A Deep Ensemble Learning Method for Monaural Speech Separation

Abstract

Monaural speech separation is a fundamental problem in robust speech processing. Recently, deep neural network (DNN)-based speech separation methods, which predict either clean speech or an ideal time-frequency mask, have demonstrated remarkable performance improvement. However, a single DNN with a given window length does not leverage contextual information sufficiently, and the differences between the two optimization objectives are not well understood. In this paper, we propose a deep ensemble method, named multicontext networks, to address monaural speech separation. The first multicontext network averages the outputs of multiple DNNs whose inputs employ different window lengths. The second multicontext network is a stack of multiple DNNs. Each DNN in a module of the stack takes the concatenation of original acoustic features and expansion of the soft output of the lower module as its input, and predicts the ratio mask of the target speaker; the DNNs in the same module employ different contexts. We have conducted extensive experiments with three speech corpora. The results demonstrate the effectiveness of the proposed method. We have also compared the two optimization objectives systematically and found that predicting the ideal time-frequency mask is more efficient in utilizing clean training speech, while predicting clean speech is less sensitive to SNR variations.

Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation

“…Recently deep learning has been employed to address speaker separation. The general idea is to train a deep neural network (DNN) to predict T-F masks or spectra of two speakers in a mixture [7] [16] [42]. There are usually two output layers in such a DNN, one for an individual speaker.…”

Probabilistic Permutation Invariant Training for Speech Separation

“…Lately, there has been increasing interest in nonlinear models, specifically, Deep Neural Networks (DNNs) [21,22,23,24]. In Deep Clustering (DPCL) [25,26], first, the timefrequency bins of the mixtures are mapped into an embedding space; then, a clustering algorithm is performed in the embedding space; finally, a binary mask is generated based on each cluster to reconstruct speech of each speaker.…”

A spatio‐temporal ensemble method for large‐scale traffic state prediction

“…To enhance the accuracy of weather prediction, Williams, Neilley, Koval, and McDonald () incorporated spatial‐temporal neighborhood bias information and used it to formulate a constraint‐regularized regression problem. Zhang and Wang () presented a multi‐context network, with one network averaging the output of multiple DNNs and the other stacking them together. Guzman, El‐Haliby, and Bruegge () compared the performance of four machine learning methods and their ensembles in classifying app reviews.…”