A Survey of Automated Harmonic Analysis Techniques
Pedro Kröger, Alexandre Passos, Marcos Sampaio
December 10th, 2010
The problem of using the computer for automated harmonic analysis has been approached from several different directions with varied degree of success. Techniques from artificial intelligence such as machine learning and pattern recognition have been used. The division of a given piece in harmonic significant segments is a crucial problem in the area of automated harmonic analysis, although it is still underrepresented in the literature. Also, most algorithms ignore relevant contextual clues and little has been done towards establishing standard benchmarks. This paper presents a comprehensive survey of the existing literature on the subject.