{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:40:14Z","timestamp":1774968014873,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T00:00:00Z","timestamp":1688774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T00:00:00Z","timestamp":1688774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702080"],"award-info":[{"award-number":["61702080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-15376-z","type":"journal-article","created":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T09:02:30Z","timestamp":1688806950000},"page":"12519-12534","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["COSMIC: Music emotion recognition combining structure analysis and modal interaction"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5557-7515","authenticated-orcid":false,"given":"Liang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhexu","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjie","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,8]]},"reference":[{"key":"15376_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal Y, Shanker RGR, Alluri V (2021) Transformer-based approach towards music emotion recognition from lyrics. In: European conference on information retrieval, pp 167\u2013175. Springer","DOI":"10.1007\/978-3-030-72240-1_12"},{"issue":"3","key":"15376_CR2","doi-asserted-by":"publisher","first-page":"0173392","DOI":"10.1371\/journal.pone.0173392","volume":"12","author":"A Aljanaki","year":"2017","unstructured":"Aljanaki A, Yang Y-H, Soleymani M (2017) Developing a benchmark for emotional analysis of music. PloS one 12(3):0173392","journal-title":"PloS one"},{"key":"15376_CR3","unstructured":"Baccianella S, Esuli A, Sebastiani F (2010) Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910)"},{"key":"15376_CR4","unstructured":"Benward B, Saker MN (1997) Music in theory and practice vol. 7. McGraw-Hill"},{"key":"15376_CR5","unstructured":"Bertin-Mahieux T, Ellis DPW, Whitman B, amere P (2011) The million song dataset. In: Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR, pp 591\u2013596"},{"key":"15376_CR6","unstructured":"Bhattacharya A, Kadambari K (2018) A multimodal approach towards emotion recognition of music using audio and lyrical content. arXiv:1811.05760"},{"issue":"3","key":"15376_CR7","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1111\/j.0021-8529.2004.00155.x","volume":"62","author":"D Carr","year":"2004","unstructured":"Carr D (2004) Music, meaning, and emotion. J Aesthet Art Crit 62(3):225\u2013234","journal-title":"J Aesthet Art Crit"},{"key":"15376_CR8","doi-asserted-by":"crossref","unstructured":"Choi K, Fazekas G, Sandler MB, Cho K (2017) Convolutional recurrent neural networks for music classification. In: 2017 IEEE International conference on acoustics, speech and signal processing, ICASSP, pp 2392\u20132396. IEEE","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"15376_CR9","unstructured":"Delbouys R, Hennequin R, Piccoli F, Royo-letelier J, Moussallam M (2018) Music mood detection based on audio and lyrics with deep neural net. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR, Paris, pp 370\u2013375"},{"key":"15376_CR10","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the north american chapter of the association for computational linguistics: Human language technologies, volume 1 (Long and Short Papers), pp 4171\u20134186"},{"key":"15376_CR11","unstructured":"Dhariwal P, Jun H, Payne C, Kim JW, Radford A, Sutskever I (2020) Jukebox: A generative model for music. arXiv:2005.00341"},{"issue":"12","key":"15376_CR12","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 (2019) Bidirectional convolutional recurrent sparse network (BCRSN):, an efficient model for music emotion recognition. IEEE Trans Multimed 21(12):3150\u20133163","journal-title":"IEEE Trans Multimed"},{"key":"15376_CR13","doi-asserted-by":"crossref","unstructured":"Eyben F, Weninger F, Gross F, Schuller B (2013) Recent developments in opensmile, the munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International conference on multimedia, pp 835\u2013838","DOI":"10.1145\/2502081.2502224"},{"key":"15376_CR14","unstructured":"Ferreira LN, Whitehead J (2019) Learning to generate music with sentiment. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR, Delft, pp 384\u2013390"},{"key":"15376_CR15","doi-asserted-by":"crossref","unstructured":"Finnegan R (2012) Music, experience, and the anthropology of emotion. In: The cultural study of music, pp 375\u2013385. Routledge","DOI":"10.4324\/9780203149454-42"},{"issue":"4","key":"15376_CR16","doi-asserted-by":"publisher","first-page":"5137","DOI":"10.1007\/s11042-021-11650-0","volume":"81","author":"A Garg","year":"2022","unstructured":"Garg A, Chaturvedi V, Kaur AB, Varshney V, Parashar A (2022) Machine learning model for mapping of music mood and human emotion based on physiological signals. Multimed Tools Appl 81(4):5137\u20135177","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"15376_CR17","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1007\/s11042-009-0332-6","volume":"47","author":"B-J Han","year":"2010","unstructured":"Han B-J, Rho S, Jun S, Hwang E (2010) Music emotion classification and context-based music recommendation. Multimed Tools Appl 47(3):433\u2013460","journal-title":"Multimed Tools Appl"},{"issue":"50","key":"15376_CR18","doi-asserted-by":"publisher","first-page":"2154","DOI":"10.21105\/joss.02154","volume":"5","author":"R Hennequin","year":"2020","unstructured":"Hennequin R, Khlif A, Voituret F, Moussallam M (2020) Spleeter: a fast and efficient music source separation tool with pre-trained models. J Open Source Softw 5(50):2154","journal-title":"J Open Source Softw"},{"issue":"3","key":"15376_CR19","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 (2021) Music emotion recognition using convolutional long short term memory deep neural networks. Eng Sci Technol an Int J 24(3):760\u2013767","journal-title":"Eng Sci Technol an Int J"},{"key":"15376_CR20","unstructured":"Hung H-T, Ching J, Doh S, Kim N, Nam J, Yang Y-H (2021) EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR, Online, pp 318\u2013325"},{"key":"15376_CR21","doi-asserted-by":"crossref","unstructured":"Kumar V, Minz S (2013) Mood classifiaction of lyrics using sentiwordnet. In: 2013 International conference on computer communication and informatics, pp 1\u20135. IEEE","DOI":"10.1109\/ICCCI.2013.6466307"},{"key":"15376_CR22","doi-asserted-by":"crossref","unstructured":"Laurier C, Grivolla J, Herrera P (2008) Multimodal music mood classification using audio and lyrics. In: 2008 7th International conference on machine learning and applications, pp 688\u2013693. IEEE","DOI":"10.1109\/ICMLA.2008.96"},{"issue":"3","key":"15376_CR23","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1109\/TAFFC.2017.2724515","volume":"10","author":"S Mo","year":"2019","unstructured":"Mo S, Niu J (2019) A novel method based on OMPGW method for feature extraction in automatic music mood classification. IEEE Trans Affect Comput 10(3):313\u2013324","journal-title":"IEEE Trans Affect Comput"},{"issue":"1","key":"15376_CR24","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/1687-4722-2013-13","volume":"2013","author":"Y Panagakis","year":"2013","unstructured":"Panagakis Y, Kotropoulos C (2013) Music classification by low-rank semantic mappings. EURASIP J Audio Speech Music Process 2013(1):13","journal-title":"EURASIP J Audio Speech Music Process"},{"issue":"4","key":"15376_CR25","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/TAFFC.2018.2820691","volume":"11","author":"R Panda","year":"2020","unstructured":"Panda R, Malheiro R, Paiva RP (2020) Novel audio features for music emotion recognition. IEEE Trans Affect Comput 11(4):614\u2013626","journal-title":"IEEE Trans Affect Comput"},{"key":"15376_CR26","unstructured":"Panda RES, Malheiro R, Rocha B, Oliveira AP, Paiva RP (2013) 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"},{"key":"15376_CR27","unstructured":"Parisi L, Francia S, Olivastri S, Tavella MS (2019) Exploiting synchronized lyrics and vocal features for music emotion detection. arXiv:1901.04831"},{"issue":"1","key":"15376_CR28","doi-asserted-by":"publisher","first-page":"5","DOI":"10.2478\/jaiscr-2021-0001","volume":"11","author":"JS Rahman","year":"2021","unstructured":"Rahman JS, Gedeon T, Caldwell S, Jones R, Jin Z (2021) Towards effective music therapy for mental health care using machine learning tools: Human affective reasoning and music genres. J Artif Intell Soft Comput Res 11(1):5\u201320","journal-title":"J Artif Intell Soft Comput Res"},{"key":"15376_CR29","doi-asserted-by":"publisher","DOI":"10.1093\/0199263655.001.0001","volume-title":"Deeper than Reason: Emotion and its role in literature, music, and art","author":"J Robinson","year":"2005","unstructured":"Robinson J (2005) Deeper than Reason: Emotion and its role in literature, music, and art. Oxford University Press on Demand, NY"},{"key":"15376_CR30","unstructured":"Shen Y, Tan S, Sordoni A, Courville AC (2019) Ordered neurons: Integrating tree structures into recurrent neural networks. In: 7th International conference on learning representations, ICLR 2019, new orleans"},{"key":"15376_CR31","volume-title":"Engaging music: Essays in music analysis","author":"D Stein","year":"2005","unstructured":"Stein D (2005) Engaging music: Essays in music analysis. Oxford University Press, USA"},{"key":"15376_CR32","doi-asserted-by":"crossref","unstructured":"Won M, Oramas S, Nieto O, Gouyon F, Serra X (2021) Multimodal metric learning for tag-based music retrieval. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 591\u2013595. IEEE","DOI":"10.1109\/ICASSP39728.2021.9413514"},{"key":"15376_CR33","unstructured":"Won M, Salamon J, Bryan NJ, Mysore GJ, Serra X (2021) Emotion embedding spaces for matching music to stories. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR, Online, pp 777\u2013785"},{"key":"15376_CR34","doi-asserted-by":"crossref","unstructured":"Xiong Y, Su F, Wang Q (2017) Automatic music mood classification by learning cross-media relevance between audio and lyrics. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp 961\u2013966. IEEE","DOI":"10.1109\/ICME.2017.8019341"},{"key":"15376_CR35","unstructured":"Xu M, Li X, Xianyu H, Tian J, Meng F, Chen W (2015) Multi-scale approaches to the MediaEval 2015 \u201cEmotion in Music\u201d task. In: Working notes proceedings of the MediaEval 2015 workshop. CEUR Workshop proceedings, vol. 1436. CEUR-WS.org"},{"issue":"9","key":"15376_CR36","doi-asserted-by":"publisher","first-page":"13559","DOI":"10.1007\/s11042-020-10386-7","volume":"80","author":"S Yousefian Jazi","year":"2021","unstructured":"Yousefian Jazi S, Kaedi M, Fatemi A (2021) An emotion-aware music recommender system: bridging the user\u2019s interaction and music recommendation. Multimed Tools Appl 80(9):13559\u201313574","journal-title":"Multimed Tools Appl"},{"key":"15376_CR37","unstructured":"Zhang Y, Jiang J, Xia G, Dixon S (2022) Interpreting song lyrics with an audio-informed pre-trained language model. In: Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR, Bangaluru, pp 19\u201326"},{"key":"15376_CR38","doi-asserted-by":"crossref","unstructured":"Zhang K, Zhang H, Li S, Yang C, Sun L (2018) The PMEmo dataset for music emotion recognition. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, ICMR, Yokohama, pp 135\u2013142","DOI":"10.1145\/3206025.3206037"},{"key":"15376_CR39","doi-asserted-by":"crossref","unstructured":"Zhang M, Zhu Y, Zhang W, Zhu Y, Feng T (2022) Modularized composite attention network for continuous music emotion recognition. Multimed Tools Appl, 1\u201323","DOI":"10.1007\/s11042-022-13577-6"},{"key":"15376_CR40","doi-asserted-by":"crossref","unstructured":"Zhao J, Ru G, Yu Y, Wu Y, Li D, Li W (2022) Multimodal music emotion recognition with hierarchical cross-modal attention network. In: IEEE International conference on multimedia and expo, ICME 2022, pp 1\u20136. IEEE","DOI":"10.1109\/ICME52920.2022.9859812"},{"key":"15376_CR41","doi-asserted-by":"crossref","unstructured":"Zhou J, Chen X, Yang D (2019) Multimodel music emotion recognition using unsupervised deep neural networks. In: Proceedings of the 6th Conference on Sound and Music Technology (CSMT), pp 27\u201339. Springer","DOI":"10.1007\/978-981-13-8707-4_3"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15376-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15376-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15376-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T10:35:00Z","timestamp":1706265300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15376-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,8]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["15376"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15376-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,8]]},"assertion":[{"value":"7 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}