Source Separation By Score Synthesis

Abstract

A musical score provides a great deal of information about a piece of music. In this paper we consider the incorporation of a music score to guide source separation on a single channel recording. We propose a method based on synthesizing lines of music in the score. Dynamic time warping (DTW) is used to to fit the synthesized data to the recording. These are then used as prior distributions in a statistical model of the recorded sound mixture. Probabilistic Latent Component Analysis (PLCA) is then used for the source separation. Preliminary results on a Bach work for string orchestra saw good separation with few artifacts.

3 Figures and Tables

Showing 1-8 of 8 references

BSS EVAL, a toolbox for performance measurement in (blind) source separation

  • C. Févotte, R. Gribonval, E. Vincent
  • 2009
2 Excerpts

Dynamic time warp (dtw) in matlab

  • D. Ellis
  • 2009
2 Excerpts

Mutopia

  • C. Sawer, D. Chan
  • 2009
2 Excerpts

Timidity++

  • M. Izumo, contributors
  • 2009
1 Excerpt

A spectral-filtering approach to music signal separation

  • M. R. Every, J. E. Szymanski
  • 2004
1 Excerpt
Showing 1-10 of 23 extracted citations