Singing voice detection of popular music using beat tracking and SVM classification

Singing voice detection for musical structural analysis is an important but difficult area, which makes a great contribution to music segment. This paper proposes an efficient singing voice detection system by using beat tracking technique and SVM classification. We do the experiment using beat as a unit of classification instead of frame. Compared with a conventional frame-based classification, the run time of beat-based classification system reduces about 20%, and achieve 72.8% of precision. Meanwhile, in practice, the beat-based classification system achieves about 88.3% of precision.