Polyphonic Music Generation by Modeling Temporal Dependencies Using a RNN-DBN

TL;DR

This paper introduces RNN-DBN, a novel model combining RNNs and Deep Belief Networks to effectively generate polyphonic music by capturing complex temporal dependencies.

Contribution

The paper presents a new hybrid RNN-DBN model that enhances sequence modeling and music generation capabilities over existing methods.

Findings

RNN-DBN outperforms traditional models in polyphonic music generation.

The hybrid model captures complex temporal dependencies effectively.

Demonstrates improved high-level data representation for sequence tasks.

Abstract

In this paper, we propose a generic technique to model temporal dependencies and sequences using a combination of a recurrent neural network and a Deep Belief Network. Our technique, RNN-DBN, is an amalgamation of the memory state of the RNN that allows it to provide temporal information and a multi-layer DBN that helps in high level representation of the data. This makes RNN-DBNs ideal for sequence generation. Further, the use of a DBN in conjunction with the RNN makes this model capable of significantly more complex data representation than an RBM. We apply this technique to the task of polyphonic music generation.