstructured":"Panda, R.E.S., Malheiro, R., Rocha, B., Oliveira, A.P., Paiva, R.P.: Multi-modal music emotion recognition: a new dataset, methodology and comparative analysis. In: 10th International Symposium on Computer Music Multidisciplinary Research (CMMR 2013), pp. 570\u2013582 (2013)"},{"key":"9_CR17","unstructured":"Qiu, J., Chen, C., Zhang, T.: Novel Multi-Task Learning Method for Symbolic Music Emotion Recognition. arXiv preprint arXiv:2201.05782 (2022)"},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39, 1161\u20131178 (1980)","journal-title":"J. Pers. Soc. Psychol."},{"key":"9_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"9_CR20","unstructured":"Won, M., Choi, K., Serra, X.: Semi-supervised music tagging transformer. In: Lee, J.H., et al. (eds.) Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, 7\u201312 November 2021, pp. 769\u2013776 (2021)"},{"key":"9_CR21","unstructured":"Won, M., Ferraro, A., Bogdanov, D., Serra, X.: Evaluation of CNN-based automatic music tagging models. In: Proceedings of 17th Sound and Music Computing (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4752-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T23:08:00Z","timestamp":1690931280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4752-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947515","9789819947522"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4752-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}