Learning Style-aware Symbolic Music Representations By Adversarial Autoencoders

Abstract

We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational autoencoders with context information concerning music genre and style. Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE). The empirical analysis on a large scale benchmark shows that our model has a higher reconstruction accuracy than state-of-the-art models based on standard variational autoencoders. It is also able to create realistic interpolations between two musical sequences, smoothly changing the dynamics of the different tracks. Experiments show that the model can organise its latent space accordingly to low-level properties of the musical pieces, as well as to embed into the

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyvalenti2020learning

Related papers

• Domain Adversarial Training On Conditional Variational Auto-encoder For Controllable Music Generation (2022)0.00
• Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
• Amadeus: Autoregressive Model With Bidirectional Attribute Modelling For Symbolic Music (2025)0.00
• Unsupervised Generative Adversarial Alignment Representation For Sheet Music, Audio And Lyrics (2020)4.52
• Music2latent2: Audio Compression With Summary Embeddings And Autoregressive Decoding (2025)2.26
• On The Joint Minimization Of Regularization Loss Functions In Deep Variational Bayesian Methods For Attribute-controlled Symbolic Music Generation (2025)0.00
• Semi-supervised Neural Chord Estimation Based On A Variational Autoencoder With Latent Chord Labels And Features (2020)7.16
• Generating Lyrics With Variational Autoencoder And Multi-modal Artist Embeddings (2018)0.00