{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T14:03:05Z","timestamp":1783605785006,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755766","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"10554-10562","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Adapter Design Tradeoffs for Low Resource Music Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7308-8936","authenticated-orcid":false,"given":"Atharva","family":"Mehta","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3033-7439","authenticated-orcid":false,"given":"Shivam","family":"Chauhan","sequence":"additional","affiliation":[{"name":"Presight, G42 Company, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7473-7839","authenticated-orcid":false,"given":"Monojit","family":"Choudhury","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325","author":"Agostinelli Andrea","year":"2023","unstructured":"Andrea Agostinelli, Timo I Denk, Zal\u00e1n Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, et al., 2023. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 18th Conference of the European","author":"Arabzadeh Negar","year":"2024","unstructured":"Negar Arabzadeh and Charles Clarke. 2024. Fr\u00e9chet Distance for Offline Evaluation of Information Retrieval Systems with Sparse Labels. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Yvette Graham and Matthew Purver (Eds.). Association for Computational Linguistics, St. Julian's, Malta, 420-431. https:\/\/aclanthology.org\/2024.eacl-long.26\/"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1076\/jnmr.32.1.83.16801"},{"key":"e_1_3_2_1_4_1","volume-title":"Gamelan Stories: Tantrism, Islam, and Aesthetics in Central Java.","author":"Becker Judith","year":"1993","unstructured":"Judith Becker. 1993. Gamelan Stories: Tantrism, Islam, and Aesthetics in Central Java. (1993)."},{"key":"e_1_3_2_1_5_1","first-page":"47704","volume-title":"Levine (Eds.)","volume":"36","author":"Copet Jade","year":"2023","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre Defossez. 2023. Simple and Controllable Music Generation. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 47704-47720. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/94b472a1842cd7c56dcb125fb2765fbd-Paper-Conference.pdf"},{"key":"e_1_3_2_1_6_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_7_1","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch and et al. 2022. Training Compute-Optimal Large Language Models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790-2799."},{"key":"e_1_3_2_1_9_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_11_1","volume-title":"The R=ags of North Indian Music: Their Structure and Evolution","author":"Jairazbhoy N.A.","year":"2026","unstructured":"N.A. Jairazbhoy. 1971. The R=ags of North Indian Music: Their Structure and Evolution. Wesleyan University Press. 77120260 https:\/\/books.google.ae\/books?id=0A0wAQAAIAAJ"},{"key":"e_1_3_2_1_12_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan and et al. 2020. Scaling Laws for Neural Language Models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kevin Kilgour Mauricio Zuluaga Dominik Roblek and Matthew Sharifi. 2019. Fr\u00e9chet Audio Distance: A Reference-Free Metric for Evaluating Music Enhancement Algorithms. In Interspeech. https:\/\/api.semanticscholar.org\/CorpusID:202725406","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_1_15_1","series-title":"and time series","volume-title":"Convolutional networks for images, speech","author":"LeCun Yann","unstructured":"Yann LeCun and Yoshua Bengio. 1998. Convolutional networks for images, speech, and time series. MIT Press, Cambridge, MA, USA, 255-258."},{"key":"e_1_3_2_1_16_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_17_1","first-page":"21450","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Liu Haohe","year":"2023","unstructured":"Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, and Mark D Plumbley. 2023. AudioLDM: Text-to-Audio Generation with Latent Diffusion Models. Proceedings of the International Conference on Machine Learning (2023), 21450-21474."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.35"},{"key":"e_1_3_2_1_19_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:53592270","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:53592270"},{"key":"e_1_3_2_1_20_1","volume-title":"Missing Melodies: AI Music Generation and its ''Nearly'' Complete Omission of the Global South. arXiv:2412.04100 [cs.SD] https:\/\/arxiv.org\/abs\/2412.04100","author":"Mehta Atharva","year":"2024","unstructured":"Atharva Mehta, Shivam Chauhan, and Monojit Choudhury. 2024. Missing Melodies: AI Music Generation and its ''Nearly'' Complete Omission of the Global South. arXiv:2412.04100 [cs.SD] https:\/\/arxiv.org\/abs\/2412.04100"},{"key":"e_1_3_2_1_21_1","unstructured":"Atharva Mehta Shivam Chauhan Amirbek Djanibekov Atharva Kulkarni Gus Xia and Monojit Choudhury. 2025. Music for All: Exploring Multicultural Representations in Music Generation Models. arXiv:2502.07328 [cs.SD]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"e_1_3_2_1_23_1","volume-title":"Music of the middle east. Excursions in world music","author":"Nettl Bruno","year":"2001","unstructured":"Bruno Nettl. 2001. Music of the middle east. Excursions in world music (2001), 46-73."},{"key":"e_1_3_2_1_24_1","volume-title":"Adapterfusion: Non-destructive task composition for transfer learning. arXiv preprint arXiv:2005.00247","author":"Pfeiffer Jonas","year":"2020","unstructured":"Jonas Pfeiffer, Aishwarya Kamath, Andreas R\u00fcckl\u00e9, Kyunghyun Cho, and Iryna Gurevych. 2020a. Adapterfusion: Non-destructive task composition for transfer learning. arXiv preprint arXiv:2005.00247 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"Adapterhub: A framework for adapting transformers. arXiv preprint arXiv:2007.07779","author":"Pfeiffer Jonas","year":"2020","unstructured":"Jonas Pfeiffer, Andreas R\u00fcckl\u00e9, Clifton Poth, Aishwarya Kamath, Ivan Vuli\u0107, Sebastian Ruder, Kyunghyun Cho, and Iryna Gurevych. 2020b. Adapterhub: A framework for adapting transformers. arXiv preprint arXiv:2007.07779 (2020)."},{"key":"e_1_3_2_1_26_1","unstructured":"Alastair Porter Mohamed Sordo and Xavier Serra. 2013. Dunya: a system for browsing audio music collections exploiting cultural context. http:\/\/hdl.handle.net\/10230\/32251"},{"key":"e_1_3_2_1_27_1","volume-title":"Early stopping-but when? In Neural Networks: Tricks of the trade","author":"Prechelt Lutz","unstructured":"Lutz Prechelt. 2002. Early stopping-but when? In Neural Networks: Tricks of the trade. Springer, 55-69."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.437"},{"key":"e_1_3_2_1_29_1","volume-title":"AES 53rd International Conference: Semantic Audio; 2014 Jan 27-29; London, UK. New York: Audio Engineering Society;","author":"Serra Xavier","year":"2014","unstructured":"Xavier Serra. 2014. Creating research corpora for the computational study of music: the case of the Compmusic project. In AES 53rd International Conference: Semantic Audio; 2014 Jan 27-29; London, UK. New York: Audio Engineering Society; 2014. Article number 1-1 [9 p.]., Audio Engineering Society."},{"key":"e_1_3_2_1_30_1","volume-title":"Makam: Modal Practice in Turkish Art Music. Usul Editions. https:\/\/books.google.ae\/books?id=-G5MPgAACAAJ","author":"Signell K.L.","year":"2008","unstructured":"K.L. Signell. 2008. Makam: Modal Practice in Turkish Art Music. Usul Editions. https:\/\/books.google.ae\/books?id=-G5MPgAACAAJ"},{"key":"e_1_3_2_1_31_1","unstructured":"Or Tal Alon Ziv Itai Gat Felix Kreuk and Yossi Adi. 2024. Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation. arXiv:2406.10970 [cs.SD] https:\/\/arxiv.org\/abs\/2406.10970"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/pnasnexus\/pgae346"},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_34_1","volume-title":"The grammar of Carnatic music","author":"Vijayakrishnan KG","unstructured":"KG Vijayakrishnan. 2007. The grammar of Carnatic music. Mouton de Gruyter."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688369"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:45:26Z","timestamp":1765309526000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":36,"alternative-id":["10.1145\/3746027.3755766","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755766","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}