Methods › Audio › Audio Model Blocks › DV3 Convolution Block

DV3 Convolution Block

9 papers tagged archive 2025-07-28

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.

Source: Deep Voice 3: Scaling Text-to-Speech with Convolutional...See Code · r9y9/deepvoice3_pytorch

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.

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.

TaskPapers
Speech Synthesis4
Text to Speech4
text-to-speech4
Domain Adaptation2
Unsupervised Domain Adaptation2
GPU1
Melody Extraction1
Retrieval1
Text-To-Speech Synthesis1

Usage over time archive 2025-07-28

Papers per year tagged with DV3 Convolution Block: 2017 to 2022, peak 3 3 0 2017: 1 paper 2017 2018: 1 paper 2018 2019: 3 papers 2019 2020: 3 papers 2020 2021: 0 papers 2021 2022: 1 paper 2022
Papers per year the archive tags with this method, by the paper's archive date (9 dated). Bars are counts, not a trend claim.

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

Audio Model Blocks

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