{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:59:17Z","timestamp":1772935157779,"version":"3.50.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401776","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"4973-4980","source":"Crossref","is-referenced-by-count":0,"title":["Chord Latent Decoupling for Music Mashups"],"prefix":"10.1109","author":[{"given":"Yu Foon Darin","family":"Chau","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Horner","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2347135"},{"key":"ref2","article-title":"Automatic mashup creation by considering both vertical and horizontal mashabilities","volume-title":"International Society for Music Information Retrieval Conference","author":"Lee","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16092"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS51600.2021.9516600"},{"key":"ref5","article-title":"Music source separation in the waveform domain","author":"D\u00e9fossez","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref8","first-page":"183","article-title":"Chord segmentation and recognition using em-trained hidden markov models","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"Sheh","year":"2003"},{"key":"ref9","first-page":"133","article-title":"Automatic chord recognition from audio using a hmm with supervised learning","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"Lee","year":"2006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495218"},{"key":"ref11","first-page":"121","article-title":"Key estimation using a hidden markov model","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"Noland","year":"2006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2012.220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738895"},{"key":"ref14","first-page":"620","article-title":"A bi-directional transformer for musical chord recognition","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Park","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081351"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462285"},{"key":"ref18","article-title":"Timbretron: A wavenet (cyclegan(cqt(audio))) pipeline for musical timbre transfer","volume-title":"International Conference on Learning Representations","author":"Huang","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019642"},{"key":"ref21","first-page":"4364","article-title":"A hierarchical latent vector model for learning long-term structure in music","volume-title":"International conference on machine learning","author":"Roberts","year":"2018"},{"key":"ref22","first-page":"747","article-title":"Midi-vae: Modeling dynamics and instrumentation of music with applications to style transfer","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference","author":"Brunner","year":"2018"},{"key":"ref23","first-page":"735","article-title":"Pianotree vae: Structured representation learning for polyphonic music","volume-title":"Proceedings of the 21th International Society for Music Information Retrieval Conference","author":"Wang","year":"2020"},{"key":"ref24","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International Conference on Learning Representations","author":"Higgins","year":"2017"},{"key":"ref25","article-title":"Understanding disentangling in beta-vae","author":"Burgess","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref26","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2018"},{"key":"ref27","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","volume":"29","author":"Chen","year":"2016","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref28","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref30","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian","year":"2019"},{"key":"ref31","volume-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"Kim","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref33","first-page":"823","article-title":"Graph neural networks for music representation learning","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Jeong","year":"2019"},{"key":"ref34","article-title":"Timbre-preserving audio synthesis via domain adaptation","author":"Luo","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref35","volume-title":"Vector-quantized timbre representation","author":"Bitton","year":"2020"},{"key":"ref36","first-page":"488","article-title":"Deep learningbased automatic mashup generation with functional segment analysis","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Lee","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746663"},{"key":"ref38","article-title":"Musicmixup: A data-driven approach to music mashup generation","author":"Wu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref39","first-page":"159","article-title":"Conditioned-u-net: Introducing a control mechanism in the u-net for multiple source separations","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Meseguer-Brocal","year":"2019"},{"key":"ref40","first-page":"409","article-title":"Mashup-oriented music stem separation using hierarchical embedding learning","volume-title":"International Conference on Multimedia Retrieval","author":"Zhao","year":"2021"},{"key":"ref41","first-page":"1085","article-title":"Semi-supervised music tagging using noisy labels and tag embeddings","volume":"28","author":"Lee","year":"2021","journal-title":"IEEE Signal Processing Letters"},{"key":"ref42","article-title":"Music transformer","author":"Huang","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","volume-title":"International Conference on Learning Representations","author":"Hawthorne","year":"2019"},{"key":"ref44","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref45","volume-title":"Musenet","author":"Payne","year":"2019"},{"key":"ref46","first-page":"685","article-title":"Lakhnes: Improving multi-instrumental music generation with crossdomain pre-training","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Donahue","year":"2019"},{"key":"ref47","volume-title":"Ace-step: A step towards music generation foundation model","author":"Gong","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01199"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref50","article-title":"Multi-level temporal-channel speaker retrieval for zeroshot voice conversion","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","volume-title":"Retrieval-based voice conversion webui","year":"2024"},{"key":"ref52","volume-title":"LAION-DISC O-12M Dataset","year":"2023"},{"key":"ref53","volume-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2019"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01448","volume-title":"Denoising diffusion autoencoders are unified self-supervised learners","author":"Xiang","year":"2023"},{"key":"ref55","volume-title":"Convergence analysis of flow matching in latent space with transformers","author":"Jiao","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401776.pdf?arnumber=11401776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:23:59Z","timestamp":1772868239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401776\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401776","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}