Modelling High-Dimensional Sequences with LSTM-RTRBM: Application to Polyphonic Music Generation

Lyu, Qi (Tsinghua University) | Wu, Zhiyong (Tsinghua University) | Zhu, Jun (Tsinghua University) | Meng, Helen (The Chinese University of Hong Kong)

AAAI Conferences 

We propose an automatic music generation demo based on artificial neural networks, which integrates the ability of Long Short-Term Memory (LSTM) in memorizing and retrieving useful history information, together with the advantage of Restricted Boltzmann Machine (RBM) in high dimensional data modelling. Our model can generalize to different musical styles and generate polyphonic music better than previous models.