Grid Diagram Features for Automatic Pipa Fingering Technique Classification

Automatic classification on 7 typical playing techniques of Pipa is taken out in this paper. First, the Pipa spectrogram is normalized according to its fundamental frequency; then, 3 types of grid diagrams are generated from the normalized spectrogram; finally, different computation zones are assigned to the grid diagrams for feature extraction with their statistical values. In the automatic classification based on machine learning, with recognition accuracies up to 95.8% with very few number of features.