{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:30:14Z","timestamp":1786476614577,"version":"build-2736575974"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176211"],"award-info":[{"award-number":["62176211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Project of the Science, Technology, and Innovation Commission of Shenzhen Municipality, China","award":["GJHZ20240218114401004"],"award-info":[{"award-number":["GJHZ20240218114401004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3673480","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:38:04Z","timestamp":1773347884000},"page":"7112-7123","source":"Crossref","is-referenced-by-count":0,"title":["DualSpec: Text-to-Spatial-Audio Generation via Dual-Spectrogram Guided Diffusion Model"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9166-2012","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sizhou","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7908-779X","authenticated-orcid":false,"given":"Linfeng","family":"Feng","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9002-6658","authenticated-orcid":false,"given":"Jichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7694-193X","authenticated-orcid":false,"given":"Xiao-Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University","place":["Xi'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref3","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Liu","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref7","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"issue":"70","key":"ref9","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2019.0024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827516"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2372062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2019.0024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414750"},{"key":"ref18","article-title":"Neural synthesis of binaural speech from mono audio","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Richard","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1721"},{"key":"ref20","article-title":"AudioSpa: Spatializing sound events with text","author":"Feng","year":"2025"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations, Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref23","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. 9th Int. Conf. Learn. Representations,","author":"Chen"},{"key":"ref24","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. 9th Int. Conf. Learn. Representations,","author":"Kong","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3359769"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.247"},{"key":"ref32","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Representations,","author":"Song","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref34","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106679"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref42","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chap. Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Kim","year":"2019"},{"key":"ref43","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017"},{"key":"ref44","article-title":"Budgeted training: Rethinking deep neural network training under resource constraints","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref45","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"in Adv. Neural Inf. Process. Syst."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11433063.pdf?arnumber=11433063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:03:54Z","timestamp":1786475034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3673480","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}