Procedia Computer Science · 2015 · 13 citations · 26 references
ComputingComputer ScienceData ScienceData MiningFeature EngineeringMachine LearningClassificationFeature ExtractionFeature SelectionGenre ClassificationKernel MethodsSupport Vector MachinesAudio Music AnalysisMachine Learning For MusicMusic ClassificationMusic Feature ExtractionMusic Genre Classification SystemsMusic Representation LearningSpectral FeaturesSupport Vector Machine Classification
Since music conveys as well as evokes a wealth of emotions in a listener, there has been tremendous research and commercial development to automatically organize music using smart machine learning techniques. In this work, various features are extracted from the music signal for an effective representation to aid in genre classification. The feature set comprises of dynamic, rhythm, tonal, and spectral features comprising a total of 144 features. The size of feature set is further reduced to 39 features using correlation-based feature selection mechanism to remove the correlated features. Support vector machine classifier is used to train the genre classification system with a flexible Pearson Universal Kernel (PUK) that can adapt its behavior to various functions (from linear to Gaussian). The reduced feature set, consisting mostly rhythm and spectral features, significantly outperforms the complete feature set leading to an accuracy of 82% for classifying 5 genres.
26
Mark Hall, Eibe Frank, Geoffrey Holmes et al. · ACM SIGKDD Explorations Newsletter · 2009 · 17.8K citations
A comparative study on content-based music genre classification
Tao Li, Mitsunori Ogihara, Qi Li · 2003 · 409 citations
Arts, Musicology, Genre Studies +12
Representing Musical Genre: A State of the Art
Jean‐Julien Aucouturier, F. Pachet · Journal of New Music Research · 2003 · 373 citations · Full text
Arts, Musicology, Genre Studies +11