Methods › Sequential › Sequence To Sequence Models › GAN-TTS
GAN-TTS
Introduced by Mikołaj Bińkowski et al. in High Fidelity Speech Synthesis with Adversarial Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
GAN-TTS is a generative adversarial network for text-to-speech synthesis. The architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators which operate on random windows of different sizes. The discriminators analyze the audio both in terms of general realism, as well as how well the audio corresponds to the utterance that should be pronounced.
The generator architecture consists of several GBlocks, which are residual based (dilated) convolution blocks. GBlocks 3–7 gradually upsample the temporal dimension of hidden representations by factors of 2, 2, 2, 3, 5, while the number of channels is reduced by GBlocks 3, 6 and 7 (by a factor of 2 each). The final convolutional layer with Tanh activation produces a single-channel audio waveform.
Instead of a single discriminator, GAN-TTS uses an ensemble of Random Window Discriminators (RWDs) which operate on randomly sub-sampled fragments of the real or generated samples. The ensemble allows for the evaluation of audio in different complementary ways.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
A Spectral Energy Distance for Parallel Speech Synthesis 3 Aug 2020 · 2 repositories · arXiv:2008.01160Syntology ran 0 of 3 samples · 3 unverified
-
High Fidelity Speech Synthesis with Adversarial Networks 25 Sep 2019 · 3 repositories · arXiv:1909.11646Syntology ran 2 of 5 samples · 3 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Speech Synthesis | 2 |
| Generative Adversarial Network | 1 |
| Text to Speech | 1 |
| Vocal Bursts Intensity Prediction | 1 |
| scoring rule | 1 |
| text-to-speech | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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