NMF based dictionary learning for automatic transcription of polyphonic piano music

Music transcription consists in transforming the musical content of audio data into a symbolic representation. The objective of this study is to investigate a transcription system for polyphonic piano. The proposed method focuses on temporal musical structures, note events and their main characteristics: the attack instant and the pitch. Onset detection exploits a time-frequency representation of the audio signal. Feature extraction is based on Sparse Nonnegative Matrix Factorization (SNMF) and Constant Q Transform (CQT), while note classification is based on Support Vector Machines (SVMs). Finally, to validate our method, we present a collection of experiments using a wide number of musical pieces of heterogeneous styles