{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:45:36Z","timestamp":1778082336312,"version":"3.51.4"},"reference-count":27,"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\/icassp48485.2024.10446088","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1116-1120","source":"Crossref","is-referenced-by-count":18,"title":["STEMGEN: A Music Generation Model That Listens"],"prefix":"10.1109","author":[{"given":"Julian D.","family":"Parker","sequence":"first","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janne","family":"Spijkervet","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katerina","family":"Kosta","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Furkan","family":"Yesiler","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju-Chiang","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matt","family":"Avent","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitong","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duc","family":"Le","sequence":"additional","affiliation":[{"name":"ByteDance Inc.,SAMI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"WaveNet: A Generative Model for Raw Audio","author":"Oord","year":"2016"},{"key":"ref2","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref3","article-title":"High-Fidelity Audio Compression with Improved RVQ-GAN","author":"Kumar","year":"2023"},{"key":"ref4","article-title":"MusicLM: Generating Music From Text","author":"Agostinelli","year":"2023"},{"key":"ref5","article-title":"Simple and Controllable Music Generation","author":"Copet","year":"2023"},{"key":"ref6","article-title":"Vamp-Net: Music Generation via Masked Acoustic Token Modeling","author":"Garcia","year":"2023"},{"key":"ref7","article-title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","author":"Huang","year":"2023"},{"key":"ref8","article-title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","author":"Hawthorne","year":"2022"},{"key":"ref9","article-title":"Mo\u00fbsai: Text-to-Music Generation with Long-Context Latent Diffusion","author":"Schneider","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198161547.001.0001"},{"key":"ref11","article-title":"Jukebox: A Generative Model for Music","author":"Dhariwal","year":"2020"},{"key":"ref12","article-title":"SingSong: Generating musical accompaniments from singing","author":"Donahue","year":"2023"},{"key":"ref13","article-title":"Multi-Source Diffusion Models for Simultaneous Music Generation and Separation","author":"Mariani","year":"2023"},{"key":"ref14","article-title":"SoundStorm: Efficient Parallel Audio Generation","author":"Borsos","year":"2023"},{"key":"ref15","article-title":"CLAP: Learning Audio Concepts From Natural Language Supervision","author":"Elizalde","year":"2022"},{"key":"ref16","article-title":"Classifier-Free Diffusion Guidance","author":"Ho","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref18","article-title":"Complete MIDI 1.0 Detailed Specification","year":"2008"},{"key":"ref19","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref21","article-title":"The construction and evaluation of statistical models of melodic structure in music perception and composition","volume-title":"Ph.D. thesis","author":"Pearce","year":"2005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2006.23.5.377"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3849-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096688"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747048"},{"key":"ref26","article-title":"SpecTNT: a Time-Frequency Transformer for Music Audio","volume-title":"International Society for Music Information Retrieval conference","author":"Lu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747252"}],"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\/10446088.pdf?arnumber=10446088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:02:13Z","timestamp":1722574933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446088","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}