Papers › RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly...

RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses

1 Nov 2021arXiv:2111.00962archive 2025-07-28

Shengyuan Xu, Wenxiao Zhao, Jing Guo

Most GAN(Generative Adversarial Network)-based approaches towards high-fidelity waveform generation heavily rely on discriminators to improve their performance. However, GAN methods introduce much uncertainty into the generation process and often result in mismatches of pitch and intensity, which is fatal when it comes to sensitive use cases such as singing voice synthesis(SVS). To address this problem, we propose RefineGAN, a high-fidelity neural vocoder focused on the robustness, pitch and intensity accuracy, and high-speed full-band audio generation. We applyed a pitch-guided refine architecture with a multi-scale spectrogram-based loss function to help stabilize the training process and maintain the robustness of the neural vocoder while using the GAN-based training method. Audio generated using this method shows a better performance in subjective tests when compared with the ground-truth audio. This result shows that the fidelity is even improved during the waveform reconstruction by eliminating defects produced by recording procedures. Moreover, it shows that models trained on a specified type of data can perform on totally unseen language and unseen speaker identically well. Generated sample pairs are provided onhttps://timedomain-tech.github.io/refinegan/.

PaperPDFCode

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

fishaudio/vocoder mentioned on GitHubpytorchSyntology: not harvested report
IAHispano/Applio pytorchMITSyntology: 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

Audio GenerationSinging Voice Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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