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

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 62 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:1609.03499, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1609.03499 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified (of 103 harvested samples) · 25 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 171 · with a code link: 83 · where Syntology ran a sample: 28 (21 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (28 of 171 tagged: 21 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 171, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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