{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:04:42Z","timestamp":1764403482465,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032020413","type":"print"},{"value":"9783032020420","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02042-0_27","type":"book-chapter","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:27:04Z","timestamp":1759991224000},"page":"349-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DiffVel: Note-Level MIDI Velocity Estimation for\u00a0Piano Performance by\u00a0a\u00a0Double Conditioned Diffusion Model"],"prefix":"10.1007","author":[{"given":"Hyon","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"27_CR1","unstructured":"Amit, S., Nachmani, E., Wolf, L.: Segdiff: image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2022)"},{"key":"27_CR2","doi-asserted-by":"publisher","unstructured":"Benetos, E., Dixon, S., Giannoulis, D., Kirchhoff, H., Klapuri, A.: Automatic music transcription: challenges and future directions. J. Intell. Inform. Syst. 41(3), 407\u2013434 (2013). https:\/\/doi.org\/10.1007\/s10844-013-0258-3","DOI":"10.1007\/s10844-013-0258-3"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Cheuk, K.W., Sawata, R., Uesaka, T., Murata, N., Takahashi, N., Takahashi, S., Herremans, D., Mitsufuji, Y.: Diffroll: Diffusion-based generative music transcription with unsupervised pretraining capability. In: ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing. pp.\u00a01\u20135 (2022)","DOI":"10.1109\/ICASSP49357.2023.10095935"},{"key":"27_CR4","unstructured":"Dannenberg, R.B.: The interpretation of midi velocity. In: International Conference on Mathematics and Computing (2006)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Devaney, J., Mandel, M.: An evaluation of score-informed methods for estimating fundamental frequency and power from polyphonic audio. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 181\u2013185 (2017)","DOI":"10.1109\/ICASSP.2017.7952142"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Ewert, S., M\u00fcller, M.: Estimating note intensities in music recordings. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 385\u2013388. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5946421"},{"issue":"1","key":"27_CR7","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1121\/1.1376133","volume":"110","author":"W Goebl","year":"2001","unstructured":"Goebl, W.: Melody lead in piano performance: expressive device or artifact? J. Acoust. Society America 110(1), 563\u2013572 (2001)","journal-title":"J. Acoust. Society America"},{"issue":"4","key":"27_CR8","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1080\/09298215.2012.731071","volume":"41","author":"M Grachten","year":"2012","unstructured":"Grachten, M., Widmer, G.: Linear basis models for prediction and analysis of musical expression. J. New Music Res. 41(4), 311\u2013322 (2012)","journal-title":"J. New Music Res."},{"key":"27_CR9","unstructured":"Hamond, L.: The pedagogical use of technology-mediated feedback in a higher education piano studio: an exploratory action case study. Ph.D. thesis, UCL (University College London) (2017)"},{"issue":"3","key":"27_CR10","doi-asserted-by":"publisher","first-page":"581","DOI":"10.20504\/opus2019c2526","volume":"25","author":"L Hamond","year":"2019","unstructured":"Hamond, L., Welch, G.F., Himonides, E.: The pedagogical use of visual feedback for enhancing dynamics in higher education piano learning and performance. Opus 25(3), 581\u2013601 (2019)","journal-title":"Opus"},{"key":"27_CR11","unstructured":"Hawthorne, C., et al.: Enabling factorized piano music modeling and generation with the maestro dataset. In: International Conference on Learning Representations (2018)"},{"issue":"1","key":"27_CR12","first-page":"34","volume":"68","author":"D Jeong","year":"2019","unstructured":"Jeong, D., Kwon, T., Nam, J.: Note-intensity estimation of piano recordings using coarsely aligned midi score. J. Audio Eng. Society 68(1), 34\u201347 (2019)","journal-title":"J. Audio Eng. Society"},{"key":"27_CR13","unstructured":"Jeong, D., Nam, J.: Note intensity estimation of piano recordings by score-informed NMF. In: 2017 AES International Conference on Semantic Audio. Audio Engineering Society (2017)"},{"key":"27_CR14","unstructured":"Kim, H., Miron, M., Serra, X.: Score-informed midi velocity estimation for piano performance by film conditioning. In: Proceedings of the International Conference on Sound and Music Computing (2023)"},{"key":"27_CR15","doi-asserted-by":"publisher","unstructured":"Kim, H., Ramoneda, P., Miron, M., Serra, X.: An overview of automatic piano performance assessment within the music education context. In: Proceedings of the 14th International Conference on Computer Supported Education (CSEDU). vol.\u00a01, pp. 465\u2013474 (2022). https:\/\/doi.org\/10.5220\/0011137600003182","DOI":"10.5220\/0011137600003182"},{"key":"27_CR16","unstructured":"Kim, J.W., Bello, J.P.: Adversarial learning for improved onsets and frames music transcription. arXiv preprint arXiv:1906.08512 (2019)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., Park, J.M., Rhyu, S., Nam, J., Lee, K.: Quantitative analysis of piano performance proficiency focusing on difference between hands. PLoS ONE 16 (2021)","DOI":"10.1371\/journal.pone.0250299"},{"key":"27_CR18","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":"27_CR19","unstructured":"Kosta, K., Bandtlow, O.F., Chew, E.: Outliers in performed loudness transitions: An analysis of chopin mazurka recordings. In: International Conference for Music Perception and Cognition (ICMPC), pp. 601\u2013604. California, USA (2016)"},{"key":"27_CR20","doi-asserted-by":"publisher","unstructured":"Kosta, K., Bandtlow, O.F., Chew, E.: Dynamics and relativity: practical implications of dynamic markings in the score. J. New Music Res. 47(5), 438\u2013461 (2018). https:\/\/doi.org\/10.1080\/09298215.2018.1486430","DOI":"10.1080\/09298215.2018.1486430"},{"issue":"2","key":"27_CR21","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1080\/17459737.2016.1193237","volume":"10","author":"K Kosta","year":"2016","unstructured":"Kosta, K., Ram\u00edrez, R., Bandtlow, O.F., Chew, E.: Mapping between dynamic markings and performed loudness: a machine learning approach. J. Math. Music 10(2), 149\u2013172 (2016)","journal-title":"J. Math. Music"},{"key":"27_CR22","unstructured":"Manilow, E., Pardo, B.: Bespoke neural networks for score-informed source separation. arXiv preprint arXiv:2009.13729 (2020)"},{"key":"27_CR23","unstructured":"Meseguer-Brocal, G., Peeters, G.: Conditioned-u-net: introducing a control mechanism in the u-net for multiple source separations. arXiv preprint arXiv:1907.01277 (2019)"},{"key":"27_CR24","unstructured":"Miron, M., Carabias, J.J., Janer, J.: Improving score-informed source separation for classical music through note refinement. In: Proceedings of the 16th International Society for Music Information Retrieval (ISMIR) Conference. M\u00e1laga, Spain (2015)"},{"key":"27_CR25","unstructured":"M\u00fcller, M., Konz, V., Bogler, W., Arifi-M., V.: Saarland music data (smd) (2011)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de\u00a0Vries, H., Dumoulin, V., Courville, A.: Film: Visual reasoning with a general conditioning layer. arXiv preprint arXiv:1709.07871 (2018). http:\/\/arxiv.org\/abs\/1709.07871","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"27_CR27","unstructured":"Qu, Y., Qin, Y., Chao, L., Qian, H., Wang, Z., Xia, G.: Modeling perceptual loudness of piano tone: Theory and applications. arXiv preprint arXiv:2209.10674 (2022)"},{"key":"27_CR28","doi-asserted-by":"publisher","unstructured":"Simonetta, F., Avanzini, F., Ntalampiras, S.: A perceptual measure for evaluating the resynthesis of automatic music transcriptions. Multimed. Tools Appl. 3, 1\u201321 (2022). https:\/\/doi.org\/10.1007\/s11042-022-12476-0","DOI":"10.1007\/s11042-022-12476-0"},{"key":"27_CR29","doi-asserted-by":"publisher","first-page":"2083","DOI":"10.1109\/TASLP.2021.3082331","volume":"29","author":"O Slizovskaia","year":"2021","unstructured":"Slizovskaia, O., Haro, G., G\u00f3mez, E.: Conditioned source separation for musical instrument performances. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 2083\u20132095 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Music and Sound Generation in the AI Era"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02042-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:27:14Z","timestamp":1759991234000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02042-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"ISBN":["9783032020413","9783032020420"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02042-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"assertion":[{"value":"10 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CMMR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Computer Music Multidisciplinary Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmmr2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cmmr2023.gttm.jp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}