Saunder January 24, 2011 10:39 book
This book provides a comprehensive introduction to the research on modeling hu-
mans’ emotion perception of music, a research topic that emerges in the face of the
explosive growth of digital music. Automatic recognition of the perceived emotion
of music allows users to retrieve and organize their music collections in a fashion
that is more content-centric than conventional metadata-based methods.
Building such a music emotion recognition system, however, is challenging be-
cause of the subjective nature of emotion perception. One needs to deal with issues
such as the reliability of ground truth data and the difficulty in evaluating the pre-
diction result, which do not exist in other pattern recognition problems such as face
recognition and speech recognition. This book provides the details of the methods
that have been developed to address the issues related to the ambiguity and granu-
larity of emotion description, the heavy cognitive load of emotion annotation, the
subjectivity of emotion perception, and the semantic gap between low-level audio
signal and high-level emotion perception.
Specifically, this book deals with a comprehensive introduction of the techniques
developed for emotion description and emotion recognition in Chapters 2 and 3.
Chapter 4 describes a regression-based computational framework that generalizes
emotion recognition from categorical domain to real-valued 2D space and thereby
resolves the issues related to emotion description. Chapter 5 describes a ranking-base
emotion annotation and model training method that reduces the effort of emotion
annotation and enhances the quality of ground truth. Chapters 6–9 describe how to
take the subjective nature of emotion perception into account in the development of
an automatic music emotion recognition system. Chapters 10–12 present methods
that integrate information extracted from lyrics, chord sequence, and genre metadata
to improve the accuracy of emotion recognition. After describing an emotion-based
music retrieval system that is particularly useful for mobile devices in Chapter 13,
we describe research directions that can be extended from the techniques introduced
in this book in Chapter 14.
To the best of our knowledge, this is the first book dedicated to automatic music
emotion recognition. It is aimed at students and researchers in the fields of com-
puter science, engineering, psychology, and musicology and industrial practition-
ers in mobile multimedia, database management, digital home, computer–human