Remixing stereo music with score-informed source separation

John Woodruff*, Bryan A Pardo, Roger Dannenberg

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

66 Scopus citations

Abstract

Musicians and recording engineers are often interested in manipulating and processing individual instrumental parts within an existing recording to create a remix of the recording. When individual source tracks for a stereo mixture are unavailable, remixing is typically difficult or impossible, since one cannot isolate the individual parts. We describe a method of informed source separation that uses knowledge of the written score and spatial information from an anechoic, stereo mixture to isolate individual sound sources, allowing remixing of stereo mixtures without access to the original source tracks. This method is tested on a corpus of string quartet performances, artificially created using Bach four-part chorale harmonizations and sample violin, viola and cello recordings. System performance is compared in cases where the algorithm has knowledge of the score and those in which it operates blindly. The results show that source separation performance is markedly improved when the algorithm has access to a well-aligned score.

Original languageEnglish (US)
Title of host publicationISMIR 2006 - 7th International Conference on Music Information Retrieval
Pages314-319
Number of pages6
StatePublished - 2006
Event7th International Conference on Music Information Retrieval, ISMIR 2006 - Victoria, BC, Canada
Duration: Oct 8 2006Oct 12 2006

Publication series

NameISMIR 2006 - 7th International Conference on Music Information Retrieval

Other

Other7th International Conference on Music Information Retrieval, ISMIR 2006
Country/TerritoryCanada
CityVictoria, BC
Period10/8/0610/12/06

Keywords

  • Music
  • Score alignment
  • Source separation

ASJC Scopus subject areas

  • Music
  • Information Systems

Fingerprint

Dive into the research topics of 'Remixing stereo music with score-informed source separation'. Together they form a unique fingerprint.

Cite this