Papers › Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with...

Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with Pitch Prediction

31 May 2024arXiv:2405.21069archive 2025-07-28

Jean-Marc Valin, Ahmed Mustafa, Jan Büthe

Neural vocoders are now being used in a wide range of speech processing applications. In many of those applications, the vocoder can be the most complex component, so finding lower complexity algorithms can lead to significant practical benefits. In this work, we propose FARGAN, an autoregressive vocoder that takes advantage of long-term pitch prediction to synthesize high-quality speech in small subframes, without the need for teacher-forcing. Experimental results show that the proposed 600~MFLOPS FARGAN vocoder can achieve both higher quality and lower complexity than existing low-complexity vocoders. The quality even matches that of existing higher-complexity vocoders.

PaperPDFCode

Code

mozilla/LPCNet mentioned on GitHubtfBSD-3-Clause report
xiph/lpcnet mentioned on GitHubtf 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.

Code Syntology ran Syntology

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

Tasks

Speech Synthesis

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