Previously, artificial neural networks have been used to capture only the informal properties of music. However, cognitive scientist Michael Dawson found that by training artificial neural networks to make basic judgments concerning tonal music, such as identifying the tonic of a scale or the quality of a musical chord, the networks revealed formal musical properties that differ dramatically from those typically presented in music theory. For example, where Western music theory identifies twelve distinct notes or pitch-classes, trained artificial neural networks treat notes as if they belong to only three of four different pitch-classes, a wildly different interpretation of the components of tonal music. Intended to introduce readers to the use of artificial neural networks in the study of music, this volume contains numerous case studies and research findings that address problems related to identifying scales, keys, classifying musical chords, and learning jazz chord progressions. A detailed analysis of networks is provided for each case study which together demonstrate that focusing on the internal structure of trained networks could yield important contributions to the field of music cognition.
Recommendations
Genre classification of music by tonal harmony
Machine Learning and MusicIn this paper we present a genre classification framework for audio music based on a symbolic classification system. Audio signals are transformed into a symbolic representation of harmony using a chord transcription algorithm, based on the computation ...
From Music Scores to Audio Recordings: Deep Pitch-Class Representations for Measuring Tonal Structures
The availability of digital music data in various modalities provides opportunities both for music enjoyment and music research. Regarding the latter, the computer-assisted analysis of tonal structures is a central topic. For Western classical music, ...
Tonal Description of Polyphonic Audio for Music Content Processing
We present a method to extract a description of the tonal aspects of music from polyphonic audio signals. We define this tonal description using different levels of abstraction, differentiating between low-level signal descriptors and high-level textual ...