Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as con...Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as convergence difficulty,model collapse,etc.In this work,an end-to-end speech enhancement model based on Wasserstein Generative Adversarial Networks is proposed,and some improvements have been made in order to get faster convergence speed and better generated speech quality.Specifically,in the generator coding part,each convolution layer adopts different convolution kernel sizes to conduct convolution operations for obtaining speech coding information from multiple scales;a gated linear unit is introduced to alleviate the vanishing gradient problem with the increase of network depth;the gradient penalty of the discriminator is replaced with spectral normalization to accelerate the convergence rate of themodel;a hybrid penalty termcomposed of L1 regularization and a scale-invariant signal-to-distortion ratio is introduced into the loss function of the generator to improve the quality of generated speech.The experimental results on both TIMIT corpus and Tibetan corpus show that the proposed model improves the speech quality significantly and accelerates the convergence speed of the model.展开更多
Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced...Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.展开更多
The wide applications of Generative adversarial networks benefit from the successful training methods,guaranteeing that an object function converges to the local minimum.Nevertheless,designing an efficient and competi...The wide applications of Generative adversarial networks benefit from the successful training methods,guaranteeing that an object function converges to the local minimum.Nevertheless,designing an efficient and competitive training method is still a challenging task due to the cyclic behaviors of some gradient-based ways and the expensive computational cost of acquiring the Hessian matrix.To address this problem,we proposed the Adaptive Composite Gradients(ACG)method,linearly convergent in bilinear games under suitable settings.Theory analysis and toy-function experiments both suggest that our approach alleviates the cyclic behaviors and converges faster than recently proposed SOTA algorithms.The convergence speed of the ACG is improved by 33%than other methods.Our ACG method is a novel Semi-Gradient-Free algorithm that can reduce the computational cost of gradient and Hessian by utilizing the predictive information in future iterations.The mixture of Gaussians experiments and real-world digital image generative experiments show that our ACG method outperforms several existing technologies,illustrating the superiority and efficacy of our method.展开更多
工业数据由于技术故障和人为因素通常导致数据异常,现有基于约束的方法因约束阈值设置的过于宽松或严格会导致修复错误,基于统计的方法因平滑修复机制导致对时间步长较远的异常值修复准确度较低.针对上述问题,提出了基于奖励机制的最小...工业数据由于技术故障和人为因素通常导致数据异常,现有基于约束的方法因约束阈值设置的过于宽松或严格会导致修复错误,基于统计的方法因平滑修复机制导致对时间步长较远的异常值修复准确度较低.针对上述问题,提出了基于奖励机制的最小迭代修复和改进WGAN混合模型的时序数据修复方法.首先,在预处理阶段,保留异常数据,进行信息标注等处理,从而充分挖掘异常值与真实值之间的特征约束.其次,在噪声模块提出了近邻参数裁剪规则,用于修正最小迭代修复公式生成的噪声向量.将其传递至模拟分布模块的生成器中,同时设计了一个动态时间注意力网络层,用于提取时序特征权重并与门控循环单元串联组合捕捉不同步长的特征依赖,并引入递归多步预测原理共同提升模型的表达能力;在判别器中设计了Abnormal and Truth奖励机制和Weighted Mean Square Error损失函数共同反向优化生成器修复数据的细节和质量.最后,在公开数据集和真实数据集上的实验结果表明,该方法的修复准确度与模型稳定性显著优于现有方法.展开更多
基金supported by the National Science Foundation under Grant No.62066039.
文摘Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as convergence difficulty,model collapse,etc.In this work,an end-to-end speech enhancement model based on Wasserstein Generative Adversarial Networks is proposed,and some improvements have been made in order to get faster convergence speed and better generated speech quality.Specifically,in the generator coding part,each convolution layer adopts different convolution kernel sizes to conduct convolution operations for obtaining speech coding information from multiple scales;a gated linear unit is introduced to alleviate the vanishing gradient problem with the increase of network depth;the gradient penalty of the discriminator is replaced with spectral normalization to accelerate the convergence rate of themodel;a hybrid penalty termcomposed of L1 regularization and a scale-invariant signal-to-distortion ratio is introduced into the loss function of the generator to improve the quality of generated speech.The experimental results on both TIMIT corpus and Tibetan corpus show that the proposed model improves the speech quality significantly and accelerates the convergence speed of the model.
基金supported by National Natural Science Foundation of China(Grant Nos.52279137,52009090).
文摘Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.
基金This work is supported by the National Key Research and Development Program of China(No.2018AAA0101001)Science and Technology Commission of Shanghai Municipality(No.20511100200)supported in part by the Science and Technology Commission of Shanghai Municipality(No.18dz2271000).
文摘The wide applications of Generative adversarial networks benefit from the successful training methods,guaranteeing that an object function converges to the local minimum.Nevertheless,designing an efficient and competitive training method is still a challenging task due to the cyclic behaviors of some gradient-based ways and the expensive computational cost of acquiring the Hessian matrix.To address this problem,we proposed the Adaptive Composite Gradients(ACG)method,linearly convergent in bilinear games under suitable settings.Theory analysis and toy-function experiments both suggest that our approach alleviates the cyclic behaviors and converges faster than recently proposed SOTA algorithms.The convergence speed of the ACG is improved by 33%than other methods.Our ACG method is a novel Semi-Gradient-Free algorithm that can reduce the computational cost of gradient and Hessian by utilizing the predictive information in future iterations.The mixture of Gaussians experiments and real-world digital image generative experiments show that our ACG method outperforms several existing technologies,illustrating the superiority and efficacy of our method.
文摘工业数据由于技术故障和人为因素通常导致数据异常,现有基于约束的方法因约束阈值设置的过于宽松或严格会导致修复错误,基于统计的方法因平滑修复机制导致对时间步长较远的异常值修复准确度较低.针对上述问题,提出了基于奖励机制的最小迭代修复和改进WGAN混合模型的时序数据修复方法.首先,在预处理阶段,保留异常数据,进行信息标注等处理,从而充分挖掘异常值与真实值之间的特征约束.其次,在噪声模块提出了近邻参数裁剪规则,用于修正最小迭代修复公式生成的噪声向量.将其传递至模拟分布模块的生成器中,同时设计了一个动态时间注意力网络层,用于提取时序特征权重并与门控循环单元串联组合捕捉不同步长的特征依赖,并引入递归多步预测原理共同提升模型的表达能力;在判别器中设计了Abnormal and Truth奖励机制和Weighted Mean Square Error损失函数共同反向优化生成器修复数据的细节和质量.最后,在公开数据集和真实数据集上的实验结果表明,该方法的修复准确度与模型稳定性显著优于现有方法.
