{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T18:29:01Z","timestamp":1760898541405,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030678319"},{"type":"electronic","value":"9783030678326"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67832-6_34","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T17:44:48Z","timestamp":1611337488000},"page":"417-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["MusiCoder: A Universal Music-Acoustic Encoder Based on Transformer"],"prefix":"10.1007","author":[{"given":"Yilun","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"34_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"34_CR2","unstructured":"Baevski, A., Schneider, S., Auli, M.: vq-wav2vec: Self-supervised learning of discrete speech representations. arXiv preprint arXiv:1910.05453 (2019)"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Baniya, B.K., Lee, J., Li, Z.N.: Audio feature reduction and analysis for automatic music genre classification. In: 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 457\u2013462. IEEE (2014)","DOI":"10.1109\/SMC.2014.6973950"},{"key":"34_CR4","unstructured":"Bogdanov, D., Won, M., Tovstogan, P., Porter, A., Serra, X.: The mtg-jamendo dataset for automatic music tagging. In: Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML 2019), Long Beach, CA, United States (2019). http:\/\/hdl.handle.net\/10230\/42015"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Bu, J., Tan, S., Chen, C., Wang, C., Wu, H., Zhang, L., He, X.: Music recommendation by unified hypergraph: combining social media information and music content. In: Proceedings of the 18th ACM international conference on Multimedia, pp. 391\u2013400 (2010)","DOI":"10.1145\/1873951.1874005"},{"key":"34_CR6","unstructured":"Carmon, Y., Raghunathan, A., Schmidt, L., Duchi, J.C., Liang, P.S.: Unlabeled data improves adversarial robustness. In: Advances in Neural Information Processing Systems, pp. 11192\u201311203 (2019)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Chi, P.H., Chung, P.H., Wu, T.H., Hsieh, C.C., Li, S.W., Lee, H.y.: Audio albert: a lite bert for self-supervised learning of audio representation. arXiv preprint arXiv:2005.08575 (2020)","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"34_CR8","unstructured":"Choi, K., Fazekas, G., Sandler, M., Cho, K.: Transfer learning for music classification and regression tasks. arXiv preprint arXiv:1703.09179 (2017)"},{"key":"34_CR9","unstructured":"Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555 (2020)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Davis, J., Goadrich, M.: The relationship between precision-recall and roc curves. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 233\u2013240 (2006)","DOI":"10.1145\/1143844.1143874"},{"key":"34_CR11","unstructured":"Defferrard, M., Benzi, K., Vandergheynst, P., Bresson, X.: FMA: a dataset for music analysis. arXiv preprint arXiv:1612.01840 (2016)"},{"key":"34_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"34_CR13","doi-asserted-by":"publisher","unstructured":"Domingues, M., et al.: Music4all: a new music database and its applications, July 2020. https:\/\/doi.org\/10.1109\/IWSSIP48289.2020.9145170","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Ghosal, D., Kolekar, M.H.: Music genre recognition using deep neural networks and transfer learning. In: Interspeech, pp. 2087\u20132091 (2018)","DOI":"10.21437\/Interspeech.2018-2045"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"34_CR16","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"34_CR17","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. In: Advances in Neural Information Processing Systems, pp. 15663\u201315674 (2019)"},{"key":"34_CR18","unstructured":"Huang, C.Z.A., et al.: Music transformer: generating music with long-term structure. In: International Conference on Learning Representations (2018)"},{"key":"34_CR19","unstructured":"Huang, Y.S., Yang, Y.H.: Pop music transformer: generating music with rhythm and harmony. arXiv preprint arXiv:2002.00212 (2020)"},{"key":"34_CR20","unstructured":"Hung, H.T., Chen, Y.H., Mayerl, M., Zangerle, M.V.E., Yang, Y.H.: Mediaeval 2019 emotion and theme recognition task: a vq-vae based approach"},{"key":"34_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"34_CR22","unstructured":"Koutini, K., Chowdhury, S., Haunschmid, V., Eghbal-zadeh, H., Widmer, G.: Emotion and theme recognition in music with frequency-aware RF-regularized cnns. arXiv preprint arXiv:1911.05833 (2019)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Ling, S., Liu, Y., Salazar, J., Kirchhoff, K.: Deep contextualized acoustic representations for semi-supervised speech recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6429\u20136433. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Liu, A.T., Yang, S.W., Chi, P.H., Hsu, P.C., Lee, H.Y.: Mockingjay: unsupervised speech representation learning with deep bidirectional transformer encoders. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6419\u20136423. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"34_CR25","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"34_CR26","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 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"34_CR28","unstructured":"Pons, J., Nieto, O., Prockup, M., Schmidt, E., Ehmann, A., Serra, X.: End-to-end learning for music audio tagging at scale. arXiv preprint arXiv:1711.02520 (2017)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Pujol, P., Macho, D., Nadeu, C.: On real-time mean-and-variance normalization of speech recognition features. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 1, pp. I-I. IEEE (2006)","DOI":"10.1109\/ICASSP.2006.1660135"},{"key":"34_CR30","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018). http:\/\/s3-us-west-2.amazonaws.com\/openai-assets\/researchcovers\/languageunsupervised\/languageunderstandingpaper.pdf"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Song, X., et al.: Speech-xlnet: unsupervised acoustic model pretraining for self-attention networks. arXiv preprint arXiv:1910.10387 (2019)","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"34_CR32","unstructured":"Sturm, B.L.: The gtzan dataset: Its contents, its faults, their effects on evaluation, and its future use. arXiv preprint arXiv:1306.1461 (2013)"},{"issue":"3","key":"34_CR33","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1023\/A:1018628609742","volume":"9","author":"JA Suykens","year":"1999","unstructured":"Suykens, J.A., Vandewalle, J.: Least squares support vector machine classifiers. Neural Process. Lett. 9(3), 293\u2013300 (1999)","journal-title":"Neural Process. Lett."},{"key":"34_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"issue":"1\u20133","key":"34_CR35","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/S0167-6393(98)00033-8","volume":"25","author":"O Viikki","year":"1998","unstructured":"Viikki, O., Laurila, K.: Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Commun. 25(1\u20133), 133\u2013147 (1998)","journal-title":"Speech Commun."},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., Tang, Q., Livescu, K.: Unsupervised pre-training of bidirectional speech encoders via masked reconstruction. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6889\u20136893. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"34_CR38","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, pp. 5753\u20135763 (2019)"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, H., Li, S., Yang, C., Sun, L.: The pmemo dataset for music emotion recognition. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp. 135\u2013142 (2018)","DOI":"10.1145\/3206025.3206037"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: Ernie: enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019)","DOI":"10.18653\/v1\/P19-1139"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67832-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T21:22:42Z","timestamp":1724361762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67832-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678319","9783030678326"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67832-6_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","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":"73","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":"35% - 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":"2,63","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":"2,5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}