{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:28:04Z","timestamp":1777631284482,"version":"3.51.4"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032243492","type":"print"},{"value":"9783032243508","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-24350-8_17","type":"book-chapter","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:23:26Z","timestamp":1777433006000},"page":"252-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Probing for Advanced Music Theory Concepts in Generative Music Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4375-0657","authenticated-orcid":false,"given":"Derek","family":"Kwan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1033-5931","authenticated-orcid":false,"given":"Patrick J.","family":"Donnelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Aghazadeh, E., Fayyaz, M., Yaghoobzadeh, Y.: Metaphors in pre-trained language models: probing and generalization across datasets and languages. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. vol.\u00a01, pp. 2037\u20132050. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.144","DOI":"10.18653\/v1\/2022.acl-long.144"},{"key":"17_CR2","unstructured":"Akhondzadeh, M.S., Lingam, V., Bojchevski, A.: Probing graph representations. In: Ruiz, F., Dy, J., van\u00a0de Meent, J.W. (eds.) Proceedings of The 26th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol.\u00a0206, pp. 11630\u201311649. PMLR (2023). https:\/\/proceedings.mlr.press\/v206\/akhondzadeh23a.html, Accessed 26 Oct 2025"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Alain, G., Bengio, Y.: Understanding intermediate layers using linear classifier probes. https:\/\/doi.org\/10.48550\/arXiv.1610.01644, Accessed 29 Oct 2025","DOI":"10.48550\/arXiv.1610.01644"},{"key":"17_CR4","unstructured":"Alain, G., Bengio, Y.: Understanding intermediate layers using linear classifier probes. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=HJ4-rAVtl, Accessed 28 Oct 2025"},{"key":"17_CR5","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Calzolari, N., et al., (eds.) Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 4218\u20134222. European Language Resources Association (2020). https:\/\/aclanthology.org\/2020.lrec-1.520\/, Accessed 30 Oct 2025"},{"issue":"1","key":"17_CR6","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/coli_a_00422","volume":"48","author":"Y Belinkov","year":"2022","unstructured":"Belinkov, Y.: Probing classifiers: promises, shortcomings, and advances. Comput. Linguist. 48(1), 207\u2013219 (2022). https:\/\/doi.org\/10.1162\/coli_a_00422","journal-title":"Comput. Linguist."},{"key":"17_CR7","unstructured":"Belinkov, Y., M\u00e0rquez, L., Sajjad, H., Durrani, N., Dalvi, F., Glass, J.: Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks. In: Kondrak, G., Watanabe, T. (eds.) Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1\u201310. Asian Federation of Natural Language Processing (2017). https:\/\/aclanthology.org\/I17-1001\/, Accessed 26 Oct 2025"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Bogdanov, D., et al.: ESSENTIA: an open-source library for sound and music analysis. In: Proceedings of the 21st ACM International Conference on Multimedia, New York, NY, USA, pp. 855\u2013858. MM \u201913, Association for Computing Machinery (2013). https:\/\/doi.org\/10.1145\/2502081.2502229","DOI":"10.1145\/2502081.2502229"},{"key":"17_CR9","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, Accessed 30 Oct 2025"},{"key":"17_CR10","doi-asserted-by":"publisher","unstructured":"Brown, J.C.: Fundamental frequency tracking and applications to musical signal analysis. In: Beauchamp, J.W. (ed.) Analysis, Synthesis, and Perception of Musical Sounds: The Sound of Music, pp. 90\u2013121. Springer (2007). https:\/\/doi.org\/10.1007\/978-0-387-32576-7_2","DOI":"10.1007\/978-0-387-32576-7_2"},{"key":"17_CR11","unstructured":"Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108\u2013122 (2013). https:\/\/hdl.handle.net\/2268\/154357, Accessed 28 Jan 2026"},{"key":"17_CR12","doi-asserted-by":"publisher","unstructured":"Castellon, R., Donahue, C., Liang, P.: Codified audio language modeling learns useful representations for music information retrieval. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference, pp. 88\u201396. ISMIR (2021). https:\/\/doi.org\/10.5281\/zenodo.5624605, Accessed 31 Oct 2025","DOI":"10.5281\/zenodo.5624605"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers (2019). https:\/\/doi.org\/10.48550\/arXiv.1904.10509, Accessed 02 Nov 2025","DOI":"10.48550\/arXiv.1904.10509"},{"key":"17_CR14","unstructured":"Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators. In: International Conference on Learning Representations (2019), https:\/\/openreview.net\/forum?id=r1xMH1BtvB, Accessed 01 Nov 2025"},{"key":"17_CR15","unstructured":"Copet, J., et al.: Simple and controllable music generation. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems. vol.\u00a036, pp. 47704\u201347720. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/hash\/94b472a1842cd7c56dcb125fb2765fbd-Abstract-Conference.html, Accessed 21 Oct 2025"},{"key":"17_CR16","unstructured":"D\u00e9fossez, A., Copet, J., Synnaeve, G., Adi, Y.: High fidelity neural audio compression. Trans. Mach. Learn. Res. (2023). https:\/\/openreview.net\/forum?id=ivCd8z8zR2, Accessed 21 Oct 2025"},{"key":"17_CR17","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Long and Short Papers). vol.\u00a01, pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR18","doi-asserted-by":"publisher","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I.: Jukebox: a generative model for music (2020). https:\/\/doi.org\/10.48550\/arXiv.2005.00341, Accessed 21 Oct 2025","DOI":"10.48550\/arXiv.2005.00341"},{"key":"17_CR19","unstructured":"Engel, J., et al.: Neural audio synthesis of musical notes with WaveNet autoencoders. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a070, pp. 1068\u20131077. PMLR (2017). https:\/\/proceedings.mlr.press\/v70\/engel17a.html, Accessed 02 Nov 2025"},{"key":"17_CR20","unstructured":"Evans, Z., Carr, C., Taylor, J., Hawley, S.H., Pons, J.: Fast timing-conditioned latent audio diffusion. In: Salakhutdinov, R., et al., (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 12652\u201312665. PMLR (2024). https:\/\/proceedings.mlr.press\/v235\/evans24a.html, Accessed 27 Oct 2025"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Facchiano, S., et al.: Activation patching for interpretable steering in music generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.04479, Accessed 05 Oct 2025","DOI":"10.48550\/arXiv.2504.04479"},{"key":"17_CR22","unstructured":"Fink, C.: Udio AI music raises \\$10 million, \\$6.5 million for Spines AI, more Sora, cinematic AI. Forbes (2024). https:\/\/www.forbes.com\/sites\/charliefink\/2024\/04\/11\/udio-ai-music-raises-10-million-65-million-for-spines-ai-more-sora-cinematic-ai\/, Accessed 28 Oct 2025"},{"key":"17_CR23","doi-asserted-by":"publisher","unstructured":"Foscarin, F., Hoedt, K., Praher, V., Flexer, A., Widmer, G.: Concept-based techniques for \u201cmusicologist- friendly\u201d explanations in deep music classifiers. In: Proceedings of the 23rd International Society for Music Information Retrieval Conference, pp. 876\u2013883. ISMIR (2022). https:\/\/doi.org\/10.5281\/zenodo.7316804, Accessed 29 May 2025","DOI":"10.5281\/zenodo.7316804"},{"key":"17_CR24","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261, ISSN: 2379-190X","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"17_CR25","unstructured":"Hutchinson, R.: Music Theory for the 21st-Century Classroom. University of Puget Sound (2025). https:\/\/musictheory.pugetsound.edu\/mt21c\/MusicTheory.html, Accessed 30 Oct 2025"},{"key":"17_CR26","unstructured":"Jensen, J.H., Christensen, M.G., Murthi, M.N., Jensen, S.H.: Evaluation of MFCC estimation techniques for music similarity. In: 2006 14th European Signal Processing Conference, pp.\u00a01\u20135 (2006). https:\/\/ieeexplore.ieee.org\/abstract\/document\/7071659, Accessed 02 Nov 2025"},{"key":"17_CR27","doi-asserted-by":"publisher","unstructured":"Kilgour, K., Zuluaga, M., Roblek, D., Sharifi, M.: Fr\u00e9chet audio distance: a reference-free metric for evaluating music enhancement algorithms. In: Interspeech 2019, pp. 2350\u20132354 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2219","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"17_CR28","unstructured":"Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: Proceedings of the 35th International Conference on Machine Learning. vol.\u00a080, pp. 2668\u20132677. PMLR (2018). https:\/\/proceedings.mlr.press\/v80\/kim18d.html, Accessed 15 Oct 2025"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Kim, D.H.S.: The Brahmsian hairpin. 19th-Century Music 36(1), 46\u201357 (2012). https:\/\/doi.org\/10.1525\/ncm.2012.36.1.046","DOI":"10.1525\/ncm.2012.36.1.046"},{"key":"17_CR30","doi-asserted-by":"publisher","unstructured":"Knees, P., et al.: Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections. In: Proceedings of the 16th International Society for Music Information Retrieval Conference, pp. 364\u2013370. ISMIR (2015). https:\/\/doi.org\/10.5281\/zenodo.1414996, Accessed 28 Oct 2025","DOI":"10.5281\/zenodo.1414996"},{"key":"17_CR31","unstructured":"Koo, J., Wichern, G., Germain, F.G., Khurana, S., Le Roux, J.: Understanding and controlling generative music transformers by probing individual attention heads. In: IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA) (2024). https:\/\/www.merl.com\/publications\/TR2024-032, Accessed 25 Oct 2025"},{"key":"17_CR32","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/OJSP.2025.3534686","volume":"6","author":"J Koo","year":"2025","unstructured":"Koo, J., Wichern, G., Germain, F.G., Khurana, S., Le Roux, J.: SMITIN: self-monitored inference-time intervention for generative music transformers. IEEE Open J. Sign. Process. 6, 266\u2013275 (2025). https:\/\/doi.org\/10.1109\/OJSP.2025.3534686","journal-title":"IEEE Open J. Sign. Process."},{"key":"17_CR33","doi-asserted-by":"publisher","unstructured":"Law, E., West, K., Mandel, M.I., Bay, M., Downie, J.S.: Evaluation of algorithms using games: the case of music tagging. In: Proceedings of the 10th International Society for Music Information Retrieval Conference, pp. 387\u2013392. ISMIR (Oct 2009). https:\/\/doi.org\/10.5281\/zenodo.1417647, Accessed 28 Oct 2025","DOI":"10.5281\/zenodo.1417647"},{"key":"17_CR34","unstructured":"Levine, M.: The Jazz Theory Book. Sher Music (1995)"},{"key":"17_CR35","unstructured":"Li, Y., et al.: MERT: acoustic music understanding model with large-scale self-supervised training. In: Kim, B., Yue, Y., Chaudhuri, S., Fragkiadaki, K., Khan, M., Sun, Y. (eds.) International Conference on Representation Learning. vol.\u00a02024, pp. 12181\u201312204 (2024). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2024\/hash\/33dffa2e3d2ab74a783d1a8c292f66d9-Abstract-Conference.html, Accessed 28 Oct 2025"},{"key":"17_CR36","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.11692, Accessed 01 Nov 2025","DOI":"10.48550\/arXiv.1907.11692"},{"key":"17_CR37","unstructured":"Ma, W., Li, X., Xia, G.: Do music LLMs learn symbolic concepts? a pilot study using probing and intervention. In: Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation (2024). https:\/\/openreview.net\/forum?id=uvzw0gS0Nn, Accessed 29 May 2025"},{"key":"17_CR38","unstructured":"Ma, W., Xia, G.: Exploring the internal mechanisms of music LLMs: a study of root and quality via probing and intervention techniques. In: International Conference on Machine Learning (ICML) Workshop on Mechanistic Interpretability (2024). https:\/\/openreview.net\/forum?id=Kr6nkNa4TQ, Accessed 29 May 2025"},{"key":"17_CR39","doi-asserted-by":"publisher","unstructured":"McCallum, M.C., Korzeniowski, F., Oramas, S., Gouyon, F., Ehmann, A.F.: Supervised and unsupervised learning of audio representations for music understanding. In: Proceedings of the 23rd International Society for Music Information Retrieval Conference, pp. 256\u2013263. ISMIR (2022). https:\/\/doi.org\/10.5281\/zenodo.7316644, Accessed 28 Oct 2025","DOI":"10.5281\/zenodo.7316644"},{"issue":"8","key":"17_CR40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0252174","volume":"16","author":"C M\u00f8ller","year":"2021","unstructured":"M\u00f8ller, C., Stupacher, J., Celma-Miralles, A., Vuust, P.: Beat perception in polyrhythms: time is structured in binary units. PLoS ONE 16(8), e0252174 (2021). https:\/\/doi.org\/10.1371\/journal.pone.0252174","journal-title":"PLoS ONE"},{"key":"17_CR41","doi-asserted-by":"publisher","unstructured":"Panda, D., et al.: Fine-grained control over music generation with activation steering (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.10225, Accessed 05 Oct 2025","DOI":"10.48550\/arXiv.2506.10225"},{"key":"17_CR42","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(85), 2825\u20132830 (2011). http:\/\/jmlr.org\/papers\/v12\/pedregosa11a.html, Accessed 22 Jan 2026"},{"key":"17_CR43","doi-asserted-by":"publisher","unstructured":"Pereira, I., Ara\u00fajo, F., Korzeniowski, F., Vogl, R.: MoisesDB: a dataset for source separation beyond 4-stems. In: Proceedings of the 24th International Society for Music Information Retrieval Conference, pp. 619\u2013626. ISMIR (2023). https:\/\/doi.org\/10.5281\/zenodo.10265363, Accessed 22 Jan 2026","DOI":"10.5281\/zenodo.10265363"},{"key":"17_CR44","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\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html, Accessed 31 Oct 2025"},{"key":"17_CR45","doi-asserted-by":"publisher","unstructured":"Rafii, Z., Liutkus, A., St\u00f6ter, F.R., Mimilakis, S.I., Bittner, R.: MUSDB18 - a corpus for music separation (2017). https:\/\/doi.org\/10.5281\/zenodo.1117372, Accessed 22 Jan 2026","DOI":"10.5281\/zenodo.1117372"},{"key":"17_CR46","doi-asserted-by":"publisher","unstructured":"Rohrmeier, M., Pearce, M.: Musical syntax I: theoretical perspectives. In: Bader, R. (ed.) Springer Handbook of Systematic Musicology, pp. 473\u2013486. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-662-55004-5_25","DOI":"10.1007\/978-3-662-55004-5_25"},{"key":"17_CR47","unstructured":"Sarmiento, I.G.: AI-generated music is here to stay. will streaming services like Spotify label it? National Public Radio (2025). https:\/\/www.npr.org\/2025\/08\/08\/nx-s1-5492314\/ai-music-streaming-services-spotify, Accessed 30 Oct 2025"},{"key":"17_CR48","doi-asserted-by":"publisher","unstructured":"Schneidermann, N., Hershcovich, D., Pedersen, B.: Probing for hyperbole in pre-trained language models. In: Padmakumar, V., Vallejo, G., Fu, Y. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. vol.\u00a04, pp. 200\u2013211. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-srw.30","DOI":"10.18653\/v1\/2023.acl-srw.30"},{"key":"17_CR49","unstructured":"Singh, N., Cherep, M., Maes, P.: Discovering and steering interpretable concepts in large generative music models. In: NeurIPS 2025 Workshop AI4Music (2025). https:\/\/openreview.net\/forum?id=jVSlJk5qNA, Accessed 22 Jan 2026"},{"key":"17_CR50","unstructured":"Spotify: Spotify strengthens AI protections for artists, songwriters, and producers (2025). https:\/\/newsroom.spotify.com\/2025-09-25\/spotify-strengthens-ai-protections\/, Accessed 30 Oct 2025"},{"issue":"3","key":"17_CR51","doi-asserted-by":"publisher","first-page":"329","DOI":"10.2307\/1417526","volume":"53","author":"SS Stevens","year":"1940","unstructured":"Stevens, S.S., Volkmann, J.: The relation of pitch to frequency: a revised scale. Am. J. Psychol. 53(3), 329\u2013353 (1940). https:\/\/doi.org\/10.2307\/1417526","journal-title":"Am. J. Psychol."},{"key":"17_CR52","unstructured":"Suno Inc.: Suno model timeline & information (2025). https:\/\/help.suno.com\/en\/articles\/5782721, Accessed 28 Oct 2025"},{"key":"17_CR53","unstructured":"Tzanetakis, G.: Manipulation, analysis and retrieval systems for audio signals. Ph.D thesis, Princeton University (2002)"},{"issue":"5","key":"17_CR54","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293\u2013302 (2002). https:\/\/doi.org\/10.1109\/TSA.2002.800560","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"17_CR55","doi-asserted-by":"publisher","unstructured":"Urbano, J., Bogdanov, D., Herrera, P., G\u00f3mez, E., Serra, X.: What is the effect of audio quality on the robustness of MFCCs and chroma features? In: Wang, H.M., Yang, Y.H., Lee, J.H. (eds.) Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014), Taipei, Taiwan, pp. 573\u2013578. ISMIR (2014). https:\/\/doi.org\/10.5281\/zenodo.1416276, Accessed 19 Oct 2025","DOI":"10.5281\/zenodo.1416276"},{"key":"17_CR56","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html, Accessed 31 Oct 2025"},{"key":"17_CR57","unstructured":"Weatherbed, J.: Adobe\u2019s new AI audio tools can add soundtracks and voice-overs to videos. The Verge (2025). https:\/\/www.theverge.com\/news\/807809\/adobe-firefly-ai-audio-generate-soundtrack-speech, Accessed 30 Oct 2025"},{"key":"17_CR58","doi-asserted-by":"publisher","unstructured":"Wei, M., Freeman, M., Donahue, C., Sun, C.: Do music generation models encode music theory? In: Proceedings of the 25th International Society for Music Information Retrieval Conference, pp. 680\u2013687. ISMIR (2024). https:\/\/doi.org\/10.5281\/zenodo.14877427, Accessed 19 Aug 2025","DOI":"10.5281\/zenodo.14877427"},{"key":"17_CR59","doi-asserted-by":"publisher","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095969","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"17_CR60","doi-asserted-by":"publisher","unstructured":"Zhao, D., Beaglehole, D., Berg-Kirkpatrick, T., McAuley, J., Novack, Z.: Steering autoregressive music generation with recursive feature machines. https:\/\/doi.org\/10.48550\/arXiv.2510.19127, Accessed 23 Oct 2025","DOI":"10.48550\/arXiv.2510.19127"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-24350-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:24:29Z","timestamp":1777433069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-24350-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032243492","9783032243508"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-24350-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toulouse","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2026\/evomusart\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}