Methods › Audio › Generative Audio Models › Jukebox

Jukebox

13 papers tagged archive 2025-07-28

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

Jukebox is a model that generates music with singing in the raw audio domain. It tackles the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers. It can condition on artist and genre to steer the musical and vocal style, and on unaligned lyrics to make the singing more controllable.

Three separate VQ-VAE models are trained with different temporal resolutions. At each level, the input audio is segmented and encoded into latent vectors hₜ, which are then quantized to the closest codebook vectors e_(zₜ). The code zₜ is a discrete representation of the audio that we later train our prior on. The decoder takes the sequence of codebook vectors and reconstructs the audio. The top level learns the highest degree of abstraction, since it is encoding longer audio per token while keeping the codebook size the same. Audio can be reconstructed using the codes at any one of the abstraction levels, where the least abstract bottom-level codes result in the highest-quality audio.

Source: Jukebox: A Generative Model for Music

In Syntology repository known, no verified implementation (declared_code; repositories: 12 listed of 12 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:2005.00341, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2005.00341) is about this method is not checked.

Origin paper of this answer, arXiv:2005.00341 (its page on this site · its page on Syntology).

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: 13 · with a code link: 7 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 13 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 13 of 13, 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 30 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
Information Retrieval4
Music Information Retrieval4
Genre classification3
Music Generation3
Retrieval3
Audio Source Separation2
Music Genre Classification2
Music Tagging2
Transfer Learning2
Attribute1
Audio Generation1
Benchmarking1
Chord Recognition1
Code Generation1
Data Augmentation1
Diversity1
Emotion Recognition1
Key Detection1
Language Modeling1
Language Modelling1

Usage over time archive 2025-07-28

Papers per year tagged with Jukebox: 2020 to 2024, peak 4 4 0 2020: 1 paper 2020 2021: 4 papers 2021 2022: 3 papers 2022 2023: 1 paper 2023 2024: 4 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (13 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