Rethinking Recurrent Latent Variable Model For Music Composition

Abstract

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.

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keykoh2018rethinking

Related papers

• Coupled Recurrent Models For Polyphonic Music Composition (2018)0.00
• A Predictive Model For Music Based On Learned Interval Representations (2018)0.00
• Semi-recurrent Cnn-based VAE-GAN For Sequential Data Generation (2018)10.21
• The Effect Of Explicit Structure Encoding Of Deep Neural Networks For Symbolic Music Generation (2018)11.49
• Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
• Convolutional Recurrent Neural Networks For Music Classification (2016)18.98
• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Music Artist Classification With Convolutional Recurrent Neural Networks (2019)11.93