{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:40Z","timestamp":1774419700446,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888635","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Melody Structure Transfer Network: Generating Music with Separable Self-Attention"],"prefix":"10.1109","author":[{"given":"Junlin","family":"Wu","sequence":"first","affiliation":[{"name":"MOE Key Lab of AI,Dept. of CSE,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[{"name":"MOE Key Lab of AI,Dept. of CSE,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"MOE Key Lab of AI,Dept. of CSE,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of AI,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanxi","family":"Liu","sequence":"additional","affiliation":[{"name":"MOE Key Lab of AI,Dept. of CSE,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of AI,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3813-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70163-9"},{"key":"ref3","article-title":"Formalized music: Thought and mathematics in composition (sharon kanach, compilation and edition)","author":"Xenakis","year":"1963"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199935321.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5920\/jcms.2018.01"},{"key":"ref6","article-title":"Music transformer: Generating music with long-term structure","author":"Huang","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.35940\/ijitee.f3580.049620"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref9","article-title":"Patch-level contrasting without patch correspondence for accurate and dense contrastive representation learning","volume-title":"ICLR","author":"Zhang"},{"key":"ref10","article-title":"Patch-level contrastive learning via positional query for visual pre-training","volume-title":"ICML","author":"Zhang"},{"key":"ref11","first-page":"725","article-title":"Struc-turenet: Inducing structure in generated melodies","volume-title":"ISMIR","author":"Medeot"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2108287"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-013-1761-9"},{"key":"ref14","article-title":"Modeling self-repetition in music generation using generative adversarial networks","volume-title":"Machine Learning for Music Discovery Workshop","author":"Jhamtani"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref17","article-title":"Ctrl: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019"},{"key":"ref18","article-title":"Learning to traverse latent spaces for musical score inpaintning","volume-title":"Proc. of the 20th International Society for Music Information Retrieval Conference (ISMIR)","author":"Pati"},{"key":"ref19","article-title":"Music transcription modelling and composition using deep learning","volume-title":"1st Conference on Computer Simulation of Musical Creativity","author":"Sturm"},{"key":"ref20","article-title":"Wikifonia","year":"2010"},{"key":"ref21","article-title":"The abc music standard 2.1","volume":"1","author":"Walshaw","year":"2011"},{"key":"ref22","first-page":"03","article-title":"Musicxml: An internet-friendly format for sheet music","volume-title":"Xml conference and expo","author":"Good"},{"key":"ref23","article-title":"Graphqntk: the quantum neural tangent kernel for graph data","volume-title":"NeurIPS","author":"Tang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02472"},{"key":"ref25","article-title":"Qvae-mole: The quantum vae with spherical latent variable learning for 3-d molecule generation","volume-title":"NeurIPS","author":"Wu"},{"key":"ref26","article-title":"Node2ket: Efficient high-dimensional network embedding in quantum hilbert space","volume-title":"ICLR","author":"Xiong"},{"key":"ref27","article-title":"Zarts: On zero-order optimization for neural architecture search","volume-title":"NeurIPS","author":"Wang"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2020\/424","article-title":"Mergenas: Merge operations into one for differentiable architecture search","volume-title":"IJCAI","author":"Wang"},{"key":"ref29","article-title":"Up2me: Univariate pre-training to multivariate fine-tuning as a general-purpose framework for multivariate time series analysis","volume-title":"ICML","author":"Zhang"},{"key":"ref30","article-title":"Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining","volume-title":"ICLR","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_22"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888635.pdf?arnumber=10888635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:12Z","timestamp":1774416252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888635","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}