Skip to Main content Skip to Navigation
Conference papers

Temporal annotation-based audio source separation using weighted nonnegative matrix factorization

Abstract : We consider an emerging user-guided audio source separation approach based on the temporal annotation of the source activity along the mixture. In this baseline algorithm nonnegative matrix factorization (NMF) is usually used as spectral model for audio sources. In this paper we propose two weighting strategies incorporated in the NMF formulation so as to better exploit the annotation. We then derive the corresponding multiplicative update (MU) rules for the parameter estimation. The proposed approach was objectively evaluated within the fourth community-based Signal Separation Evaluation Campaign (SiSEC 2013) and shown to outperform the baseline algorithm, while obtaining comparable result to some other state-of-the-art methods.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01016316
Contributor : Alexey Ozerov <>
Submitted on : Monday, June 30, 2014 - 1:04:55 AM
Last modification on : Tuesday, July 1, 2014 - 11:14:51 AM
Long-term archiving on: : Tuesday, September 30, 2014 - 2:25:24 PM

File

Duong_et_al_ICCE-Berlin_2014.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01016316, version 1

Citation

Ngoc Duong, Alexey Ozerov, Louis Chevallier. Temporal annotation-based audio source separation using weighted nonnegative matrix factorization. 4th IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin 2014), Sep 2014, Berlin, Germany. ⟨hal-01016316⟩

Share

Metrics

Record views

121

Files downloads

546