Artificial Intelligence for Classical Music composition in different eras

Abstract

Artificial Intelligence could bring music composition to another level with limitless possibilities as an assistant for human musicians or an AI musician itself. Living in a digital era, Classical Music plays a dominant role in commercial films, movie trailers, game soundtracks, and more. In general, Classical Music can be subdivided into Baroque, Classical, Romantic, and Modernist eras. Among all Classical Music of different periods, musicians nowadays might be proficient in only one of them. With this AI it would be possible for composers, musicians, or even non-specialists without prior knowledge of Classical Music theories and backgrounds could quickly compose Classical Music according to their favorite musical era for many practical purposes.

In recent years, AI arts, especially the AI music generation, have become popular, and related technologies have become available to people. However, most AI music generator platforms mainly focus on creating modern music, and they usually categorize all genres of Classical Music into a single category – Classical Music. Most research on AI music generation adopted LSTMs or other types of algorithms published earlier to generate music. Thus, it is worthwhile to discover different types of newer machine learning methods such as CNN-GANs for this task, and perhaps the proposed models could set successful precedence in this research area.

This project aims to generate Classical Music using generative models – Bi-LSTM and CNN-GAN to compose Classical Music for some particular Classical Music genres and evaluate their performance respectively and collectively. Also, to further explore and strengthen the area of Artificial Intelligence in music composition.