arXiv subjects

Chengshi Zheng

Publications and source records attributed to Chengshi Zheng.

50 records · Page 3Linked to original sources

arXiv2021

A Simultaneous Denoising and Dereverberation Framework with Target Decoupling

Background noise and room reverberation are regarded as two major factors to degrade the subjective speech quality. In this paper, we propose an integrated framework to address simultaneous denoising and dereverberation under complicated scenario environments. It adopts a chain optimization strategy and designs four sub-stages accordingly. In the first two stages, we decouple the multi-task learning w.r.t. complex spectrum into magnitude and phase, and only implement noise and reverberation removal in the magnitude domain. Based on the estimated priors above, we further polish the spectrum in the third stage, where both magnitude and phase information are explicitly repaired with the residual learning. Due to the data mismatch and nonlinear effect of DNNs, the residual noise often exists in the DNN-processed spectrum. To resolve the problem, we adopt a light-weight algorithm as the post-processing module to capture and suppress the residual noise in the non-active regions. In the Interspeech 2021 Deep Noise Suppression (DNS) Challenge, our submitted system ranked top-1 for the real-time track in terms of Mean Opinion Score (MOS) with ITU-T P.835 framework

cs.SD↗

arXiv2021

Learning to Inference with Early Exit in the Progressive Speech Enhancement

In real scenarios, it is often necessary and significant to control the inference speed of speech enhancement systems under different conditions. To this end, we propose a stage-wise adaptive inference approach with early exit mechanism for progressive speech enhancement. Specifically, in each stage, once the spectral distance between adjacent stages lowers the empirically preset threshold, the inference will terminate and output the estimation, which can effectively accelerate the inference speed. To further improve the performance of existing speech enhancement systems, PL-CRN++ is proposed, which is an improved version over our preliminary work PL-CRN and combines stage recurrent mechanism and complex spectral mapping. Extensive experiments are conducted on the TIMIT corpus, the results demonstrate the superiority of our system over state-of-the-art baselines in terms of PESQ, ESTOI and DNSMOS. Moreover, by adjusting the threshold, we can easily control the inference efficiency while sustaining the system performance.

cs.SD↗

arXiv2021

Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement

The capability of the human to pay attention to both coarse and fine-grained regions has been applied to computer vision tasks. Motivated by that, we propose a collaborative learning framework in the complex domain for monaural noise suppression. The proposed system consists of two principal modules, namely spectral feature extraction module (FEM) and stacked glance-gaze modules (GGMs). In FEM, the UNet-block is introduced after each convolution layer, enabling the feature recalibration from multiple scales. In each GGM, we decompose the multi-target optimization in the complex spectrum into two sub-tasks. Specifically, the glance path aims to suppress the noise in the magnitude domain to obtain a coarse estimation, and meanwhile, the gaze path attempts to compensate for the lost spectral detail in the complex domain. The two paths work collaboratively and facilitate spectral estimation from complementary perspectives. Besides, by repeatedly unfolding the GGMs, the intermediate result can be iteratively refined across stages and lead to the ultimate estimation of the spectrum. The experiments are conducted on the WSJ0-SI84, DNS-Challenge dataset, and Voicebank+Demand dataset. Results show that the proposed approach achieves state-of-the-art performance over previous advanced systems on the WSJ0-SI84 and DNS-Challenge dataset, and meanwhile, competitive performance is achieved on the Voicebank+Demand corpus.

cs.SD↗

arXiv2021

ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network

It remains a tough challenge to recover the speech signals contaminated by various noises under real acoustic environments. To this end, we propose a novel system for denoising in the complicated applications, which is mainly comprised of two pipelines, namely a two-stage network and a post-processing module. The first pipeline is proposed to decouple the optimization problem w:r:t: magnitude and phase, i.e., only the magnitude is estimated in the first stage and both of them are further refined in the second stage. The second pipeline aims to further suppress the remaining unnatural distorted noise, which is demonstrated to sufficiently improve the subjective quality. In the ICASSP 2021 Deep Noise Suppression (DNS) Challenge, our submitted system ranked top-1 for the real-time track 1 in terms of Mean Opinion Score (MOS) with ITU-T P.808 framework.

cs.SD↗

arXiv2021

A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution

For multichannel speech enhancement, this letter derives a robust maximum likelihood distortionless response beamformer by modeling speech sparse priors with a complex generalized Gaussian distribution, where we refer to as the CGGD-MLDR beamformer. The proposed beamformer can be regarded as a generalization of the minimum power distortionless response beamformer and its improved variations. For narrowband applications, we also reveal that the proposed beamformer reduces to the minimum dispersion distortionless response beamformer, which has been derived with the ${{\ell}_{p}}$-norm minimization. The mechanisms of the proposed beamformer in improving the robustness are clearly pointed out and experimental results show its better performance in PESQ improvement.

eess.AS↗

arXiv2020

A Time-domain Monaural Speech Enhancement with Feedback Learning

In this paper, we propose a type of neural network with feedback learning in the time domain called FTNet for monaural speech enhancement, where the proposed network consists of three principal components. The first part is called stage recurrent neural network, which is introduced to effectively aggregate the deep feature dependencies across different stages with a memory mechanism and also remove the interference stage by stage. The second part is the convolutional auto-encoder. The third part consists of a series of concatenated gated linear units, which are capable of facilitating the information flow and gradually increasing the receptive fields. Feedback learning is adopted to improve the parameter efficiency and therefore, the number of trainable parameters is effectively reduced without sacrificing its performance. Numerous experiments are conducted on TIMIT corpus and experimental results demonstrate that the proposed network can achieve consistently better performance in terms of both PESQ and STOI scores than two state-of-the-art time domain-based baselines in different conditions.

cs.SD↗

arXiv2020

Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain

In low signal-to-noise ratio conditions, it is difficult to effectively recover the magnitude and phase information simultaneously. To address this problem, this paper proposes a two-stage algorithm to decouple the joint optimization problem w.r.t. magnitude and phase into two sub-tasks. In the first stage, only magnitude is optimized, which incorporates noisy phase to obtain a coarse complex clean speech spectrum estimation. In the second stage, both the magnitude and phase components are refined. The experiments are conducted on the WSJ0-SI84 corpus, and the results show that the proposed approach significantly outperforms previous baselines in terms of PESQ, ESTOI, and SDR.

cs.SD↗

arXiv2020

Distributed Node-Specific Block-Diagonal LCMV Beamforming in Wireless Acoustic Sensor Networks

This paper derives the analytical solution of a novel distributed node-specific block-diagonal linearly constrained minimum variance beamformer from the centralized linearly constrained minimum variance (LCMV) beamformer when considering that the noise covariance matrix is block-diagonal. To further reduce the computational complexity of the proposed beamformer, the ShermanMorrison-Woodbury formula is introduced to compute the inversion of noise sample covariance matrix. By doing so, the exchanged signals can be computed with lower dimensions between nodes, where the optimal LCMV beamformer is still available at each node as if each node is to transmit its all raw sensor signal observations. The proposed beamformer is fully distributable without imposing restrictions on the underlying network topology or scaling computational complexity, i.e., there is no increase in the per-node complexity when new nodes are added to the networks. Compared with state-of-the-art distributed node-specific algorithms that are often time-recursive, the proposed beamformer exactly solves the LCMV beamformer optimally frame by frame, which has much lower computational complexity and is more robust to acoustic transfer function estimation error and voice activity detector error. Numerous experimental results are presented to validate the effectiveness of the proposed beamformer.

eess.AS↗

arXiv2020

Dynamic Attention Based Generative Adversarial Network with Phase Post-Processing for Speech Enhancement

The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a powerful Dynamic Attention Recursive GAN called DARGAN for noise reduction in the time-frequency domain. Different from previous works, we have several innovations. First, recursive learning, an iterative training protocol, is used in the generator, which consists of multiple steps. By reusing the network in each step, the noise components are progressively reduced in a step-wise manner. Second, the dynamic attention mechanism is deployed, which helps to re-adjust the feature distribution in the noise reduction module. Third, we exploit the deep Griffin-Lim algorithm as the module for phase postprocessing, which facilitates further improvement in speech quality. Experimental results on Voice Bank corpus show that the proposed GAN achieves state-of-the-art performance than previous GAN- and non-GAN-based models

cs.SD↗

arXiv2020

The IOA System for Deep Noise Suppression Challenge using a Framework Combining Dynamic Attention and Recursive Learning

This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a type of training protocol which aggravates the information through multiple stages with a memory mechanism. The attention generator network is designed to dynamically control the feature distribution of the noise reduction network. To improve the phase recovery accuracy, we take the complex spectral mapping procedure by decoding both real and imaginary spectra. For the final blind test set, the average MOS improvements of the submitted system in noreverb, reverb, and realrec categories are 0.49, 0.24, and 0.36, respectively.

cs.SD↗

arXiv2020

A Recursive Network with Dynamic Attention for Monaural Speech Enhancement

A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursive learning together for monaural speech enhancement. Apart from a major noise reduction network, we design a separated sub-network, which adaptively generates the attention distribution to control the information flow throughout the major network. To effectively decrease the number of trainable parameters, recursive learning is introduced, which means that the network is reused for multiple stages, where the intermediate output in each stage is correlated with a memory mechanism. As a result, a more flexible and better estimation can be obtained. We conduct experiments on TIMIT corpus. Experimental results show that the proposed architecture obtains consistently better performance than recent state-of-the-art models in terms of both PESQ and STOI scores.

cs.SD↗

arXiv2020

Convolutional Recurrent Neural Network Based Progressive Learning for Monaural Speech Enhancement

Recently, progressive learning has shown its capacity to improve speech quality and speech intelligibility when it is combined with deep neural network (DNN) and long short-term memory (LSTM) based monaural speech enhancement algorithms, especially in low signal-to-noise ratio (SNR) conditions. Nevertheless, due to a large number of parameters and high computational complexity, it is hard to implement in current resource-limited micro-controllers and thus, it is essential to significantly reduce both the number of parameters and the computational load for practical applications. For this purpose, we propose a novel progressive learning framework with causal convolutional recurrent neural networks called PL-CRNN, which takes advantage of both convolutional neural networks and recurrent neural networks to drastically reduce the number of parameters and simultaneously improve speech quality and speech intelligibility. Numerous experiments verify the effectiveness of the proposed PL-CRNN model and indicate that it yields consistent better performance than the PL-DNN and PL-LSTM algorithms and also it gets results close even better than the CRNN in terms of objective measurements. Compared with PL-DNN, PL-LSTM, and CRNN, the proposed PL-CRNN algorithm can reduce the number of parameters up to 93%, 97%, and 92%, respectively.

cs.SD↗

arXiv2019

A Supervised Speech enhancement Approach with Residual Noise Control for Voice Communication

For voice communication, it is important to extract the speech from its noisy version without introducing unnaturally artificial noise. By studying the subband mean-squared error (MSE) of the speech for unsupervised speech enhancement approaches and revealing its relationship with the existing loss function for supervised approaches, this paper derives a generalized loss function, when taking the residual noise control into account, for supervised approaches. Our generalized loss function contains the well-known MSE loss function and many other often-used loss functions as special cases. Compared with traditional loss functions, our generalized loss function is more flexible to make a good trade-off between speech distortion and noise reduction. This is because a group of well-studied noise shaping schemes can be introduced to control residual noise for practical applications. Objective and subjective test results verify the importance of residual noise control for the supervised speech enhancement approach.

cs.SD↗

arXiv2015

Binaural coherent-to-diffuse-ratio estimation for dereverberation using an ITD model

Most previously proposed dual-channel coherent-to-diffuse-ratio (CDR) estimators are based on a free-field model. When used for binaural signals, e.g., for dereverberation in binaural hearing aids, their performance may degrade due to the influence of the head, even when the direction-of-arrival of the desired speaker is exactly known. In this paper, the head shadowing effect is taken into account for CDR estimation by using a simplified model for the frequency-dependent interaural time difference and a model for the binaural coherence of the diffuse noise field. Evaluation of CDR-based dereverberation with measured binaural impulse responses indicates that the proposed binaural CDR estimators can improve PESQ scores.

cs.SD↗