A Classifying Variational Autoencoder with Application to Polyphonic Music Generation
This addresses a specific challenge in algorithmic music generation for researchers and practitioners by enabling better key modeling, though it is incremental as it builds on existing VAE frameworks.
The authors tackled the problem of generating polyphonic music in multiple keys by extending the variational autoencoder (VAE) with a classifier to handle discrete latent variables, resulting in models that outperform non-classifying versions in generating musical samples that stay in key, especially on untransposed data.
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classifier to infer the discrete class of the modeled data. To model sequential data, we can combine our Classifying VAE with a recurrent neural network such as an LSTM. We apply this model to algorithmic music generation, where our model learns to generate musical sequences in different keys. Most previous work in this area avoids modeling key by transposing data into only one or two keys, as opposed to the 10+ different keys in the original music. We show that our Classifying VAE and Classifying VAE+LSTM models outperform the corresponding non-classifying models in generating musical samples that stay in key. This benefit is especially apparent when trained on untransposed music data in the original keys.