Learning Musical Structure and Style with Neural Networks
Dominik Hörnel, Wolfram Menzel · Computer Music Journal · 1998
The investigation of neural information structures in music is a rather new, exciting research area bringing together different disciplines such as computer science, musicology, mathematics, and cognitive science. One of its objectives is to develop neural network models that are able to learn from musical compositions the structural elements that characterize a composer's personal style. This has been a starting point for research activities at our institute in recent years. We have the impression that artificial neural networks, when carefully developed, can be sensitive, powerful, and innovative tools for capturing the specificity of a certain composer's style.