Advancing music generation via accelerated deep learning (with HPC-AI Technology)

The capability of generating music in real-time from large-scale music data is becoming a key topic in generative art. Deep music generation is to use computers utilising Deep Neural Network (DNN) architectures to automatically generate music. Unfortunately, to cope with the growth in music data, the DNN models also have grown in parameters from multi-millions (e.g., RNN and LSTMs) to multi-billions (e.g., GPT-3). Consequently, the time, computational costs and carbon footprint required to train and deploy DNN models for music generation have exploded.
This PhD project aims to investigate, propose and implement novel optimisations on the algorithmic and system levels to accelerate the training and inference of DNN models for music generation in HPC or Cloud environments. This involves solving a hard optimisation problem with multi-objectives involving time, computation and energy efficiency. Based on these optimisations, we will develop software frameworks that can accelerate Deep Music Generation tasks. This will help advance the field of music generation by making it more sustainable and affordable.