Generalization of an Active Set Newton Algorithm with Alpha-Beta divergences for audio separation

• Published in: 2021 29th European Signal Processing Conference (EUSIPCO) pp. 306 - 310
• Main Authors: Sarmiento Vega, Auxiliadora, Duran Diaz, Ivan, Fondon, Irene, Cruces, Sergio
• Format: Conference Proceeding
• Language: English
• Published: EURASIP 23-08-2021
• Subjects: Active Set-Newton algorithm; Alpha-Beta divergence; compositional model; dictionary learning; Europe; Multiple signal classification; Signal processing algorithms; signal separation; Source separation; Time-frequency analysis
• ISSN: 2076-1465
• DOI: 10.23919/EUSIPCO54536.2021.9616330

This article considers the decomposition of a nonnegative signal into a non-negative linear combination of the contributions of pre-specified atomic units, which are also nonnegative. This model, referred as compositional model, is evident in the time-frequency characterisations of audio signals, where the sound can be viewed as a blending of spectral patterns of the component sounds that are present simultaneously. The algorithm proposed in this article obtains the activation vector of the atoms through an Active-Set Newton algorithm that employ the Alpha-Beta-divergence between the observed signal and the decomposition. This divergence family has been proved to be more efficient than other more common divergences, such as the generic Kullback-Leibler divergence in various audio signal processing applications. We have evaluated the proposed algorithm in a signal separation application of polyphonic music.