{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T04:19:57Z","timestamp":1780892397618,"version":"3.54.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3359352","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:44:52Z","timestamp":1706553892000},"page":"1324-1335","source":"Crossref","is-referenced-by-count":7,"title":["Disentanglement in a GAN for Unconditional Speech Synthesis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3001-6292","authenticated-orcid":false,"given":"Matthew","family":"Baas","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adversarial audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref5","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref6","first-page":"7616","article-title":"Its raw! audio generation with state-space models","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Goel","year":"2022"},{"key":"ref7","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref8","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref9","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref10","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref13","first-page":"8107","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Karras","year":"2020"},{"key":"ref14","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karras","year":"2020"},{"key":"ref15","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023153"},{"key":"ref17","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"9","author":"Lakhotia","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref21","first-page":"21450","article-title":"Audio LDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref23","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1461"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101244"},{"key":"ref26","article-title":"Basic syntax from speech: Spontaneous concatenation in unsupervised deep neural networks","author":"Begu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.175"},{"key":"ref28","article-title":"Generating diverse vocal bursts with StyleGAN2 and mel-spectrograms","volume-title":"Proc. Int. Conf. Mach. Learn. ExVo Generate","author":"Jiralerspong","year":"2022"},{"key":"ref29","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref30","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tancik","year":"2020"},{"key":"ref31","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref36","first-page":"3478","article-title":"Which training methods for GANs do actually converge?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mescheder","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00127"},{"key":"ref38","first-page":"218","article-title":"Digital filters","volume-title":"System Analysis by Digital Computer","author":"Kaiser","year":"1966"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref40","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.525"},{"key":"ref42","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref43","article-title":"Activation maximization generative adversarial nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-970"},{"key":"ref45","volume-title":"Speech Enhancement","author":"Benesty","year":"2006"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref50","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747120"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1130"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10415490.pdf?arnumber=10415490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T11:26:18Z","timestamp":1707823578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10415490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3359352","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}