{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:21:26Z","timestamp":1760055686030,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":31,"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_11","type":"book-chapter","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:24:10Z","timestamp":1759991050000},"page":"149-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pitch Class and\u00a0Octave-Based Pitch Embedding Training Strategies for\u00a0Symbolic Music Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6166-1596","authenticated-orcid":false,"given":"Yuqiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-298X","authenticated-orcid":false,"given":"Shengchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2580-0007","authenticated-orcid":false,"given":"Gy\u00f6rgy","family":"Fazekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"11_CR1","unstructured":"Simon, I., Oore, S.: Performance rNN: generating music with expressive timing and dynamics (2017). https:\/\/magenta.tensorflow.org\/performance-rnn"},{"key":"11_CR2","unstructured":"Meade, N., Barreyre, N., Lowe, S.C., Oore, S.: Exploring conditioning for generative music systems with human-interpretable controls. In: International Conference on Computational Creativity (2019)"},{"key":"11_CR3","unstructured":"Huang, C.Z.A., et al.: Music transformer. In: International Conference on Learning Representations (2019)"},{"key":"11_CR4","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. Association for Computing Machinery, NY, USA (2020)","DOI":"10.1145\/3394171.3413671"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978\u20132988. Association for Computational Linguistics, Florence, Italy (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1285","DOI":"10.18653\/v1\/P19-1285"},{"key":"11_CR6","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":"11_CR7","doi-asserted-by":"publisher","unstructured":"Guo, Z., Kang, J., Herremans, D.: A domain-knowledge-Inspired music embedding space and a novel attention mechanism for symbolic music modeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37(4), pp. 5070\u20135077 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i4.25635","DOI":"10.1609\/aaai.v37i4.25635"},{"issue":"4","key":"11_CR8","doi-asserted-by":"publisher","first-page":"12","DOI":"10.2307\/3679550","volume":"13","author":"B Laden","year":"1989","unstructured":"Laden, B., Keefe, D.H.: The representation of pitch in a neural net model of chord classification. Comput. Music. J. 13(4), 12\u201326 (1989). https:\/\/doi.org\/10.2307\/3679550","journal-title":"Comput. Music. J."},{"key":"11_CR9","unstructured":"Ens, J., Pasquier, P.: Quantifying musical style: ranking symbolic music based on similarity to a style (2020)"},{"issue":"1","key":"11_CR10","doi-asserted-by":"publisher","first-page":"113","DOI":"10.5334\/tismir.114","volume":"5","author":"J Yust","year":"2022","unstructured":"Yust, J., Lee, J., Pinsky, E.: A clustering-based approach to automatic harmonic analysis: an exploratory study of harmony and form in mozart\u2019s piano sonatas. Trans. Int. Soc. Music Inf. Retrieval 5(1), 113\u2013128 (2022). https:\/\/doi.org\/10.5334\/tismir.114","journal-title":"Trans. Int. Soc. Music Inf. Retrieval"},{"key":"11_CR11","unstructured":"Gao, J., He, D., Tan, X., Qin, T., Wang, L., Liu, T.: Representation degeneration problem in training natural language generation models. In: International Conference on Learning Representations (2022)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Briot, J.P., Hadjeres, G., Pachet, F.D.: Deep learning techniques for music generation \u2013 A survey. In: Computational Synthesis and Creative Systems (2020)","DOI":"10.1007\/978-3-319-70163-9"},{"key":"11_CR13","unstructured":"Ji, S., Luo, J., Yang, X.: A comprehensive survey on deep music generation: multi-level representations, algorithms, evaluations, and future directions. arXiv:2011.06801 [cs, eess] (2020)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Mozer, M.C.: Connectionist music composition based on melodic, stylistic and psychophysical constraints. Comput. Sci. Tech. Rep. (476) (1990)","DOI":"10.7551\/mitpress\/4804.003.0018"},{"key":"11_CR15","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1037\/0033-295X.89.4.305","volume":"89","author":"RN Shepard","year":"1982","unstructured":"Shepard, R.N.: Geometrical approximations to the structure of musical pitch. Psychol. Rev. 89, 305\u2013333 (1982). https:\/\/doi.org\/10.1037\/0033-295X.89.4.305","journal-title":"Psychol. Rev."},{"issue":"3","key":"11_CR16","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/0010-0285(79)90016-1","volume":"11","author":"CL Krumhansl","year":"1979","unstructured":"Krumhansl, C.L.: The psychological representation of musical pitch in a tonal context. Cogn. Psychol. 11(3), 346\u2013374 (1979). https:\/\/doi.org\/10.1016\/0010-0285(79)90016-1","journal-title":"Cogn. Psychol."},{"issue":"4","key":"11_CR17","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1037\/0033-295X.89.4.334","volume":"89","author":"CL Krumhansl","year":"1982","unstructured":"Krumhansl, C.L., Kessler, E.J.: Tracing the dynamic changes in perceived tonal organization in a spatial representation of musical keys. Psychol. Rev. 89(4), 334\u2013368 (1982)","journal-title":"Psychol. Rev."},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Liang, H., Lei, W., Chan, P.Y., Yang, Z., Sun, M., Chua, T.S.: PiRhDy: learning pitch-, rhythm-, and dynamics-aware embeddings for symbolic music. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 574\u2013582 (2020). https:\/\/doi.org\/10.1145\/3394171.3414032","DOI":"10.1145\/3394171.3414032"},{"key":"11_CR19","unstructured":"Euler, L.: Tentamen novae theoriae musicae: ex certissimis harmoniae principiis dilucide expositae. Saint Petersburg Academy (1739)"},{"key":"11_CR20","doi-asserted-by":"publisher","unstructured":"Chuan, C.H., Herremans, D.: Modeling temporal tonal relations in polyphonic music through deep networks with a novel image-based representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.11880","DOI":"10.1609\/aaai.v32i1.11880"},{"issue":"1","key":"11_CR21","doi-asserted-by":"publisher","first-page":"153","DOI":"10.5334\/tismir.46","volume":"3","author":"R Lieck","year":"2020","unstructured":"Lieck, R., Moss, F.C., Rohrmeier, M.: The tonal diffusion model. Trans. Int. Soc. Music Inf. Retrieval 3(1), 153\u2013164 (2020). https:\/\/doi.org\/10.5334\/tismir.46","journal-title":"Trans. Int. Soc. Music Inf. Retrieval"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Yu, S., Song, J., Kim, H., Lee, S.M., Ryu, W.J., Yoon, S.: Rare tokens degenerate all tokens: improving neural text generation via adaptive gradient gating for rare token embeddings. arXiv:2109.03127 (2022)","DOI":"10.18653\/v1\/2022.acl-long.3"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Wallace, E., Wang, Y., Li, S., Singh, S., Gardner, M.: Do NLP models know numbers? Probing numeracy in embeddings. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5307\u20135315. Association for Computational Linguistics, Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1534"},{"key":"11_CR24","unstructured":"Gorishniy, Y., Rubachev, I., Babenko, A.: On embeddings for numerical features in tabular deep learning. In: Thirty-Sixth Conference on Neural Information Processing Systems. New Orleans (2022)"},{"key":"11_CR25","unstructured":"Lazzari, N., Poltronieri, A., Presutti, V.: Pitchclass2vec: symbolic music structure segmentation with chord embeddings. In: Workshop on Artificial Intelligence and Creativity, p.\u00a017 (2022)"},{"issue":"1","key":"11_CR26","doi-asserted-by":"publisher","first-page":"223","DOI":"10.5334\/tismir.83","volume":"4","author":"D Chawin","year":"2021","unstructured":"Chawin, D., Rom, U.B.: Sliding-window pitch-class histograms as a means of modeling musical form. Trans. Int. Soc. Music Inf. Retrieval 4(1), 223\u2013235 (2021). https:\/\/doi.org\/10.5334\/tismir.83","journal-title":"Trans. Int. Soc. Music Inf. Retrieval"},{"key":"11_CR27","unstructured":"Moore, B.C.J.: An Introduction to the Psychology of Hearing. BRILL (2012)"},{"key":"11_CR28","unstructured":"Wu, S.L., Yang, Y.H.: The jazz transformer on the front line: exploring the shortcomings of AI-composed music through quantitative measures. In: The 21st International Society for Music Information Retrieval Conference. arXiv:2008.01307, Montr\u00e9al, Canada (2020)"},{"key":"11_CR29","unstructured":"Dong, H.W., Chen, K., McAuley, J., Berg-Kirkpatrick, T.: MusPy: a toolkit for symbolic music generation. In: The 21st International Society for Music Information Retrieval Conference. arXiv:2008.01951, Montr\u00e9al, Canada (2020)"},{"key":"11_CR30","unstructured":"Yang, L.C., Chou, S.Y., Yang, Y.H.: MidiNet: a convolutional generative adversarial network for symbolic-domain music generation. In: The 18th International Society for Music Information Retrieval Conference. Suzhou, China (2017)"},{"key":"11_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations. arXiv:1711.05101 (2019)"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T06:24:22Z","timestamp":1759991062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02042-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"ISBN":["9783032020413","9783032020420"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02042-0_11","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"}}]}}