{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:02:38Z","timestamp":1776888158229,"version":"3.51.2"},"reference-count":36,"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\/icassp49660.2025.10888882","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models"],"prefix":"10.1109","author":[{"given":"Saksham Singh","family":"Kushwaha","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbo","family":"Ma","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark R. P.","family":"Thomas","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avery","family":"Bruni","sequence":"additional","affiliation":[{"name":"Dolby Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315707525-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10603"},{"key":"ref4","article-title":"Neural synthesis of binaural speech from mono audio","volume-title":"International Conference on Learning Representations","author":"Richard"},{"key":"ref5","article-title":"Self-supervised generation of spatial audio for 360 video","volume":"31","author":"Morgado","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref8","first-page":"859","article-title":"Ambisonics in multichannel broadcasting and video","volume":"33","author":"Gerzon","year":"1985","journal-title":"J. Audio Eng. Soc."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2307\/3680991"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17207-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref12","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Vintage: Joint video and text conditioning for holistic audio generation","author":"Kushwaha","year":"2024"},{"key":"ref14","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref17","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref18","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang","year":"2023"},{"key":"ref19","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref21","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref22","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024"},{"key":"ref23","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"key":"ref24","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref25","article-title":"Spatial decomposition method on non-uniform reproduction layouts","volume-title":"Ph.D. dissertation, Master\u2019s thesis","author":"Hold","year":"2019"},{"key":"ref26","article-title":"Analyzing the effect of equal-angle spatial discretization on sound event localization and detection","volume-title":"Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022)","author":"Kushwaha"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248194"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref29","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"Politis","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref31","article-title":"The nigens general sound events database","author":"Trowitzsch","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17207-7"},{"key":"ref33","article-title":"Fr\\\u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref35","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446118"}],"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\/10888882.pdf?arnumber=10888882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:47Z","timestamp":1774416407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888882","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}