From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
It offers a comprehensive overview for researchers and practitioners interested in applying deep learning to creative content generation, specifically in music, but is incremental as it synthesizes existing work rather than introducing new methods.
This paper provides a tutorial on using deep learning for music generation, tracing its history from early artificial neural networks in the 1980s to modern techniques that learn musical styles from corpora and generate controlled samples.
The current wave of deep learning (the hyper-vitamined return of artificial neural networks) applies not only to traditional statistical machine learning tasks: prediction and classification (e.g., for weather prediction and pattern recognition), but has already conquered other areas, such as translation. A growing area of application is the generation of creative content, notably the case of music, the topic of this paper. The motivation is in using the capacity of modern deep learning techniques to automatically learn musical styles from arbitrary musical corpora and then to generate musical samples from the estimated distribution, with some degree of control over the generation. This paper provides a tutorial on music generation based on deep learning techniques. After a short introduction to the topic illustrated by a recent exemple, the paper analyzes some early works from the late 1980s using artificial neural networks for music generation and how their pioneering contributions have prefigured current techniques. Then, we introduce some conceptual framework to analyze the various concepts and dimensions involved. Various examples of recent systems are introduced and analyzed to illustrate the variety of concerns and of techniques.