{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:47:42Z","timestamp":1776883662762,"version":"3.51.2"},"reference-count":41,"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"}],"funder":[{"DOI":"10.13039\/100009757","name":"National Institute of Advanced Industrial Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009757","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446121","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10121-10125","source":"Crossref","is-referenced-by-count":10,"title":["BIGVSAN: Enhancing Gan-Based Neural Vocoders with Slicing Adversarial Network"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Shibuya","sequence":"first","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Yuhta","family":"Takida","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"Fast-Speech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref3","author":"van den Oord","year":"2016","journal-title":"WaveNet: A generative model for raw audio"},{"key":"ref4","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. ICML","volume":"80","author":"Kalchbrenner"},{"key":"ref5","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. NeurIPS","volume":"32","author":"Kumar"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref7","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref8","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. ICML","volume":"80","author":"van den Oord"},{"key":"ref9","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume-title":"Proc. ICLR","author":"Ping"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683143"},{"key":"ref11","first-page":"3370","article-title":"FloWaveNet : A generative flow for raw audio","volume-title":"Proc. ICML","volume":"97","author":"Kim"},{"key":"ref12","first-page":"7706","article-title":"WaveFlow: A compact flow-based model for raw audio","volume-title":"Proc. ICML","volume":"119","author":"Ping"},{"key":"ref13","first-page":"14058","article-title":"NanoFlow: Scalable normalizing flows with sublinear parameter complexity","volume-title":"Proc. NeurIPS","volume":"33","author":"Lee"},{"key":"ref14","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref15","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref16","article-title":"PriorGrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref17","first-page":"803","article-title":"Spec-Grad: Diffusion probabilistic model based neural vocoder with adaptive noise spectral shaping","volume-title":"Proc. Interspeech","author":"Koizumi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095749"},{"key":"ref19","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. ICLR","author":"Xiao"},{"key":"ref20","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref21","author":"Takida","year":"2023","journal-title":"SAN: Inducing metrizability of gan with discriminative normalized linear layer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","author":"Lim","year":"2017","journal-title":"Geometric gan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1288"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref29","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. NeurIPS","volume":"29","author":"Nowozin"},{"key":"ref30","author":"Arjovsky","year":"2017","journal-title":"Wasserstein GAN"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref32","first-page":"1583","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume-title":"Proc. NeurIPS","volume":"33","author":"Ziyin"},{"key":"ref33","article-title":"auraloss: Audio focused loss functions in PyTorch","volume-title":"Proc. Digital Music Research Network One-day Workshop (DMRN+15)","author":"Steinmetz"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref36","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. ICLR","author":"Morrison"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746698"},{"key":"ref39","article-title":"The LJ Speech dataset","author":"Ito","year":"2017"},{"key":"ref40","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit version 0.92","author":"Yamagishi","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446121.pdf?arnumber=10446121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:28Z","timestamp":1722573508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446121","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}