Methods › Audio › Audio Model Blocks › DV3 Convolution Block
DV3 Convolution Block
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
DV3 Convolution Block is a convolutional block used for the Deep Voice 3 text-to-speech architecture. It consists of a 1-D convolution with a gated linear unit and a residual connection. In the Figure, c denotes the dimensionality of the input. The convolution output of size 2 ·c is split into equal-sized portions: the gate vector and the input vector. A scaling factor √(0.5) is used to ensure that we preserve the input variance early in training. The gated linear unit provides a linear path for the gradient flow, which alleviates the vanishing gradient issue for stacked convolution blocks while retaining non-linearity. To introduce speaker-dependent control, a speaker-dependent embedding is added as a bias to the convolution filter output, after a softsign function. The authors use the softsign nonlinearity because it limits the range of the output while also avoiding the saturation problem that exponential based nonlinearities sometimes exhibit. Convolution filter weights are initialized with zero-mean and unit-variance activations throughout the entire network.
Papers archive 2025-07-28
9 shown of 9, 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.
-
Clarinet: A Music Retrieval System 23 Oct 2022 · 1 repository · arXiv:2210.12648
-
Learning from a Complementary-label Source Domain: Theory and Algorithms 4 Aug 2020 · 1 repository · arXiv:2008.01454Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
-
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation 29 Jul 2020 · 1 repository · arXiv:2007.14612Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
-
Parallel Neural Text-to-Speech 1 Jan 2020 · 0 repositories
-
Multi-Speaker End-to-End Speech Synthesis 9 Jul 2019 · 0 repositories · arXiv:1907.04462
-
Non-Autoregressive Neural Text-to-Speech 21 May 2019 · 2 repositories · arXiv:1905.08459Syntology ran 2 of 7 samples · 5 unverified
-
Neural source-filter waveform models for statistical parametric speech synthesis 27 Apr 2019 · 0 repositories · arXiv:1904.12088
-
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech 19 Jul 2018 · 5 repositories · arXiv:1807.07281Syntology ran 1 of 13 samples · 12 unverified
-
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning 20 Oct 2017 · 7 repositories · arXiv:1710.07654Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
9 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 | 4 |
| Text to Speech | 4 |
| text-to-speech | 4 |
| Domain Adaptation | 2 |
| Unsupervised Domain Adaptation | 2 |
| GPU | 1 |
| Melody Extraction | 1 |
| Retrieval | 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