From artificial neural networks to deep learning for music generation: history, concepts and trends

Jean-Pierre Briot
2020 Neural computing & applications (Print)  
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
more » ... es 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 example, 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. * an image recognition competition (the ImageNet large scale visual recognition challenge) was won by a deep neural network algorithm named AlexNet [33] , with a stunning margin over the other algorithms which were using handcrafted features. This striking victory was the event which ended the prevalent opinion that neural networks with many hidden layers could not be efficiently trained and which started the deep learning wave. 2 Audio source separation, often coined as the cocktail party effect, has been known for a long time to be a very difficult problem [5] .
doi:10.1007/s00521-020-05399-0 fatcat:yrjjfarnlbdphgaunk62luidg4