{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:09:27Z","timestamp":1777630167725,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548084","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"1204-1213","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Structure-Enhanced Pop Music Generation via Harmony-Aware Learning"],"prefix":"10.1145","author":[{"given":"Xueyao","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qiu","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Deep Learning Techniques for Music Generation","author":"Briot Jean-Pierre","unstructured":"Jean-Pierre Briot , Ga\u00ebtan Hadjeres , and Francois-David Pachet . 2020. Deep Learning Techniques for Music Generation . Springer . Jean-Pierre Briot, Ga\u00ebtan Hadjeres, and Francois-David Pachet. 2020. Deep Learning Techniques for Music Generation. Springer."},{"key":"e_1_3_2_2_2_1","volume-title":"ISMIR 2006, 7th International Conference on Music Information Retrieval. 198--201","author":"Bruderer Michael J.","year":"2006","unstructured":"Michael J. Bruderer , Martin F. McKinney , and Armin Kohlrausch . 2006 . Structural boundary perception in popular music . In ISMIR 2006, 7th International Conference on Music Information Retrieval. 198--201 . Michael J. Bruderer, Martin F. McKinney, and Armin Kohlrausch. 2006. Structural boundary perception in popular music. In ISMIR 2006, 7th International Conference on Music Information Retrieval. 198--201."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00014"},{"key":"e_1_3_2_2_4_1","volume-title":"The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation. In 2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","author":"Chen Ke","unstructured":"Ke Chen , Weilin Zhang , Shlomo Dubnov , Gus Xia , and Wei Li. 2019. The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation. In 2019 International Workshop on Multilayer Music Representation and Processing (MMRP) . IEEE Computer Society , 77--84. Ke Chen, Weilin Zhang, Shlomo Dubnov, Gus Xia, and Wei Li. 2019. The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation. In 2019 International Workshop on Multilayer Music Representation and Processing (MMRP). IEEE Computer Society, 77--84."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.2307\/3680238"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021. 143--150","author":"Dai Shuqi","unstructured":"Shuqi Dai , Zeyu Jin , Celso Gomes , and Roger B. Dannenberg . 2021. Controllable deep melody generation via hierarchical music structure representation . In Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021. 143--150 . Shuqi Dai, Zeyu Jin, Celso Gomes, and Roger B. Dannenberg. 2021. Controllable deep melody generation via hierarchical music structure representation. In Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021. 143--150."},{"key":"e_1_3_2_2_7_1","volume-title":"Proc. of the 2020 Joint Conference on AI Music Creativity, CSMC-MuMe","author":"Dai Shuqi","year":"2020","unstructured":"Shuqi Dai , Huan Zhang , and Roger B Dannenberg . 2020 . Automatic analysis and influence of hierarchical structure on melody, rhythm and harmony in popular music . In Proc. of the 2020 Joint Conference on AI Music Creativity, CSMC-MuMe 2020. Shuqi Dai, Huan Zhang, and Roger B Dannenberg. 2020. Automatic analysis and influence of hierarchical structure on melody, rhythm and harmony in popular music. In Proc. of the 2020 Joint Conference on AI Music Creativity, CSMC-MuMe 2020."},{"key":"e_1_3_2_2_8_1","volume-title":"A Dictionary of Music and Musicians","author":"Grove George","unstructured":"George Grove . 1883. A Dictionary of Music and Musicians . Vol. 3 . Macmillan . George Grove. 1883. A Dictionary of Music and Musicians. Vol. 3. Macmillan."},{"key":"e_1_3_2_2_9_1","volume-title":"ACM Comput. Surv.","volume":"50","author":"Herremans Dorien","year":"2017","unstructured":"Dorien Herremans , Ching-Hua Chuan , and Elaine Chew . 2017 . A Functional Taxonomy of Music Generation Systems . ACM Comput. Surv. , Vol. 50 , 5 (2017), 69:1--69:30. Dorien Herremans, Ching-Hua Chuan, and Elaine Chew. 2017. A Functional Taxonomy of Music Generation Systems. ACM Comput. Surv., Vol. 50, 5 (2017), 69:1--69:30."},{"key":"e_1_3_2_2_10_1","volume-title":"The Curious Case of Neural Text Degeneration. In 8th International Conference on Learning Representations, ICLR","author":"Holtzman Ari","year":"2020","unstructured":"Ari Holtzman , Jan Buys , Li Du , Maxwell Forbes , and Yejin Choi . 2020 . The Curious Case of Neural Text Degeneration. In 8th International Conference on Learning Representations, ICLR 2020. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The Curious Case of Neural Text Degeneration. In 8th International Conference on Learning Representations, ICLR 2020."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.2307\/3680893"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"e_1_3_2_2_13_1","volume-title":"Music Transformer: Generating Music with Long-Term Structure. In 7th International Conference on Learning Representations, ICLR","author":"Anna Huang Cheng-Zhi","year":"2019","unstructured":"Cheng-Zhi Anna Huang , Ashish Vaswani , Jakob Uszkoreit , Ian Simon , Curtis Hawthorne , Noam Shazeer , Andrew M. Dai , Matthew D. Hoffman , Monica Dinculescu , and Douglas Eck . 2019 . Music Transformer: Generating Music with Long-Term Structure. In 7th International Conference on Learning Representations, ICLR 2019. Cheng-Zhi Anna Huang, Ashish Vaswani, Jakob Uszkoreit, Ian Simon, Curtis Hawthorne, Noam Shazeer, Andrew M. Dai, Matthew D. Hoffman, Monica Dinculescu, and Douglas Eck. 2019. Music Transformer: Generating Music with Long-Term Structure. In 7th International Conference on Learning Representations, ICLR 2019."},{"key":"e_1_3_2_2_14_1","volume-title":"Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions. In MM '20: The 28th ACM International Conference on Multimedia. 1180--1188","author":"Huang Yu-Siang","year":"2020","unstructured":"Yu-Siang Huang and Yi-Hsuan Yang . 2020 . Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions. In MM '20: The 28th ACM International Conference on Multimedia. 1180--1188 . Yu-Siang Huang and Yi-Hsuan Yang. 2020. Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions. In MM '20: The 28th ACM International Conference on Multimedia. 1180--1188."},{"key":"e_1_3_2_2_15_1","volume-title":"Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP","author":"Jiang Junyan","year":"2020","unstructured":"Junyan Jiang , Gus Xia , Dave B. Carlton , Chris N. Anderson , and Ryan H. Miyakawa . 2020 . Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020 . 516--520. Junyan Jiang, Gus Xia, Dave B. Carlton, Chris N. Anderson, and Ryan H. Miyakawa. 2020. Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020. 516--520."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML).","author":"Katharopoulos A.","unstructured":"A. Katharopoulos , A. Vyas , N. Pappas , and F. Fleuret . 2020. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention . In Proceedings of the International Conference on Machine Learning (ICML). A. Katharopoulos, A. Vyas, N. Pappas, and F. Fleuret. 2020. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_2_17_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015 . Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015."},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2019. 725--731","author":"Medeot Gabriele","year":"2018","unstructured":"Gabriele Medeot , Srikanth Cherla , Katerina Kosta , Matt McVicar , Samer Abdallah , Marco Selvi , Ed Newton-Rex , and Kevin Webster . 2018 . StructureNet: Inducing Structure in Generated Melodies . In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2019. 725--731 . Gabriele Medeot, Srikanth Cherla, Katerina Kosta, Matt McVicar, Samer Abdallah, Marco Selvi, Ed Newton-Rex, and Kevin Webster. 2018. StructureNet: Inducing Structure in Generated Melodies. In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2019. 725--731."},{"key":"e_1_3_2_2_19_1","volume-title":"Analysis, Algorithms, Applications","author":"M\u00fcller Meinard","unstructured":"Meinard M\u00fcller . 2015. Fundamentals of Music Processing - Audio , Analysis, Algorithms, Applications . Springer . Meinard M\u00fcller. 2015. Fundamentals of Music Processing - Audio, Analysis, Algorithms, Applications. Springer."},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 97--102","author":"M\u00fcller Meinard","year":"2012","unstructured":"Meinard M\u00fcller and Nanzhu Jiang . 2012 . A Scape Plot Representation for Visualizing Repetitive Structures of Music Recordings . In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 97--102 . Meinard M\u00fcller and Nanzhu Jiang. 2012. A Scape Plot Representation for Visualizing Repetitive Structures of Music Recordings. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 97--102."},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016.","author":"O'Brien Tim","year":"2016","unstructured":"Tim O'Brien . 2016 . Musical Structure Segmentation with Convolutional Neural Networks . In Proceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016. Tim O'Brien. 2016. Musical Structure Segmentation with Convolutional Neural Networks. In Proceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"e_1_3_2_2_23_1","volume-title":"High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , Alban Desmaison , Andreas K\u00f6pf , Edward Yang , Zachary DeVito , Martin Raison , Alykhan Tejani , Sasank Chilamkurthy , Benoit Steiner , Lu Fang , Junjie Bai , and Soumith Chintala . 2019 . PyTorch: An Imperative Style , High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 , NeurIPS 2019. 8024--8035. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019. 8024--8035."},{"key":"e_1_3_2_2_24_1","volume-title":"The Harvard Concise Dictionary of Music and Musicians","author":"Randel Don Michael","unstructured":"Don Michael Randel . 1999. The Harvard Concise Dictionary of Music and Musicians . Harvard University Press . Don Michael Randel. 1999. The Harvard Concise Dictionary of Music and Musicians. Harvard University Press."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2019. 4361--4370","author":"Roberts Adam","year":"2018","unstructured":"Adam Roberts , Jesse H. Engel , Colin Raffel , Curtis Hawthorne , and Douglas Eck . 2018 . A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music . In Proceedings of the 35th International Conference on Machine Learning, ICML 2019. 4361--4370 . Adam Roberts, Jesse H. Engel, Colin Raffel, Curtis Hawthorne, and Douglas Eck. 2018. A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music. In Proceedings of the 35th International Conference on Machine Learning, ICML 2019. 4361--4370."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.2307\/3679551"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.2307\/40285492"},{"key":"e_1_3_2_2_28_1","volume-title":"NIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All you Need. In Advances in Neural Information Processing Systems , NIPS 2017. 5998--6008. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, NIPS 2017. 5998--6008."},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 38--45","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang , Ke Chen , Junyan Jiang , Yiyi Zhang , Maoran Xu , Shuqi Dai , and Gus Xia . 2020 a. POP909: A Pop-Song Dataset for Music Arrangement Generation . In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 38--45 . Ziyu Wang, Ke Chen, Junyan Jiang, Yiyi Zhang, Maoran Xu, Shuqi Dai, and Gus Xia. 2020a. POP909: A Pop-Song Dataset for Music Arrangement Generation. In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 38--45."},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 662--669","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang , Dingsu Wang , Yixiao Zhang , and Gus Xia . 2020 b. Learning Interpretable Representation for Controllable Polyphonic Music Generation . In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 662--669 . Ziyu Wang, Dingsu Wang, Yixiao Zhang, and Gus Xia. 2020b. Learning Interpretable Representation for Controllable Polyphonic Music Generation. In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 662--669."},{"key":"e_1_3_2_2_31_1","volume-title":"A Framework for Automated Pop-song Melody Generation with Piano Accompaniment Arrangement. arXiv preprint arXiv:1812.10906","author":"Wang Ziyu","year":"2018","unstructured":"Ziyu Wang and Gus Xia . 2018. A Framework for Automated Pop-song Melody Generation with Piano Accompaniment Arrangement. arXiv preprint arXiv:1812.10906 ( 2018 ). Ziyu Wang and Gus Xia. 2018. A Framework for Automated Pop-song Melody Generation with Piano Accompaniment Arrangement. arXiv preprint arXiv:1812.10906 (2018)."},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 368--375","author":"Wang Ziyu","year":"2020","unstructured":"Ziyu Wang , Yiyi Zhang , Yixiao Zhang , Junyan Jiang , Ruihan Yang , Gus Xia , and Junbo Zhao . 2020 c. PIANOTREE VAE: Structured Representation Learning for Polyphonic Music . In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 368--375 . Ziyu Wang, Yiyi Zhang, Yixiao Zhang, Junyan Jiang, Ruihan Yang, Gus Xia, and Junbo Zhao. 2020c. PIANOTREE VAE: Structured Representation Learning for Polyphonic Music. In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 368--375."},{"key":"e_1_3_2_2_33_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Homophony. [Online]","author":"Wikipedia Wikipedia","unstructured":"Wikipedia contributors. 2022a. Homophony -- Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Homophony. [Online] . Wikipedia contributors. 2022a. Homophony -- Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Homophony. [Online]."},{"key":"e_1_3_2_2_34_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Musical_form. [Online].","author":"Wikipedia","unstructured":"Wikipedia contributors. 2022b. Musical form -- Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Musical_form. [Online]. Wikipedia contributors. 2022b. Musical form -- Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Musical_form. [Online]."},{"key":"e_1_3_2_2_35_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Post-chorus. [Online]","author":"Wikipedia Wikipedia","unstructured":"Wikipedia contributors. 2022c. Post-chorus -- Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Post-chorus. [Online] . Wikipedia contributors. 2022c. Post-chorus -- Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Post-chorus. [Online]."},{"key":"e_1_3_2_2_36_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Texture_(music). [Online]","author":"Wikipedia Wikipedia","unstructured":"Wikipedia contributors. 2022d. Texture (music) -- Wikipedia , The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Texture_(music). [Online] . Wikipedia contributors. 2022d. Texture (music) -- Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Texture_(music). [Online]."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103303"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 142--149","author":"Wu Shih-Lun","year":"2020","unstructured":"Shih-Lun Wu and Yi-Hsuan Yang . 2020 . The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures . In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 142--149 . Shih-Lun Wu and Yi-Hsuan Yang. 2020. The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures. In Proceedings of the 21th International Society for Music Information Retrieval Conference, ISMIR 2020. 142--149."},{"key":"e_1_3_2_2_39_1","volume-title":"MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE. arXiv preprint arXiv:2105.04090","author":"Wu Shih-Lun","year":"2021","unstructured":"Shih-Lun Wu and Yi-Hsuan Yang . 2021. MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE. arXiv preprint arXiv:2105.04090 ( 2021 ). Shih-Lun Wu and Yi-Hsuan Yang. 2021. MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE. arXiv preprint arXiv:2105.04090 (2021)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019. 655--662","author":"Zhou Yichao","year":"2019","unstructured":"Yichao Zhou , Wei Chu , Sam Young , and Xin Chen . 2019 . BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine . In Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019. 655--662 . Yichao Zhou, Wei Chu, Sam Young, and Xin Chen. 2019. BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine. In Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019. 655--662."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220105"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548084","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:18Z","timestamp":1750186818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":41,"alternative-id":["10.1145\/3503161.3548084","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548084","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}