Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

Abstract

We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our approach outperforms many traditional models of polyphonic music on a variety of realistic datasets. We show how our musical language model can serve as a symbolic prior to improve the accuracy of polyphonic transcription.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

References in corpus (1)

• Conditional Restricted Boltzmann Machines for Structured Output Prediction

Cited by in corpus (1)

• On the difficulty of training Recurrent Neural Networks