{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:15:24Z","timestamp":1773119724803,"version":"3.50.1"},"reference-count":21,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446643","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1471-1475","source":"Crossref","is-referenced-by-count":1,"title":["Generating Stereophonic Music with Single-Stage Language Models"],"prefix":"10.1109","author":[{"given":"Xingda","family":"Li","sequence":"first","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Fan","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Dan","family":"Luo","sequence":"additional","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":"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":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Han","family":"Fang","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]},{"given":"Yahui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Skywork AI PTE. LTD."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9781351252225"},{"key":"ref2","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref3","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref4","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref5","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref6","article-title":"Efficient neural music generation","author":"Lam","year":"2023"},{"key":"ref7","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref8","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"International Conference on Machine Learning","author":"Kalchbrenner"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref10","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Van Den Oord"},{"key":"ref11","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Razavi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref15","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref17","article-title":"Stereo signal separation and upmixing by mid-side decomposition in the frequency-domain","volume-title":"18th International Conference on Digital Audio Effects (DAFx)","author":"Kraft"},{"key":"ref18","author":"Rafii","year":"2017","journal-title":"The MUSDB18 corpus for music separation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_28"},{"key":"ref20","first-page":"1","article-title":"Visqol: The virtual speech quality objective listener","volume-title":"IWAENC 2012; international workshop on acoustic signal enhancement","author":"Hines"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"}],"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\/10446643.pdf?arnumber=10446643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:23:42Z","timestamp":1722576222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446643","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}