mlsanityData to 7 Oct 2026

Encoding Musical Style with Transformer Autoencoders

arXiv 1912.05537 ↗First posted 10 Dec 2019cs.SD cs.LG eess.AScited by 35

Not on the map. Why?

Abstract (arXiv)

We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer autoencoder, which aggregates encodings of the input data across time to obtain a global representation of style from a given performance. We show it is possible to combine this global representation with other temporally distributed embeddings, enabling improved control over the separate aspects of performance style and melody. Empirically, we demonstrate the effectiveness of our method on various music generation tasks on the MAESTRO dataset and a YouTube dataset with 10,000+ hours of piano performances, where we achieve improvements in terms of log-likelihood and mean listening scores as compared to baselines.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 8; 2024: 6; 2025: 3; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Symbolic Music Generation with Diffusion Modelscited by 152
  2. 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
  3. 2024Symbolic Music Generation with Non-Differentiable Rule Guided Diffusioncited by 52
  4. 2023MuseCoco: Generating Symbolic Music from Textcited by 50
  5. 2021MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAEcited by 39
  6. 2022Attention Mechanism in Neural Networks: Where it Comes and Where it Goescited by 29
  7. 2023Byte Pair Encoding for Symbolic Musiccited by 19
  8. 2023V2Meow: Meowing to the Visual Beat via Video-to-Music Generationcited by 18
  9. 2021Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encodingcited by 14
  10. 2022PART: Pre-trained Authorship Representation Transformercited by 13
  11. 2022Symbolic music generation conditioned on continuous-valued emotionscited by 12
  12. 2022A Review of Intelligent Music Generation Systemscited by 11
23 more
  1. 2023Transformers in Reinforcement Learning: A Surveycited by 11
  2. 2023Understanding writing style in social media with a supervised contrastively pre-trained transformercited by 11
  3. 2022Pop2Piano : Pop Audio-based Piano Cover Generationcited by 10
  4. 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Modelscited by 8
  5. 2021Ember: No-Code Context Enrichment via Similarity-Based Keyless Joinscited by 7
  6. 2023Reconstructing Human Expressiveness in Piano Performances with a Transformer Networkcited by 6
  7. 2021Generative Pretraining for Paraphrase Evaluationcited by 4
  8. 2024Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenizationcited by 3
  9. 2025Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generationcited by 3
  10. 2021A Contextual Latent Space Model: Subsequence Modulation in Melodic Sequencecited by 2
  11. 2024A Survey of Music Generation in the Context of Interactioncited by 2
  12. 2024BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Featurescited by 2
  13. 2024WaveTransfer: A Flexible End-to-end Multi-instrument Timbre Transfer with Diffusioncited by 2
  14. 2021Calliope -- A Polyphonic Music Transformercited by 1
  15. 2022FIGARO: Generating Symbolic Music with Fine-Grained Artistic Controlcited by 1
  16. 2024Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generationcited by 1
  17. 2025LZMidi: Compression-Based Symbolic Music Generationcited by 1
  18. 2021MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveformscited by 0
  19. 2021Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experiencecited by 0
  20. 2022Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfercited by 0
  21. 2023NPS: A Framework for Accurate Program Sampling Using Graph Neural Networkcited by 0
  22. 2025On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generationcited by 0
  23. 2026Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimationcited by 0