Papers › BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

6 Sep 2023arXiv:2309.02836archive 2025-07-28

Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji

Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between real and fake data in the feature space. In the literature, it has been demonstrated that slicing adversarial network (SAN), an improved GAN training framework that can find the optimal projection, is effective in the image generation task. In this paper, we investigate the effectiveness of SAN in the vocoding task. For this purpose, we propose a scheme to modify least-squares GAN, which most GAN-based vocoders adopt, so that their loss functions satisfy the requirements of SAN. Through our experiments, we demonstrate that SAN can improve the performance of GAN-based vocoders, including BigVGAN, with small modifications. Our code is available at https://github.com/sony/bigvsan.

PaperPDFConference PDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

sony/bigvsan officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
sony/bigvsan_eval officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
IAHispano/Applio pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for... (arXiv:2306.00814; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Speech Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis LibriTTS BigVSAN (w/ snakebeta) M-STFT 0.7992 #6 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN (w/ snakebeta) MCD 0.4129 #6 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN (w/ snakebeta) PESQ 4.120 #6 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN (w/ snakebeta) Periodicity 0.0924 #6 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN (w/ snakebeta) V/UV F1 0.9644 #6 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN M-STFT 0.7881 #7 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN MCD 0.3381 #7 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN PESQ 4.116 #7 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN Periodicity 0.0935 #7 of 15 Archive leaderboard report
Speech Synthesis LibriTTS BigVSAN V/UV F1 0.9635 #7 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections