Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial featur...Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial features among the consecutive speech frames become highly correlated such that it is helpful for speaker separation by providing additional spatial information.To fully exploit this information,we design a separation system on Recurrent Neural Network(RNN)with long short-term memory(LSTM)which effectively learns the temporal dynamics of spatial features.In detail,a LSTM-based speaker separation algorithm is proposed to extract the spatial features in each time-frequency(TF)unit and form the corresponding feature vector.Then,we treat speaker separation as a supervised learning problem,where a modified ideal ratio mask(IRM)is defined as the training function during LSTM learning.Simulations show that the proposed system achieves attractive separation performance in noisy and reverberant environments.Specifically,during the untrained acoustic test with limited priors,e.g.,unmatched signal to noise ratio(SNR)and reverberation,the proposed LSTM based algorithm can still outperforms the existing DNN based method in the measures of PESQ and STOI.It indicates our method is more robust in untrained conditions.展开更多
By establishing concept an transient solutions of general nonlinear systems converging to its equilibrium set, long-time behavior of solutions for cellular neural network systems is studied. A stability condition in g...By establishing concept an transient solutions of general nonlinear systems converging to its equilibrium set, long-time behavior of solutions for cellular neural network systems is studied. A stability condition in generalized sense is obtained. This result reported has an important guide to concrete neural network designs.展开更多
针对部分场景下标签较少、样本不均衡的时序数据,为了更好的捕捉序列之间的逐步依赖关系,本文一方面使用具有因果关系属性的时域卷积网络构建生成对抗网络,另一方面使用长短期记忆网络构建嵌入网络和复现网络,以实现模型同时处理短期依...针对部分场景下标签较少、样本不均衡的时序数据,为了更好的捕捉序列之间的逐步依赖关系,本文一方面使用具有因果关系属性的时域卷积网络构建生成对抗网络,另一方面使用长短期记忆网络构建嵌入网络和复现网络,以实现模型同时处理短期依存项和长期依存项,从而提出一种基于时域卷积网络和长短期记忆网络的时间序列生成对抗网络(A Time-series Generative Adversarial Network based on Temporal convolutional network and Long-short term memory network, TL-TimeGAN)。采用覆盖性、有用性和相似度检验的综合分析方法作为合成数据质量的评价指标,进一步全面地评价合成数据的覆盖性、预测程度和相似性。最终,基于以太坊欺诈检测数据集,使用Tabnet网络对扩增数据进行异常检测并获得局部特征重要性以及全局特征重要性,以增强扩增数据应用于实际工作的实践指导价值。展开更多
基金This work is supported by the National Nature Science Foundation of China(NSFC)under Grant Nos.61571106,61501169,41706103the Fundamental Research Funds for the Central Universities under Grant No.2242013K30010.
文摘Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial features among the consecutive speech frames become highly correlated such that it is helpful for speaker separation by providing additional spatial information.To fully exploit this information,we design a separation system on Recurrent Neural Network(RNN)with long short-term memory(LSTM)which effectively learns the temporal dynamics of spatial features.In detail,a LSTM-based speaker separation algorithm is proposed to extract the spatial features in each time-frequency(TF)unit and form the corresponding feature vector.Then,we treat speaker separation as a supervised learning problem,where a modified ideal ratio mask(IRM)is defined as the training function during LSTM learning.Simulations show that the proposed system achieves attractive separation performance in noisy and reverberant environments.Specifically,during the untrained acoustic test with limited priors,e.g.,unmatched signal to noise ratio(SNR)and reverberation,the proposed LSTM based algorithm can still outperforms the existing DNN based method in the measures of PESQ and STOI.It indicates our method is more robust in untrained conditions.
文摘By establishing concept an transient solutions of general nonlinear systems converging to its equilibrium set, long-time behavior of solutions for cellular neural network systems is studied. A stability condition in generalized sense is obtained. This result reported has an important guide to concrete neural network designs.
文摘针对部分场景下标签较少、样本不均衡的时序数据,为了更好的捕捉序列之间的逐步依赖关系,本文一方面使用具有因果关系属性的时域卷积网络构建生成对抗网络,另一方面使用长短期记忆网络构建嵌入网络和复现网络,以实现模型同时处理短期依存项和长期依存项,从而提出一种基于时域卷积网络和长短期记忆网络的时间序列生成对抗网络(A Time-series Generative Adversarial Network based on Temporal convolutional network and Long-short term memory network, TL-TimeGAN)。采用覆盖性、有用性和相似度检验的综合分析方法作为合成数据质量的评价指标,进一步全面地评价合成数据的覆盖性、预测程度和相似性。最终,基于以太坊欺诈检测数据集,使用Tabnet网络对扩增数据进行异常检测并获得局部特征重要性以及全局特征重要性,以增强扩增数据应用于实际工作的实践指导价值。
