Music genre classification using novel features and a weighted voting method

This paper proposes a novel music genre classification system based on two novel features and a weighted voting method. The proposed features, modulation spectral flatness measure (MSFM) and modulation spectral crest measure (MSCM) represent the time-varying behavior of music signals and indicate the strength of beat. The proposed weighted voting method determines a music genre by summarizing the classification results of consecutive time windows. Experimental results show that the proposed features and the weighted voting method improve the music genre classification system.

• Type: Conference
• Year: 2008
• Where: ICMCS
• Authors: Dalwon Jang, Minho Jin, Chang D. Yoo
• Keywords: ICMCS 2008, Multimedia, Music Genre, Music Genre Classification, Weighted Voting Method