Methods › Audio › Audio Model Blocks › FiLM Module
FiLM Module
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Feature-wise linear modulation (FiLM) module combines information from both noisy waveform and input mel-spectrogram. It is used in the WaveGrad model. The authors also added iteration index n which indicates the noise level of the input waveform by using the Transformer sinusoidal positional embedding. To condition on the noise level directly, n is replaced by √(α̅) and a linear scale C = 5000 is applied. The FiLM module produces both scale and bias vectors given inputs, which are used in a UBlock for feature-wise affine transformation as:
γ(D, √(α̅)) ⊙U + ζ(D, √(α̅))
where γ and ζ correspond to the scaling and shift vectors from the FiLM module, D is the output from corresponding DBlock, U is an intermediate output in the UBlock.
Papers archive 2025-07-28
7 shown of 7, 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.
-
GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model 9 Feb 2024 · 0 repositories · arXiv:2402.15516
-
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis 25 Mar 2022 · 1 repository · arXiv:2203.13508Syntology ran 5 of 6 samples · 1 unverified
-
InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training 8 Feb 2022 · 0 repositories · arXiv:2202.03751
-
Quasi-Taylor Samplers for Diffusion Generative Models based on Ideal Derivatives 26 Dec 2021 · 0 repositories · arXiv:2112.13339
-
VocBench: A Neural Vocoder Benchmark for Speech Synthesis 6 Dec 2021 · 1 repository · arXiv:2112.03099
-
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis 17 Jun 2021 · 3 repositories · arXiv:2106.09660Syntology ran 2 of 2 samples · 0 unverified
-
WaveGrad: Estimating Gradients for Waveform Generation 2 Sep 2020 · 7 repositories · arXiv:2009.00713Syntology ran 1 of 3 samples · 2 unverified · 1 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 | 5 |
| Denoising | 2 |
| Image Generation | 2 |
| Text-To-Speech Synthesis | 2 |
| Text to Speech | 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