{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:59:42Z","timestamp":1775199582077,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434600","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Sinba: Singing-To-Accompaniment Generation With Pitch Guidance Via Mamba-Based Language Model"],"prefix":"10.1109","author":[{"given":"Jianwei","family":"Cui","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Shihao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Chengxing","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-391"},{"key":"ref7","article-title":"Experimental Music; Composition with an electronic computer","author":"Hiller","year":"1979"},{"key":"ref8","article-title":"Using patterns to generate rhythmic accompaniment for guitar","author":"Dahia","year":"2004","journal-title":"Journ\u00e9es d\u2019informatique musicale"},{"key":"ref9","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Fastsag: Towards fast non-autoregressive singing accompaniment generation","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2405.07682"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937261"},{"key":"ref12","article-title":"Jukedrummer: Conditional beat-aware audio-domain drum accompaniment generation via transformer vqvae","author":"Wu","year":"2022","journal-title":"arXiv preprint arXiv:2210.06007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/app10186627"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446400"},{"key":"ref15","article-title":"Singsong: Generating musical accompaniments from singing","author":"Donahue","year":"2023","journal-title":"arXiv preprint arXiv:2301.12662"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/83.480761"},{"key":"ref22","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref24","article-title":"The MIDI manual, Sams","author":"Huber","year":"1991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2874719"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1142\/S0218195995000064"},{"key":"ref27","article-title":"Fr \u2018 echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018","journal-title":"arXiv preprint arXiv:1812.08466"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref29","article-title":"The musdb18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00362-012-0443-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434600.pdf?arnumber=11434600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:22Z","timestamp":1775192182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434600","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}