Rethinking Recurrent Latent Variable Model for Music Composition
This addresses music composition automation for musicians and AI researchers, but appears incremental as it builds on existing encoder-decoder and latent variable approaches.
The authors tackled the problem of generating novel music sequences by proposing a Convolutional Variational Recurrent Neural Network, which showed better statistical resemblance to training data structure compared to other neural networks.
We present a model for capturing musical features and creating novel sequences of music, called the Convolutional Variational Recurrent Neural Network. To generate sequential data, the model uses an encoder-decoder architecture with latent probabilistic connections to capture the hidden structure of music. Using the sequence-to-sequence model, our generative model can exploit samples from a prior distribution and generate a longer sequence of music. We compare the performance of our proposed model with other types of Neural Networks using the criteria of Information Rate that is implemented by Variable Markov Oracle, a method that allows statistical characterization of musical information dynamics and detection of motifs in a song. Our results suggest that the proposed model has a better statistical resemblance to the musical structure of the training data, which improves the creation of new sequences of music in the style of the originals.