{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:39Z","timestamp":1775229759972,"version":"3.50.1"},"reference-count":40,"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\/icassp48485.2024.10446400","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1166-1170","source":"Crossref","is-referenced-by-count":8,"title":["Bass Accompaniment Generation Via Latent Diffusion"],"prefix":"10.1109","author":[{"given":"Marco","family":"Pasini","sequence":"first","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maarten","family":"Grachten","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lattner","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deepbach: A steerable model for bach chorales generation","volume-title":"ICML","author":"Hadjeres"},{"key":"ref2","article-title":"Music transformer: Generating music with long-term structure","volume-title":"ICLR","author":"Huang"},{"key":"ref3","article-title":"Figaro: Generating symbolic music with fine-grained artistic control","author":"von R\u00fctte","year":"2022"},{"key":"ref4","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref5","author":"Agostinelli","year":"2023","journal-title":"Musiclm: Generating music from text"},{"key":"ref6","author":"Mariani","year":"2023","journal-title":"Multi-source diffusion models for simultaneous music generation and separation"},{"key":"ref7","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref8","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref9","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref11","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref13","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","volume-title":"ICLR","author":"Mehri"},{"key":"ref14","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref15","article-title":"Generative adversarial nets","volume-title":"NeurIPS","author":"Goodfellow"},{"key":"ref16","article-title":"Adversarial audio synthesis","volume-title":"ICLR","author":"Donahue"},{"key":"ref17","article-title":"GANSynth: Adversarial neural audio synthesis","volume-title":"ICLR","author":"Engel"},{"key":"ref18","article-title":"Musika! fast infinite waveform music generation","volume-title":"ISMIR","author":"Pasini"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app10186627"},{"key":"ref20","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"ICLR","author":"Kong"},{"key":"ref21","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"ICLR","author":"Chen"},{"key":"ref22","volume-title":"Riffusion - stable diffusion for real-time music generation","author":"Forsgren","year":"2022"},{"key":"ref23","article-title":"Mo\\\u02c6 usai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref24","article-title":"Jen-1: Text-guided universal music generation with omnidirectional diffusion models","author":"Li","year":"2023"},{"key":"ref25","article-title":"DDSP: differentiable digital signal processing","volume-title":"ICLR","author":"Engel"},{"key":"ref26","article-title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","author":"Caillon","year":"2021"},{"key":"ref27","article-title":"Maximum likelihood training of scorebased diffusion models","volume-title":"NeurIPS","author":"Song"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref29","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.816"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"Crossformer: A versatile vision transformer hinging on cross-scale attention","volume-title":"ICLR","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref33","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref34","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00532"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref37","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref38","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans"},{"key":"ref39","article-title":"The mtg-jamendo dataset for automatic music tagging","volume-title":"Machine Learning for Music Discovery Workshop, ICML","author":"Bogdanov"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"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\/10446400.pdf?arnumber=10446400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:03Z","timestamp":1722573423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446400","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}