{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T07:28:29Z","timestamp":1749022109618,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466731"},{"type":"electronic","value":"9783031466748"}],"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\/978-3-031-46674-8_12","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"168-181","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Symbolic and Acoustic: Multi-domain Music Emotion Modeling for\u00a0Instrumental Music"],"prefix":"10.1007","author":[{"given":"Kexin","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Xulong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"unstructured":"de Berardinis, J., Cangelosi, A., Coutinho, E.: The multiple voices of musical emotions: source separation for improving music emotion recognition models and their interpretability. In: Proceedings of the 21st International Society for Music Information Retrieval Conference, pp. 310\u2013317 (2020)","key":"12_CR1"},{"unstructured":"Chen, N., Wang, S.: High-level music descriptor extraction algorithm based on combination of multi-channel cnns and lstm. In: Proceedings of the 18th International Society for Music Information Retrieval Conference, pp. 509\u2013514 (2017)","key":"12_CR2"},{"unstructured":"Choi, K., Fazekas, G., Sandler, M., Cho, K.: Transfer learning for music classification and regression tasks. In: 18th International Society for Music Information Retrieval Conference, pp. 141\u2013149. International Society for Music Information Retrieval (2017)","key":"12_CR3"},{"unstructured":"Chou, Y.H., Chen, I., Chang, C.J., Ching, J., Yang, Y.H., et al.: Midibert-piano: large-scale pre-training for symbolic music understanding. arXiv:2107.05223 (2021)","key":"12_CR4"},{"unstructured":"Chou, Y.H., Chen, I., Chang, C.J., Ching, J., Yang, Y.H., et al.: Midibert-piano: Large-scale pre-training for symbolic music understanding. arXiv:2107.05223 (2021)","key":"12_CR5"},{"unstructured":"Coutinho, E., Trigeorgis, G., Zafeiriou, S., Schuller, B.: Automatically estimating emotion in music with deep long-short term memory recurrent neural networks. In: Working Notes Proceedings of the MediaEval 2015 Workshop, vol. 1436, pp. 1\u20133 (2015)","key":"12_CR6"},{"unstructured":"Ferreira, L., Whitehead, J.: Learning to generate music with sentiment. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, pp. 384\u2013390 (2019)","key":"12_CR7"},{"doi-asserted-by":"crossref","unstructured":"Fukayama, S., Goto, M.: Music emotion recognition with adaptive aggregation of gaussian process regressors. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 71\u201375. IEEE (2016)","key":"12_CR8","DOI":"10.1109\/ICASSP.2016.7471639"},{"issue":"6","key":"12_CR9","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/MSP.2021.3106232","volume":"38","author":"JS G\u00f3mez-Ca\u00f1\u00f3n","year":"2021","unstructured":"G\u00f3mez-Ca\u00f1\u00f3n, J.S., et al.: Music emotion recognition: toward new, robust standards in personalized and context-sensitive applications. IEEE Signal Process. Mag. 38(6), 106\u2013114 (2021)","journal-title":"IEEE Signal Process. Mag."},{"doi-asserted-by":"crossref","unstructured":"Grekow, J., Ra\u015b, Z.W.: Detecting emotions in classical music from midi files. In: Foundations of Intelligent Systems: 18th International Symposium, pp. 261\u2013270. Springer (2009)","key":"12_CR10","DOI":"10.1007\/978-3-642-04125-9_29"},{"unstructured":"Hawthorne, C., et al.: Onsets and frames: Dual-objective piano transcription. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, pp. 50\u201357 (2018)","key":"12_CR11"},{"unstructured":"Hawthorne, C., et al.: Enabling factorized piano music modeling and generation with the MAESTRO dataset. In: 7th International Conference on Learning Representations (2019)","key":"12_CR12"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"12_CR13","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Huang, Y.S., Chou, S.Y., Yang, Y.H.: Music thumbnailing via neural attention modeling of music emotion. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, pp. 347\u2013350. IEEE (2017)","key":"12_CR14","DOI":"10.1109\/APSIPA.2017.8282049"},{"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, pp. 1180\u20131188 (2020)","key":"12_CR15","DOI":"10.1145\/3394171.3413671"},{"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: Proceedings of the 22nd International Society for Music Information Retrieval Conference, pp. 318\u2013325 (2021)","key":"12_CR16"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (2015)","key":"12_CR17"},{"issue":"3","key":"12_CR18","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1037\/a0031388","volume":"13","author":"P Laukka","year":"2013","unstructured":"Laukka, P., Eerola, T., Thingujam, N.S., Yamasaki, T., Beller, G.: Universal and culture-specific factors in the recognition and performance of musical affect expressions. Emotion 13(3), 434 (2013)","journal-title":"Emotion"},{"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: 2016 IEEE International Conference on Multimedia and Expo, pp. 1\u20136. IEEE (2016)","key":"12_CR19","DOI":"10.1109\/ICME.2016.7552956"},{"unstructured":"Lin, Y., Chen, X., Yang, D.: Exploration of music emotion recognition based on midi. In: Proceedings of the 14th International Society for Music Information Retrieval Conference, pp. 221\u2013226 (2013)","key":"12_CR20"},{"unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. In: 5th International Conference on Learning Representations (2017)","key":"12_CR21"},{"unstructured":"Liu, X., Chen, Q., Wu, X., Liu, Y., Liu, Y.: Cnn based music emotion classification. arXiv:1704.05665 (2017)","key":"12_CR22"},{"doi-asserted-by":"crossref","unstructured":"Malik, M., Adavanne, S., Drossos, K., Virtanen, T., Ticha, D., Jarina, R.: Stacked convolutional and recurrent neural networks for music emotion recognition. arXiv:1706.02292 (2017)","key":"12_CR23","DOI":"10.23919\/EUSIPCO.2017.8081505"},{"doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference, vol. 8, pp. 18\u201325. Citeseer (2015)","key":"12_CR24","DOI":"10.25080\/Majora-7b98e3ed-003"},{"unstructured":"McKay, C., Fujinaga, I.: jsymbolic: a feature extractor for midi files. In: Proceedings of the 2006 International Computer Music Conference (2006)","key":"12_CR25"},{"issue":"4","key":"12_CR26","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."},{"unstructured":"Panda, R., Malheiro, R., Paiva, R.P.: Musical texture and expressivity features for music emotion recognition. In: 19th International Society for Music Information Retrieval Conference, pp. 383\u2013391 (2018)","key":"12_CR27"},{"unstructured":"Panda, R., Malheiro, R., Rocha, B., Oliveira, A., Paiva, R.P.: Multi-modal music emotion recognition: a new dataset, methodology and comparative analysis. In: International Symposium on Computer Music Multidisciplinary Research (2013)","key":"12_CR28"},{"unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (2019)","key":"12_CR29"},{"unstructured":"Qiu, J., Chen, C., Zhang, T.: A novel multi-task learning method for symbolic music emotion recognition. arXiv:2201.05782 (2022)","key":"12_CR30"},{"doi-asserted-by":"publisher","unstructured":"Ru, G., Zhang, X., Wang, J., Cheng, N., Xiao, J.: Improving music genre classification from multi-modal properties of music and genre correlations perspective. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10097241","key":"12_CR31","DOI":"10.1109\/ICASSP49357.2023.10097241"},{"doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N., Xiao, J.: Emomix: emotion mixing via diffusion models for emotional speech synthesis. In: 24th Annual Conference of the International Speech Communication Association (2023)","key":"12_CR32","DOI":"10.21437\/Interspeech.2023-1317"},{"doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, vol. 2019, p. 6558. NIH Public Access (2019)","key":"12_CR33","DOI":"10.18653\/v1\/P19-1656"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)","key":"12_CR34"},{"unstructured":"Won, M., Ferraro, A., Bogdanov, D., Serra, X.: Evaluation of cnn-based automatic music tagging models. arXiv:2006.00751 (2020)","key":"12_CR35"},{"doi-asserted-by":"crossref","unstructured":"Xu, J., Li, X., Hao, Y., Yang, G.: Source separation improves music emotion recognition. In: Proceedings of International Conference on Multimedia Retrieval, pp. 423\u2013426 (2014)","key":"12_CR36","DOI":"10.1145\/2578726.2578784"},{"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: 2022 IEEE International Conference on Multimedia and Expo, pp. 1\u20136. IEEE (2022)","key":"12_CR37","DOI":"10.1109\/ICME52920.2022.9859812"},{"doi-asserted-by":"publisher","unstructured":"Zhao, J., Wu, Y., Wen, L., Ma, L., Ruan, L., Wang, W., Li, W.: Improving automatic piano transcription by refined feature fusion and weighted loss. In: Proceedings of the 9th Conference on Sound and Music Technology. pp. 43\u201353. Springer, Cham (2023). doi: https:\/\/doi.org\/10.1007\/978-981-19-4703-2_4","key":"12_CR38","DOI":"10.1007\/978-981-19-4703-2_4"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46674-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:16:55Z","timestamp":1699103815000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46674-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466731","9783031466748"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46674-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"216","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.97","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.77","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}