Polyphonic piano note transcription with recurrent neural networks

Sebastian Bock, Markus Schedl
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper a new approach for polyphonic piano note onset transcription is presented. It is based on a recurrent neural network to simultaneously detect the onsets and the pitches of the notes from spectral features. Long Short-Term Memory units are used in a bidirectional neural network to model the context of the notes. The use of a single regression output layer instead of the often used one-versus-all classification approach enables the system to significantly lower the number of
more » ... s note detections. Evaluation is based on common test sets and shows exceptional temporal precision combined with a significant boost in note transcription performance compared to current state-of-the-art approaches. The system is trained jointly with various synthesized piano instruments and real piano recordings and thus generalizes much better than existing systems. Index Termsmusic information retrieval, neural networks
doi:10.1109/icassp.2012.6287832 dblp:conf/icassp/BockS12 fatcat:3suzzh7uojbt7abftittlcasdy