Skip to Main Content
Song and music discrimination play a significant role in multimedia applications such as genre classification and singer identification. The problem of identifying sections of singer voice and instruments is addressed in this paper. A set of classification techniques based on features extracted from the auditory models, which are commonly used in the speech and speaker recognition domains, are investigated in this paper. All the proposed approaches, assuming no knowledge of song and music segments, use only a threshold based distance measure for discrimination. Particularly, it is observed that certain approaches are more appropriate for tracking the singer, while others are more appropriate for detecting the transition from music to the singer and vice versa. The experimental data are extracted from the music genre database RWC including various styles.