Polyphonic music transcription through dynamic networks and spectral pattern identification∗

The automatic extraction of the notes that were played in a digital musical signal (automatic music transcription) is an open problem. A number of techniques have been applied to solve it without concluding results. This work tries to pose it through the identification of the spectral pattern of a given instrument in the signal spectrogram using time-delay neural networks. We will work in the monotimbrical polyphonic version of the problem: more than one note can sound at the same time but always played by just one instrument. Our purpose is to discover wether a neural network fed only with an spectrogram can detect the notes of a polyphonic music score. In this paper our preliminary but promising results using synthetic instruments are presented.