Vocal characteristics classification of audio segments: An investigation of the influence of accompaniment music on low-level features

The characteristics of vocal segments in music are an important cue for automatic, content-based music recommendation, especially in the urban genre. In this paper, we investigate the classification of audio segments into singing and rap, using low-level acoustic features and a Bayesian classifier. GMMs are used as parametric clustering method to describe the distribution of the training data. Different low-level audio features features are assessed with regard to their ability to perform this task. Further, we study the influence of the accompaniment music on the performance of the classifier. We find that the performance of the classifier also depends on the background music of the training and testing data. Some features, even if they yielded useful results on isolated vocal tracks, are not able to preserve information about the vocal content when mixed with background music, thus leading to erroneous classifications.