Skip to Main content Skip to Navigation
Conference papers

An interactive audio source separation framework based on non-negative matrix factorization

Abstract : Though audio source separation offers a wide range of applications in audio enhancement and post-production, its performance has yet to reach the satisfactory especially for single-channel mixtures with limited training data. In this paper we present a novel interactive source separation framework that allows end-users to provide feedback at each separation step so as to gradually improve the result. For this purpose, a prototype graphical user interface (GUI) is developed to help users annotating time-frequency regions where a source can be labeled as either active, inactive, or well-separated within the displayed spectrogram. This user feedback information, which is partially new with respect to the state-of-the-art annotations, is then taken into account in a proposed uncertainty-based learning algorithm to constraint the source estimates in next separation step. The considered framework is based on non-negative matrix factorization and is shown to be effective even without using any isolated training data.
Complete list of metadata

https://hal.inria.fr/hal-00960717
Contributor : Alexey Ozerov <>
Submitted on : Tuesday, March 18, 2014 - 3:57:24 PM
Last modification on : Tuesday, March 18, 2014 - 4:01:48 PM
Long-term archiving on: : Wednesday, June 18, 2014 - 1:25:58 PM

File

icassp2014_revised.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00960717, version 1

Citation

Ngoc Duong, Alexey Ozerov, Louis Chevallier, Joel Sirot. An interactive audio source separation framework based on non-negative matrix factorization. IEEE International Conference on Acoustics Speech and Signal Processing, May 2014, Florence, Italy. ⟨hal-00960717⟩

Share

Metrics

Record views

901

Files downloads

459