Pith. sign in

REVIEW 4 cited by

A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1803.05428 v5 pith:KDPXFHSC submitted 2018-03-13 cs.LG cs.SDeess.ASstat.ML

classification cs.LGcs.SDeess.ASstat.ML
keywords modellatentstructuredataembeddingshierarchicalissuelong-term
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we demonstrate, existing recurrent VAE models have difficulty modeling sequences with long-term structure. To address this issue, we propose the use of a hierarchical decoder, which first outputs embeddings for subsequences of the input and then uses these embeddings to generate each subsequence independently. This structure encourages the model to utilize its latent code, thereby avoiding the "posterior collapse" problem, which remains an issue for recurrent VAEs. We apply this architecture to modeling sequences of musical notes and find that it exhibits dramatically better sampling, interpolation, and reconstruction performance than a "flat" baseline model. An implementation of our "MusicVAE" is available online at http://g.co/magenta/musicvae-code.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Translating Visual Art into Music

    cs.CV 2019-09 conditional novelty 6.0 of 10

    An unsupervised image-to-music model, SynVAE, lets human listeners match generated music to its source image with up to 73% accuracy.

  2. Workflow-Based Evaluation of Music Generation Systems

    eess.AS 2025-06 conditional novelty 5.0 of 10

    A single-producer workflow evaluation of eight music AI tools finds they work as idea and sound generators but not as complete composers, and proposes a reusable framework.

  3. Calliope: An Online Generative Music System for Symbolic Multi-Track Composition

    cs.HC 2025-04 conditional novelty 4.0 of 10

    Calliope is a browser-based system that wraps the MMM transformer model in an interface for multi-track MIDI generation, editing, batch sampling, and DAW streaming.

  4. Apollo: An Interactive Environment for Generating Symbolic Musical Phrases using Corpus-based Style Imitation

    cs.HC 2025-04 conditional novelty 4.0 of 10

    Apollo is a new interactive desktop application that combines user-managed MIDI corpora, trainable style imitation models, and graphical controls for generating symbolic musical phrases.

Pith tools