Skip to Main content Skip to Navigation
Journal articles

Normalized cuts for predominant melodic source separation

Abstract : The singing voice and melody are important characteristics of music signals. In this paper we describe a method for extracting the singing voice and corresponding melody from "real-world" polyphonic music. The proposed method is inspired by ideas from Computational Auditory Scene Analysis. We formulate singing voice 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 (HWPS) 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.
Complete list of metadatas

Cited literature [44 references]  Display  Hide  Download
Contributor : Mathieu Lagrange <>
Submitted on : Monday, January 21, 2019 - 10:19:59 AM
Last modification on : Wednesday, June 24, 2020 - 4:19:33 PM


Files produced by the author(s)


  • HAL Id : hal-01697331, version 1


Mathieu Lagrange, Luis Gustavo Martins, Jennifer Murdoch, George Tzanetakis. Normalized cuts for predominant melodic source separation. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2008, 16 (2). ⟨hal-01697331⟩



Record views


Files downloads