Normalized cuts for predominant melodic source separation

Mathieu Lagrange*, Luis Gustavo Martins, Jennifer Murdoch, George Tzanetakis

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

31 Citations (Scopus)

Abstract

The predominant melodic source, frequently the singing voice, is an important component of musical signals. In this paper, we describe a method for extracting the predominant source and corresponding melody from ldquoreal-worldrdquo polyphonic music. The proposed method is inspired by ideas from computational auditory scene analysis. We formulate predominant melodic source tracking and formation as a graph partitioning problem and solve it using the normalized cut which is a global criterion for segmenting graphs that has been used in computer vision. Sinusoidal modeling is used as the underlying representation. A novel harmonicity cue which we term harmonically wrapped peak similarity is introduced. Experimental results supporting the use of this cue are presented. In addition, we show results for automatic melody extraction using the proposed approach.
Original languageEnglish
Article number4432646
Pages (from-to)278-290
Number of pages13
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume16
Issue number2
DOIs
Publication statusPublished - Feb 2008
Externally publishedYes

Keywords

  • Computational auditory scene analysis (CASA)
  • Music information retrieval (MIR)
  • Normalized cut
  • Sinusoidal modeling
  • Spectral clustering

Fingerprint

Dive into the research topics of 'Normalized cuts for predominant melodic source separation'. Together they form a unique fingerprint.

Cite this