Ensemble learning for speech enhancement

Over the years, countless algorithms have been proposed to solve the problem of speech enhancement from a noisy mixture. Many have succeeded in improving at least parts of the signal, while often deteriorating others. Based on the assumption that different algo-rithms are likely to enjoy different qualities and suffer from differ-ent flaws, we investigate the possibility of combining the strengths of multiple speech enhancement algorithms, formulating the prob-lem in an ensemble learning framework. As a first example of such a system, we consider the prediction of a time-frequency mask ob-tained from the clean speech, based on the outputs of various al-gorithms applied on the noisy mixture. We consider several ap-proaches involving various notions of context and various machine learning algorithms for classification, in the case of binary masks, and regression, in the case of continuous masks. We show that com-bining several algorithms in this way can lead to an improvement in enhancement performance, while simple averaging or voting tech-niques fail to do so. Index Terms — Ensemble learning, Speech enhancement, Time-frequency mask, Classification, Stackin