{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T16:58:41Z","timestamp":1769014721136,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023153","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"906-911","source":"Crossref","is-referenced-by-count":6,"title":["GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models"],"prefix":"10.1109","author":[{"given":"Matthew","family":"Baas","sequence":"first","affiliation":[{"name":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adver-sarial audio synthesis","author":"Donahue","year":"2018","journal-title":"ICLR"},{"key":"ref2","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Deep unsupervised learning using nonequilib-rium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref4","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Its raw! Audio generation with state-space models","author":"Goel","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00044"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref13","article-title":"Alias-free generative adversarial networks","author":"Karras","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Training generative adversarial net-works with limited data","author":"Karras","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Activation maximization generative adversarial nets","author":"Zhou","year":"2018","journal-title":"ICLR"},{"key":"ref17","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv preprint"},{"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","article-title":"Generative spoken language modeling from raw audio","author":"Lakhotia","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref23","article-title":"Which training methods for GANs do actually converge?","author":"Mescheder","year":"2018","journal-title":"ICML"},{"key":"ref24","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2018","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101244"},{"key":"ref26","article-title":"Generating diverse vocal bursts with StyleGAN2 and mel-spectrograms","author":"Jiralerspong","year":"2022","journal-title":"ICML ExVo Generate"},{"key":"ref27","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","author":"Tancik","year":"2020","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.525"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00127"},{"key":"ref35","first-page":"218","article-title":"Digital filters","volume-title":"System analysis by digital computer","author":"Kaiser","year":"1966"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023153.pdf?arnumber=10023153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:35:59Z","timestamp":1707813359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023153","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}