{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T14:45:22Z","timestamp":1769179522576,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228529","type":"proceedings-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:04:59Z","timestamp":1769029499000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["StereoSync: Spatially-Aware Stereo Audio Generation from Video"],"prefix":"10.1109","author":[{"given":"Christian","family":"Marinoni","sequence":"first","affiliation":[{"name":"Sapienza University of Rome,Italy"}]},{"given":"Riccardo F.","family":"Gramaccioni","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Italy"}]},{"given":"Kazuki","family":"Shimada","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Takashi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Danilo","family":"Comminiello","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref2","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning (ICML)","volume":"202","author":"Huang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2700"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3376297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3005033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094853"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.9728\/dcs.2024.25.12.3811"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","volume":"139","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref15","first-page":"48855","article-title":"Diff-Foley: Synchronized video-to-audio synthesis with latent diffusion models","volume":"36","author":"Luo","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref17","article-title":"Stable-V2A: Synthesis of synchronized sound effects with temporal and semantic controls","author":"Gramaccioni","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref20","first-page":"304","article-title":"Mono-to-stereo through parametric stereo generation","volume-title":"Proceedings of the 24th International Society for Music Information Retrieval Conference, ISMIR 2023, Milan, Italy, November 5-9, 2023","author":"Serr\u00e0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3432393"},{"key":"ref22","article-title":"Both ears wide open: Towards language-driven spatial audio generation","author":"Sun","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463624"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00678"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01794"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref30","article-title":"EVA-CLIP: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref32","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"in International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref33","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_17"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref39","article-title":"Savgbench: Benchmarking spatially aligned audio-video generation","author":"Shimada","year":"2024"},{"key":"ref40","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref42","article-title":"Two vs. four-channel sound event localization and detection","author":"Wilkins","year":"2023"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228529.pdf?arnumber=11228529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T20:57:29Z","timestamp":1769115449000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228529","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}