Skip to Main Content
Music loops are seamlessly repeating segments of audio. The automatic extraction of music loops from digital audio is useful for searching reusable materials for new compositions. In this paper, an effective approach of music loop discovery and extraction is proposed. In our approach, we use a pitch class distribution feature to represent the tonal characteristics of the signal. Based on tonal self-similarity, we propose a pattern recognition technique to discover loop segments. For extracting single loop instances from the audio signal, we propose a timbre-based similarity criterion on beat level to allocate optimal cutting points. Our method was evaluated in a listening test with 200 extracted loop segments. The qualitative evaluation shows that for 85% of the test data, our method succeeded in extracting music loops of agreeable quality directly from audio signals.