Mitsubishi Electric Research Laboratories

Non-Negative Matrix Factorization for Polyphonic Music Transcription

Citation: Smaragdis, P.; Brown, J.C., "Non-negative Matrix Factorization for Polyphonic Music Transcription", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 177-180, October 2003 (IEEE Xplore)

Date:
October 2003

MERL Contact: Bent Schmidt-Nielsen

Abstract: In this paper we present a methodology for analyzing polyphonic musical passages comprised by notes that exhibit a harmonically fixed spectral profile (such as piano notes). Taking advantage of this unique note structure we can model the audio content of the musical passage by a linear basis transform and use non-negative matrix decomposition methods to estimate the spectral profile and the temporal information of every note. This approach results in a very simple and compact system that is not knowledge based, but rather learns notes by observation.


 Read the full technical report (PDF: 172.7 kB)