{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:31:49Z","timestamp":1777631509645,"version":"3.51.4"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448249","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"941-945","source":"Crossref","is-referenced-by-count":3,"title":["Multi-View Midivae: Fusing Track- and Bar-View Representations for Long Multi-Track Symbolic Music Generation"],"prefix":"10.1109","author":[{"given":"Zhiwei","family":"Lin","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Boshi","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Binzhu","family":"Sha","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}]},{"given":"Yaolong","family":"Ju","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}]},{"given":"Fan","family":"Fan","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Wavjourney: Compositional audio creation with large language models","author":"Liu","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094628"},{"key":"ref5","article-title":"Music Transformer: Generating Music with Long-Term Structure","volume-title":"International Conference on Learning Representations","author":"Huang"},{"key":"ref6","article-title":"Lakhnes: Improving multi-instrumental music generation with cross-domain pretraining","volume-title":"Proc. ISMIR","author":"Donahue"},{"key":"ref7","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref8","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref9","article-title":"Simple and Controllable Music Generation","author":"Copet","year":"2023"},{"key":"ref10","article-title":"Efficient Neural Music Generation","author":"Lam","year":"2023"},{"key":"ref11","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref12","article-title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","author":"Huang","year":"2023"},{"key":"ref13","article-title":"A Survey on Deep Learning for Symbolic Music Generation: Representations, Algorithms, Evaluations, and Challenges","author":"Ji","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"ref14","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"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280895"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05270-2"},{"key":"ref17","article-title":"Pianotree vae: Structured representation learning for polyphonic music","volume-title":"Proc. ISMIR","author":"Wang"},{"key":"ref18","article-title":"Learning long-term music representations via hierarchical contextual constraints","volume-title":"Proc. ISMIR","author":"Wei"},{"key":"ref19","article-title":"Symbolic music generation with diffusion models","author":"Mittal","year":"2021"},{"key":"ref20","article-title":"Learning a latent space of multitrack measures","author":"Simon","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.70"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","article-title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","author":"Wu","year":"2022"},{"key":"ref25","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International conference on learning representations","author":"Higgins"},{"key":"ref26","article-title":"FIGARO: Generating symbolic music with fine-grained artistic control","author":"von R\u00fctte","year":"2022"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448249.pdf?arnumber=10448249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:46:08Z","timestamp":1722660368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448249","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}