{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:05:19Z","timestamp":1758121519153,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10627035","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"480-484","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing GAN-based Vocoders with Contrastive Learning Under Data-Limited Condition"],"prefix":"10.1109","author":[{"given":"Haoming","family":"Guo","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seth Z.","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiachen","family":"Lian","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gopala","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerald","family":"Friedland","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Enhancing gan-based vocoders with contrastive learning","volume-title":"M.S. thesis","author":"Guo","year":"2023"},{"journal-title":"Generative adversarial networks","year":"2014","author":"Goodfellow","key":"ref2"},{"key":"ref3","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Kumar","year":"2019"},{"article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","year":"2020","author":"Kong","key":"ref4"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lee","key":"ref5"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413528"},{"article-title":"Masked autoencoders that listen","year":"2022","author":"Huang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-816"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11225"},{"article-title":"Utts: Unsupervised tts with conditional disentangled sequential variational auto-encoder","year":"2022","author":"Lian","key":"ref15"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","year":"2022","author":"Shi","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"article-title":"Differentiable augmentation for data-efficient gan training","year":"2020","author":"Zhao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00783"},{"key":"ref20","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Karras","year":"2020"},{"key":"ref21","article-title":"Projected gans converge faster","author":"Sauer","year":"2021","journal-title":"CoRR"},{"article-title":"Training {gan}s with stronger augmentations via contrastive discriminator","volume-title":"International Conference on Learning Representations","author":"Jeong","key":"ref22"},{"key":"ref23","article-title":"Investigating why contrastive learning benefits robustness against label noise","author":"Xue","year":"2022","journal-title":"First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022"},{"key":"ref24","article-title":"Using self-supervised learning can improve model robustness and uncertainty","author":"Hendrycks","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00304"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949462"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref27"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref28"},{"article-title":"Vision-language navigation with self-supervised auxiliary reasoning tasks","year":"2019","author":"Zhu","key":"ref29"},{"article-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10627035.pdf?arnumber=10627035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:27:13Z","timestamp":1723786033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10627035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627035","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}