{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:44:25Z","timestamp":1776887065084,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620630","type":"print"},{"value":"9789819620647","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2064-7_8","type":"book-chapter","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:24:59Z","timestamp":1735327499000},"page":"101-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Music2MIDI: Pop Music to\u00a0MIDI Piano Cover Generation"],"prefix":"10.1007","author":[{"given":"Tin Yui","family":"Yip","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2861-3306","authenticated-orcid":false,"given":"Chuck-jee","family":"Chau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Ariga, S., Fukayama, S., Goto, M.: Song2Guitar: a difficulty-aware arrangement system for generating guitar solo covers from polyphonic audio of popular music. In: Proceedings of the 18th International Society for Music Information Retrieval Conference, pp. 568\u2013574. ISMIR (2018). https:\/\/doi.org\/10.5281\/zenodo.1417501","DOI":"10.5281\/zenodo.1417501"},{"key":"8_CR2","doi-asserted-by":"publisher","unstructured":"Choi, J., Lee, K.: Pop2piano: Pop audio-based piano cover generation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095653","DOI":"10.1109\/ICASSP49357.2023.10095653"},{"key":"8_CR3","unstructured":"Donahue, C., Thickstun, J., Liang, P.: Melody transcription via generative pre-training. In: Rao, P., et al. (eds.) Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR 2022, Bengaluru, India, 4\u20138 December 2022, pp. 485\u2013492 (2022)"},{"key":"8_CR4","unstructured":"Gardner, J., Simon, I., Manilow, E., Hawthorne, C., Engel, J.H.: MT3: multi-task multitrack music transcription. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)"},{"key":"8_CR5","unstructured":"Gover, M., Zewi, O.: Music translation: generating piano arrangements in different playing levels. In: Rao, P., et al. (eds.) Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR 2022, Bengaluru, India, 4\u20138 December 2022, pp. 36\u201343 (2022)"},{"key":"8_CR6","unstructured":"Hawthorne, C., Simon, I., Swavely, R., Manilow, E., Engel, J.H.: Sequence-to-sequence piano transcription with transformers. In: Lee, J.H., Lerch, A., Duan, Z., Nam, J., Rao, P., van Kranenburg, P., Srinivasamurthy, A. (eds.) Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, 7\u201312 November 2021, pp. 246\u2013253 (2021)"},{"key":"8_CR7","unstructured":"Hawthorne, C., et al.: Enabling factorized piano music modeling and generation with the MAESTRO dataset. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019)"},{"key":"8_CR8","doi-asserted-by":"publisher","unstructured":"Hennequin, R., Khlif, A., Voituret, F., Moussallam, M.: Spleeter: a fast and efficient music source separation tool with pre-trained models. J. Open Source Softw. 5(50), 2154 (2020). https:\/\/doi.org\/10.21105\/joss.02154","DOI":"10.21105\/joss.02154"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Hsiao, W.Y., Liu, J.Y., Yeh, Y.C., Yang, Y.H.: Compound word transformer: learning to compose full-song music over dynamic directed hypergraphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 1, pp. 178\u2013186 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i1.16091","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"8_CR10","doi-asserted-by":"publisher","unstructured":"Huang, Q., Yang, X., Qian, F., Li, Z.: Pop piano music generation with the simplified transformer-xl. In: 2021 33rd Chinese Control and Decision Conference (CCDC), pp. 3818\u20133822 (2021). https:\/\/doi.org\/10.1109\/CCDC52312.2021.9601430","DOI":"10.1109\/CCDC52312.2021.9601430"},{"key":"8_CR11","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1145\/3394171.3413671","DOI":"10.1145\/3394171.3413671"},{"key":"8_CR12","doi-asserted-by":"publisher","unstructured":"Kim, J.W., Bello, J.: Adversarial learning for improved onsets and frames music transcription. In: Proceedings of the 20th International Society for Music Information Retrieval Conference, pp. 670\u2013677. ISMIR (2019). https:\/\/doi.org\/10.5281\/zenodo.3527898","DOI":"10.5281\/zenodo.3527898"},{"key":"8_CR13","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). https:\/\/doi.org\/10.1109\/TASLP.2021.3121991","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR14","doi-asserted-by":"publisher","unstructured":"Manilow, E., Seetharaman, P., Pardo, B.: Simultaneous separation and transcription of mixtures with multiple polyphonic and percussive instruments. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 771\u2013775 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054340","DOI":"10.1109\/ICASSP40776.2020.9054340"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Manilow, E., Wichern, G., Seetharaman, P., Le\u00a0Roux, J.: Cutting music source separation some Slakh: a dataset to study the impact of training data quality and quantity. In: Proceedings of EEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). IEEE (2019)","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"8_CR16","doi-asserted-by":"publisher","unstructured":"Mauch, M., Dixon, S.: PYIN: a fundamental frequency estimator using probabilistic threshold distributions. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, 4\u20139 May 2014, pp. 659\u2013663. IEEE (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6853678","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"8_CR17","doi-asserted-by":"publisher","unstructured":"M\u00fcller, M., \u00d6zer, Y., Krause, M., Pr\u00e4tzlich, T., Driedger, J.: Sync toolbox: a python package for efficient, robust, and accurate music synchronization. J. Open Source Softw. 6(64), 3434 (2021). https:\/\/doi.org\/10.21105\/joss.03434","DOI":"10.21105\/joss.03434"},{"key":"8_CR18","doi-asserted-by":"publisher","unstructured":"Percival, G., Fukayama, S., Goto, M.: Song2Quartet: a system for generating string quartet cover songs from polyphonic audio of popular music. In: Proceedings of the 16th International Society for Music Information Retrieval Conference, pp. 114\u2013120. ISMIR (2018). https:\/\/doi.org\/10.5281\/zenodo.1415014","DOI":"10.5281\/zenodo.1415014"},{"key":"8_CR19","unstructured":"Raffel, C., Ellis, D.P.: Intuitive analysis, creation and manipulation of midi data with pretty_midi. In: 15th International Society for Music Information Retrieval Conference Late Breaking and Demo Papers, pp. 84\u201393 (2014)"},{"key":"8_CR20","unstructured":"Raffel, C., et al.: Mir_eval: a transparent implementation of common MIR metrics. In: Wang, H., Yang, Y., Lee, J.H. (eds.) Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, 27\u201331 October 2014, pp. 367\u2013372 (2014)"},{"key":"8_CR21","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"8_CR22","doi-asserted-by":"publisher","unstructured":"Ren, Y., He, J., Tan, X., Qin, T., Zhao, Z., Liu, T.: Popmag: Pop music accompaniment generation. In: Chen, C.W., et al. (eds.) MM 2020: The 28th ACM International Conference on Multimedia, Virtual Event\/Seattle, WA, USA, 12\u201316 October 2020, pp. 1198\u20131206. ACM (2020). https:\/\/doi.org\/10.1145\/3394171.3413721","DOI":"10.1145\/3394171.3413721"},{"key":"8_CR23","unstructured":"Shazeer, N., Stern, M.: Adafactor: adaptive learning rates with sublinear memory cost. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a080, pp. 4596\u20134604. PMLR (2018)"},{"key":"8_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-030-05716-9_14","volume-title":"MultiMedia Modeling","author":"H Takamori","year":"2019","unstructured":"Takamori, H., Nakatsuka, T., Fukayama, S., Goto, M., Morishima, S.: Audio-based automatic generation of a piano reduction score by considering the musical structure. In: Kompatsiaris, I., Huet, B., Mezaris, V., Gurrin, C., Cheng, W.-H., Vrochidis, S. (eds.) MMM 2019. LNCS, vol. 11296, pp. 169\u2013181. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-05716-9_14"},{"key":"8_CR25","doi-asserted-by":"publisher","unstructured":"Tan, C.P., Guan, S.H., Yang, Y.H.: Picogen: generate piano covers with a two-stage approach. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, ICMR 2024, pp. 1180\u20131184. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3652583.3657626","DOI":"10.1145\/3652583.3657626"},{"key":"8_CR26","unstructured":"Wang, Z., et al.: Pop909: a pop-song dataset for music arrangement generation. In: Proceedings of 21st International Conference on Music Information Retrieval, ISMIR, pp. 38\u201345. ISMIR (2020)"},{"key":"8_CR27","doi-asserted-by":"publisher","unstructured":"Wang, Z., Xu, D., Xia, G., Shan, Y.: Audio-to-symbolic arrangement via cross-modal music representation learning. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 181\u2013185 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747884","DOI":"10.1109\/ICASSP43922.2022.9747884"},{"key":"8_CR28","doi-asserted-by":"publisher","unstructured":"Zeng, M., Tan, X., Wang, R., Ju, Z., Qin, T., Liu, T.Y.: MusicBERT: symbolic music understanding with large-scale pre-training. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 791\u2013800. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.70","DOI":"10.18653\/v1\/2021.findings-acl.70"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2064-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T20:02:39Z","timestamp":1735329759000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2064-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"ISBN":["9789819620630","9789819620647"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2064-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"28 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}