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

Ngoc Q. K. Duong (1) , Alexey Ozerov (1) , Louis Chevallier (1) , Joel Sirot (1)

1 Technicolor R & I [Cesson Sévigné]

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.

Mots clés: Interactive audio source separation; nonnegative matrix factorization; uncertainty-based learning; timefrequency annotation; user feedback

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Ngoc Q. K. 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⟩