{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:02:39Z","timestamp":1776888159513,"version":"3.51.2"},"reference-count":29,"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\/icassp49660.2025.10889311","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model"],"prefix":"10.1109","author":[{"given":"Mojtaba","family":"Heydari","sequence":"first","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehrez","family":"Souden","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno","family":"Conejo","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Atkins","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"Proc. 40th PMLR ICML","author":"Liu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref3","first-page":"12652","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Proc. 41st PMLR ICML, 235","author":"Evans"},{"key":"ref4","article-title":"Learning Spatially-Aware Language and Audio Embeddings","author":"Devnani","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref6","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cai59869.2024.00146"},{"key":"ref8","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref9","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362645"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/3680991"},{"key":"ref12","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref14","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Mulan: A joint embedding of music audio and natural language","author":"Huang","year":"2022"},{"key":"ref16","article-title":"Edmsound: Spectrogram based diffusion models for efficient and high-quality audio synthesis","author":"Zhu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29773"},{"key":"ref18","article-title":"Musicongen: Rhythm and chord control for transformer-based text-to-music generation","author":"Lan","year":"2024"},{"key":"ref19","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL, 2019","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref23","article-title":"Controllable music production with diffusion models and guidance gradients","author":"Levy","year":"2023"},{"key":"ref24","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2117"},{"key":"ref27","article-title":"auraloss: Audio focused loss functions in pytorch","volume-title":"Digital music research network one-day workshop (DMRN+ 15)","author":"Steinmetz"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1515\/9781400844807"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"}],"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\/10889311.pdf?arnumber=10889311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:43Z","timestamp":1774416283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889311","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}