mlsanityData to 7 Oct 2026

PIANOTREE VAE: Structured Representation Learning for Polyphonic Music

arXiv 2008.07118 ↗First posted 17 Aug 2020eess.AS cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE). However, most, if not all, viable attempts on this problem have largely been limited to monophonic music. Normally composed of richer modality and more complex musical structures, the polyphonic counterpart has yet to be addressed in the context of music representation learning. In this work, we propose the PianoTree VAE, a novel tree-structure extension upon VAE aiming to fit the polyphonic music learning. The experiments prove the validity of the PianoTree VAE via (i)-semantically meaningful latent code for polyphonic segments; (ii)-more satisfiable reconstruction aside of decent geometry learned in the latent space; (iii)-this model's benefits to the variety of the downstream music generation.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 6; 2024: 5; 2025: 3; 2026: 1.

25 papers.

Sort:

By area:

  1. 2021Symbolic Music Generation with Diffusion Modelscited by 152
  2. 2024Foundation Models for Music: A Surveycited by 34
  3. 2022Multitrack Music Transformercited by 28
  4. 2022A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modelingcited by 17
  5. 2021Music Composition with Deep Learning: A Reviewcited by 12
  6. 2021Structure-Enhanced Pop Music Generation via Harmony-Aware Learningcited by 11
  7. 2022JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAEcited by 11
  8. 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
  9. 2023Structured Multi-Track Accompaniment Arrangement via Style Prior Modellingcited by 9
  10. 2023Exploring XAI for the Arts: Explaining Latent Space in Generative Musiccited by 8
  11. 2021Audio-to-symbolic Arrangement via Cross-modal Music Representation Learningcited by 6
  12. 2024Nested Music Transformer: Sequentially Decoding Compound Tokens in Symbolic Music and Audio Generationcited by 5
13 more
  1. 2022Vis2Mus: Exploring Multimodal Representation Mapping for Controllable Music Generationcited by 4
  2. 2023Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AIcited by 4
  3. 2024α-TCVAE: On the relationship between Disentanglement and Diversitycited by 4
  4. 2022A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectivescited by 3
  5. 2023An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generationcited by 2
  6. 2023Graph-based Polyphonic Multitrack Music Generationcited by 2
  7. 2024Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generationcited by 2
  8. 2025PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generationcited by 2
  9. 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Stepscited by 2
  10. 2022Flat Latent Manifolds for Human-machine Co-creation of Musiccited by 1
  11. 2023Motif-Centric Representation Learning for Symbolic Musiccited by 1
  12. 2025From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-trainingcited by 1
  13. 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understandingcited by 1