Repeating pattern discovery of audio

In this paper, we propose an effective method to discover repeating pattern from audio. Since the previous feature extraction methods are usually process monophony audio, for extracting more descriptive features from polyphony audio, Gabor filters bank is introduced. Meanwhile the measure criterion is given for qualitatively and quantitatively weighting the discernibility of extracted features. In addition, we present an incremental repeating pattern discovering algorithm with time complexity O(n log(n)). Experimental evaluations show that our proposed method could extract complete and meaningful repeating patterns from polyphony audio.