Music Mood Classification using Reduced Audio Features
Babu Kaji Baniya, Choong Seon Hong · 2015
Music emotion is a crucial component in the field of multimedia database retrieval and computational musicology. Nowadays, the large online musical datasets are major challenges for searching, retrieving, and organizing the music content. Therefore, there is a need for robust automatic music emotion classifier system for organizing various music pieces into different classes according to the specific viable information. Two fundamental components are to be considered for music emotion classification: audio feature extraction and classifier design. In this paper, we propose diverse audio features to precisely characterize the music content. The feature sets belong to four groups: dynamic, rhythmic, spectral, and harmonic. From the features, five statistical parameters are considered as representatives, including the fourth-order central moments of each feature as well as covariance components. The large number of insignificant parameters is controlled by minimum redundancy maximum relevance (MRMR) algorithm and principal component analysis (PCA). Support Vector Machine (SVM) is used as a classifier to classify the music mood. 1.