Computational approaches to music composition and style imitation have engaged musicians, music scholars, and computer scientists since the early days of computing. Music generation research has generally employed one of two strategies: knowledge-based methods that model style through explicitly formalized rules, and data mining methods that apply machine learning to induce statistical models of musical style. The five chapters in this book illustrate the range of tasks and design choices in current music generation research applying machine learning techniques and highlighting recurring research issues such as training data, music representation, candidate generation, and evaluation. The contributions focus on different aspects of modeling and generating music, including melody, chord sequences, ornamentation, and dynamics. Models are induced from audio data or symbolic data. This book was originally published as a special issue of the Journal of Mathematics and Music.
Table of Contents
Introduction: Machine learning and music generation 1. Chord sequence generation with semiotic patterns 2. A machine learning approach to ornamentation modeling and synthesis in jazz guitar 3. Analysis of analysis: Using machine learning to evaluate the importance of music parameters for Schenkerian analysis 4. Mapping between dynamic markings and performed loudness: a machine learning approach 5. Data-based melody generation through multi-objective evolutionary computation
José M. Iñesta is a Professor in the Department of Software and Computing Systems at the Universidad de Alicante, Spain.
Darrell Conklin is a Professor in the Department of Computer Science and Artificial Intelligence at the University of the Basque Country.
Rafael Ramírez-Melendez is Associate Professor in the Music Technology Group in the Department of Information and Communication Technologies at the Universidad Pompeu Fabra, Barcelona, Spain.
Thomas M. Fiore is Associate Professor of Mathematics at the University of Michigan-Dearborn, MI, USA.