{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T06:29:20Z","timestamp":1723789760184},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096288","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"source":"Crossref","is-referenced-by-count":6,"title":["Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Takuhiro","family":"Kaneko","sequence":"first","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shogo","family":"Seki","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref35","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv preprint arXiv 1607 08022"},{"key":"ref13","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref34","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11152"},{"key":"ref37","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref15","first-page":"5210","article-title":"Auto-VC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"Proc ICML"},{"key":"ref36","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proc NIPS"},{"key":"ref14","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"},{"key":"ref31","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"lindbo larsen","year":"2016","journal-title":"Proc ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref33","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref2","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 03286"},{"key":"ref39","first-page":"3481","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"ref19","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref18","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref24","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref23","first-page":"3642","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref26","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc MICCAI"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00823"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"Proc ICLR"},{"key":"ref41","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref22","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref21","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref28","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"yamagishi","year":"2016","journal-title":"The Centre for Speech Technology Research"},{"key":"ref27","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref29","article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"sonobe","year":"2017","journal-title":"arXiv preprint arXiv 1711 00540"},{"key":"ref8","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref3","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref5","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096288.pdf?arnumber=10096288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:55Z","timestamp":1700507215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096288","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}