A Deep Ensemble Learning Method for Monaural Speech Separation

By Xiao-Lei Zhang, DeLiang Wang. 2016

203 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Speech Denoising with Deep Feature Losses (2018, background): “However, most pipelines still operate in the spectrogram domain [4, 5, 6, 7, 8, 9, 10, 11].”
TaSNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation (2017, background): “In recent years, deep learning approaches have signiﬁcantly advanced the state of this problem compared to traditional methods [1, 2, 3, 4, 5].”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “2The conclusion is also nuanced for speaker separation [206].”
Speaker-Independent Speech Separation With Deep Attractor Network (2017, methodology): “r speaker from the mixed audio signal of others. Several proposed systems have shown signiﬁcant performance improvement on the separation task when prior information of speakers in a mixture is given [1], [2]. This however is still challenging when no prior information about the speakers is availabl”
Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation (2019, methodology): “Many deep learning based speaker separation systems [7], [17], [44] address this problem in the T-F domain, where STFT is calculated using an analysis window w(n) with FFT length N and frame shift R:”
Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures (2017, methodology): “Training speaker dependent networks for speaker extraction was already successfully used in previous works [25, 26].”