DMCA
Non-negative matrix factorization for polyphonic music transcription (2003)
Cached
Download Links
| Venue: | IN PROC. IEEE WORKSHOP APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS |
| Citations: | 236 - 14 self |
BibTeX
@INPROCEEDINGS{Smaragdis03non-negativematrix,
author = {Paris Smaragdis and Judith C. Brown},
title = {Non-negative matrix factorization for polyphonic music transcription},
booktitle = {IN PROC. IEEE WORKSHOP APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS},
year = {2003},
pages = {177--180},
publisher = {}
}
Share
 |
 |
 |
 |
||
OpenURL
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.
Keyphrases
non-negative matrix factorization polyphonic music transcription spectral profile musical passage temporal information learns note approach result non-negative matrix decomposition method compact system piano note audio content linear basis transform polyphonic musical passage unique note structure
