Methods › Audio › Generative Audio Models › WaveVAE
WaveVAE
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
WaveVAE is a generative audio model that can be used as a vocoder in text-to-speech systems. It is a VAE based model that can be trained from scratch by jointly optimizing the encoder q_ϕ(𝐳|𝐱, 𝐜) and decoder p_θ(𝐱|𝐳, 𝐜), where 𝐳 is latent variables and 𝐜 is the mel spectrogram conditioner.
The encoder of WaveVAE q_ϕ(𝐳|𝐱) is parameterized by a Gaussian autoregressive WaveNet that maps the ground truth audio x into the same length latent representation 𝐳. The decoder p_θ(𝐱|𝐳) is parameterized by the one-step ahead predictions from an inverse autoregressive flow.
The training objective is the ELBO for the observed 𝐱 in the VAE.
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.
-
Autoregressive Speech Synthesis with Next-Distribution Prediction 22 Dec 2024 · 0 repositories · arXiv:2412.16846
-
Non-Autoregressive Neural Text-to-Speech 21 May 2019 · 2 repositories · arXiv:1905.08459Syntology ran 2 of 7 samples · 5 unverified
Tasks archive 2025-07-28
7 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 |
|---|---|
| Text to Speech | 2 |
| text-to-speech | 2 |
| Language Modeling | 1 |
| Language Modelling | 1 |
| Prediction | 1 |
| Speech Synthesis | 1 |
| Text-To-Speech Synthesis | 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