Detection of common mistakes in novice violin playing

Analyzing and modeling playing mistakes are essential parts of computer-aided education tools in learning musical instruments. In this paper, we present a system for identifying four types of mistakes commonly made by novice violin players. We construct a new dataset comprising of 981 legato notes played by 10 players across different skill levels, and have violin experts annotate all possible mistakes associated with each note by listening to the recordings. Five feature representations are generated from the same feature set with different scales, including two note-level representations and three segment-level representations of the onset, sustain and offset, and are tested for automatically identifying playing mistakes. Performance is evaluated under the framework of using the Fisher score for feature selection and the support vector machine for classification. Results show that the F-measures using different feature representations can vary up to 20% for two types of playing mistakes. It demonstrates the different sensitivities of each feature representation to different mistakes. Moreover, our results suggest that the standard audio features such as MFCCs are not good enough and more advanced feature design may be needed.