Methods › Audio › Generative Audio Models › WaveNet

WaveNet

171 papers tagged archive 2025-07-28

Introduced by Aaron van den Oord et al. in WaveNet: A Generative Model for Raw Audio

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

WaveNet is an audio generative model based on the PixelCNN architecture. In order to deal with long-range temporal dependencies needed for raw audio generation, architectures are developed based on dilated causal convolutions, which exhibit very large receptive fields.

The joint probability of a waveform x⃗ = { x₁, …, x_T } is factorised as a product of conditional probabilities as follows:

p(x⃗) = ∏ₜ₌₁ᵀ p(xₜ |x₁, …,xₜ₋₁)

Each audio sample xₜ is therefore conditioned on the samples at all previous timesteps.

PaperSource

Papers archive 2025-07-28

30 shown of 171, 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

20 shown of 121 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 Synthesis54
Text to Speech51
text-to-speech51
Decoder18
Text-To-Speech Synthesis16
Voice Conversion12
Audio Synthesis10
Audio Generation8
GPU8
Time Series7
Deep Learning6
Speech Enhancement6
Generative Adversarial Network5
Speech Recognition5
Time Series Analysis5
Transfer Learning5
Translation5
CPU4
Data Augmentation4
Graph Neural Network4

Usage over time archive 2025-07-28

Papers per year tagged with WaveNet: 2016 to 2025, peak 38 38 0 2016: 2 papers 2016 2017: 10 papers 2017 2018: 26 papers 2018 2019: 38 papers 2019 2020: 32 papers 2020 2021: 24 papers 2021 2022: 12 papers 2022 2023: 10 papers 2023 2024: 13 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (171 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

Generative Audio Models

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