Improvised emotion and genre detection for songs through signal processing and genetic algorithm

摘要

Musical tunes are bundle of chords representing emotion which impart diverse of genres. Pasthistory highlighted copious amount of research work emotion and genre classification with stillincreasingly rapid advancement.Music has various emotional forms as happy, sad, anger and fear.Its various genre forms are Classical, Country, Disco, Hip-hop, Jazz, and Rock. These emotionsand genre can be segregated by identifying the frequency of chords notes (swarams in Tamilmusic). This paper deals with identifying emotions and genre for classical music both westernand south Indian classical music, viz, Carnatic music. The music was clipped and segmentedto determining frequency of notes using Shortest Fast Fourier Transformation (STFT). Musicfeatures such asmel frequency, pitch beat, zero crossing rate, and spectral centroid were derivedfrom the obtained frequency. Based on the audio features, emotion and genre were identifiedfor the given data set with genetic algorithm as a classification technique. The MIREX-Moodclassification dataset was considered for listing out emotions. The songs from Million songdata set and emotion classification repository were considered as ground truth for westernclassicalmusic and group of Illayaraja Tamil film songs was considered to identify Carnatic musicemotions. The classification was done using genetic algorithm. Mel frequency, pitch, and zerocrossing rate were considered as individual representations to get best fit ratio and it is foundto give accuracy percentage of 99.03%.