Query：
学者姓名：鲍长春
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-Author
Language
Clean All
Abstract ：
针对最小方差无失真响应(Minimum Variance Distortionless Response,MVDR)波束形成器对导向矢量失配较敏感的问题,本文提出了一种有效的干扰声源抑制方法.该方法首先将语音信号的频带划分为多个子带,通过聚焦信号子空间方法估计各子带的声源到达方向(Direction of Arrival,DOA),并采用统计直方图估计各声源的初始DOA;其次,为了减小导向矢量失配,利用声源的空间稀疏性,通过Capon功率构建目标声源导向矢量估计的代价函数,约束目标声源导向矢量远离干扰声源空间;最后,根据估计的导向矢量,估计干扰声源加噪声协方差矩阵,以获得MVDR波束形成器的权重.基于TIMIT语料库的实验结果证明,提出的干扰声源抑制方法的输出信干噪比(SINR)及语音质量感知评价(PESQ)优于参考方法,具有更佳的抗导向矢量失配性能.
Keyword ：
最小方差无失真响应 最小方差无失真响应 语音增强 语音增强 聚焦信号子空间 聚焦信号子空间 麦克风阵列 麦克风阵列 波束形成 波束形成
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 周静 , 鲍长春 , 张旭 . 基于聚焦信号子空间估计导向矢量的干扰声源抑制方法 [J]. | 电子学报 , 2023 , 51 (1) : 76-85 . |
| MLA | 周静 等. "基于聚焦信号子空间估计导向矢量的干扰声源抑制方法" . | 电子学报 51 . 1 (2023) : 76-85 . |
| APA | 周静 , 鲍长春 , 张旭 . 基于聚焦信号子空间估计导向矢量的干扰声源抑制方法 . | 电子学报 , 2023 , 51 (1) , 76-85 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Most of the existing Beamforming methods are based on the assumptions that the sources are all point sources and the angular separation between the direction of arrival (DOA) of the source and the interference is large enough to assure good performance. In this paper, we consider a tough scenario where the target source and the interference are simultaneously spatially distributed and overlapped. To improve the performance of Beamforming in this scenario, we propose two approaches: the first approach exploits the non-Gaussianity as well as the spectrogram sparsity of the output of the microphone array; the second approach exploits the generalized sparsity with overlapped groups of the Beampattern. The proposed criteria are solved by methods based on linearized preconditioned alternating direction method of multipliers (LPADMM) with high accuracy and high computational efficiency. Numerical simulations and real data experiments show the advantages of the proposed approaches compared to previously proposed Beamforming methods for signal enhancement.
Keyword ：
Speech enhancement Speech enhancement microphone array microphone array DOA DOA Correlation Correlation speech enhancement speech enhancement Interference Interference Arrays Arrays Array signal processing Array signal processing Signal to noise ratio Signal to noise ratio MVDR MVDR Microphone arrays Microphone arrays
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiong Wenmeng , Bao Changchun , Jia Maoshen et al. Speech Enhancement With Robust Beamforming for Spatially Overlapped and Distributed Sources [J]. | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING , 2022 , 30 : 2778-2790 . |
| MLA | Xiong Wenmeng et al. "Speech Enhancement With Robust Beamforming for Spatially Overlapped and Distributed Sources" . | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 30 (2022) : 2778-2790 . |
| APA | Xiong Wenmeng , Bao Changchun , Jia Maoshen , Picheral, Jose . Speech Enhancement With Robust Beamforming for Spatially Overlapped and Distributed Sources . | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING , 2022 , 30 , 2778-2790 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
一种基于CTC多层损失的语音识别方法，属于模式识别、声学领域。该方法对语音识别网络不同层的输出进行规范，使不同层的输出尽量接近所需要的语音识别结果，从而提高语音识别的性能。该方法包括模型训练与模型测试两个阶段：在训练阶段，将预处理后的训练集输入所搭建的多层语音识别网络中，计算不同层的损失和不同层的权重，将不同层损失加权求和得到多层损失，循环计算损失，更新网络参数直至收敛；在测试阶段，将预处理后的测试集输入训练好的多层语音识别网络，输出识别结果。本发明仅仅改变CTC语音识别模型训练阶段的损失函数，并不改变CTC语音识别模型的结构及其语音识别的过程，以低复杂度、低开销的特点提高语音识别的准确率。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈仙红 , 罗德雨 , 鲍长春 . 一种基于CTC多层损失的语音识别方法 : CN202210619908.5[P]. | 2022-06-02 . |
| MLA | 陈仙红 et al. "一种基于CTC多层损失的语音识别方法" : CN202210619908.5. | 2022-06-02 . |
| APA | 陈仙红 , 罗德雨 , 鲍长春 . 一种基于CTC多层损失的语音识别方法 : CN202210619908.5. | 2022-06-02 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
In this letter, a novel weighted mean square error (WMSE) is proposed to improve the DNN-based mask approximation method for speech enhancement, in which the weighting is closely related to the power exponent about noisy spectrum amplitude (NSA) base. The power exponents 0 and 2 separately reflect ideal amplitude masking (IAM) without any clippings and the indirect mapping (IM) on short-time spectral amplitude (STSA), and it is highly related to the enhanced spectrum and the performance of the enhanced signal based on the tests. Also, the experimental results show that the outstanding weighting is the noisy spectrum base with the power exponent 1 for the phase-unaware masking and results in better harmonic structure restoration. The objective function with the WMSE on the NSA (WMSE-NSA) can averagely improve 0.1 on the test of perceptual evaluation of speech quality (PESQ) and 1.7% on the test of short-time objective intelligibility (STOI) compared with the MSE-based mask approximation methods. © 1994-2012 IEEE.
Keyword ：
Deep neural networks Deep neural networks Photomapping Photomapping Speech intelligibility Speech intelligibility Speech enhancement Speech enhancement Mean square error Mean square error Approximation theory Approximation theory
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cui, Zihao , Bao, Changchun . Power Exponent Based Weighting Criterion for DNN-Based Mask Approximation in Speech Enhancement [J]. | IEEE Signal Processing Letters , 2021 , 28 : 618-622 . |
| MLA | Cui, Zihao et al. "Power Exponent Based Weighting Criterion for DNN-Based Mask Approximation in Speech Enhancement" . | IEEE Signal Processing Letters 28 (2021) : 618-622 . |
| APA | Cui, Zihao , Bao, Changchun . Power Exponent Based Weighting Criterion for DNN-Based Mask Approximation in Speech Enhancement . | IEEE Signal Processing Letters , 2021 , 28 , 618-622 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
In this article, the direction of arrival (DOA) estimation of multiple speech sources in reverberant environments is investigated based on the recording of a soundfield microphone. First, the recordings are analyzed in the time-frequency (T-F) domain to detect both 'points' (single T-F points) and 'regions' (multiple, adjacent T-F points) corresponding to a single source with low reverberation (known as low-reverberant-single-source (LRSS) points). Then, a LRSS point detection algorithm is proposed based on a joint dominance measure and instantaneous single-source point (SSP) identification. Following this, initial DOA estimates obtained for the detected LRSS points are analyzed using a Gaussian Mixture Model (GMM) derived by the Expectation-Maximization (EM) algorithm to cluster components into sources or outliers using a rule-based method. Finally, the DOA of each actual source is obtained from the estimated source components. Experiments on both simulated data and data recorded in an actual acoustic chamber demonstrate that the proposed algorithm exhibits improved performance for the DOA estimation in reverberant environments when compared to several existing approaches. © 2014 IEEE.
Keyword ：
Gaussian distribution Gaussian distribution Reverberation Reverberation Frequency domain analysis Frequency domain analysis Frequency estimation Frequency estimation Clustering algorithms Clustering algorithms Maximum principle Maximum principle Direction of arrival Direction of arrival Image segmentation Image segmentation Audio recordings Audio recordings
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jia, Maoshen , Wu, Yuxuan , Bao, Changchun et al. Multi-Source DOA Estimation in Reverberant Environments by Jointing Detection and Modeling of Time-Frequency Points [J]. | ACM Transactions on Audio Speech and Language Processing , 2021 , 29 : 379-392 . |
| MLA | Jia, Maoshen et al. "Multi-Source DOA Estimation in Reverberant Environments by Jointing Detection and Modeling of Time-Frequency Points" . | ACM Transactions on Audio Speech and Language Processing 29 (2021) : 379-392 . |
| APA | Jia, Maoshen , Wu, Yuxuan , Bao, Changchun , Ritz, Christian . Multi-Source DOA Estimation in Reverberant Environments by Jointing Detection and Modeling of Time-Frequency Points . | ACM Transactions on Audio Speech and Language Processing , 2021 , 29 , 379-392 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Variations of speech content increase the difficulty of speaker verification. In this paper, to alleviate the negative effect of the variations, phoneme-unit-specific time-delay neural network (PUSTDNN) is proposed and applied to the state-of-the-art x-vector system. It models each phoneme unit with an individual time-delay neural network (TDNN). That is to say, each TDNN mainly deals with a phoneme unit. Compared with handling all phoneme units together, when handling a phoneme unit, a TDNN can extract more discriminative speaker information, thus improving the system performance. Two realizations of the PUSTDNN are proposed. The first one can retain speech temporal information. The second one further combines all the TDNNs in a PUSTDNN into a larger TDNN to reduce computational complexity. To avoid model overfitting, the phoneme units are obtained by clustering phonemes based on the phonetic knowledge and phonetic sparsity degree. The PUSTDNN is also compared with two other techniques, i.e., phonetic vector and multitask. Experiments on the Fisher, NIST SRE10, and VoxCeleb datasets show that the phonetic vector technique is most robust to the phoneme unit recognition accuracy. When the accuracy is high enough, the multitask performs better than the phonetic vector, and the PUSTDNN performs best and can achieve over 10% relative improvement compared with the x-vector baseline. © 2014 IEEE.
Keyword ：
Timing circuits Timing circuits Speech recognition Speech recognition Linguistics Linguistics Time delay Time delay Neural networks Neural networks Vectors Vectors
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Xianhong , Bao, Changchun . Phoneme-Unit-Specific Time-Delay Neural Network for Speaker Verification [J]. | ACM Transactions on Audio Speech and Language Processing , 2021 , 29 : 1243-1255 . |
| MLA | Chen, Xianhong et al. "Phoneme-Unit-Specific Time-Delay Neural Network for Speaker Verification" . | ACM Transactions on Audio Speech and Language Processing 29 (2021) : 1243-1255 . |
| APA | Chen, Xianhong , Bao, Changchun . Phoneme-Unit-Specific Time-Delay Neural Network for Speaker Verification . | ACM Transactions on Audio Speech and Language Processing , 2021 , 29 , 1243-1255 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
The auto-regressive (AR) model is an effective method to describe the correlation of time series.The classic AR coefficient estimation method utilizes a simple assumption about residual signal.It is a challenge to accurately estimate the auto-regressive coefficients in a complex environment such as noise or interference.Even though Deep Neural Networks (DNN)based AR (DNN-AR) coefficient estimation method can estimate the AR coefficients in a complex environment,the DNN-AR method is easily affected by the numerical stability of Levinson-Durbin recursion (LDR) approach during the training stage.The main target is to improve the stability and overall performance of the DNN-AR based method.In this paper,the precision transform method is utilized to improve computational efficiency while keeping system stability,and the generalized analysis-by-synthesis combing DNN (GABS-DNN) model is proposed for improving the accuracy of AR coefficient estimation and stability of the DNN training in the noisy environment.The GABS-DNN model consists of three main parts:spectrum enhancement network in the modifier,DNN preprocessing and LDR parameter estimation at the encoder,and the conversion from autoregressive coefficient to power spectrum at the decoder.In the process of optimizing the objective function,the error between the enhanced spectrum and the observed spectrum is added for reducing the influence of the gradient of the LDR on the enhanced network during back-propagation,which results in a stable estimation of the AR coefficients of noisy speech. © 2021, Chinese Institute of Electronics. All right reserved.
Keyword ：
Backpropagation Backpropagation Deep neural networks Deep neural networks Numerical methods Numerical methods System stability System stability Complex networks Complex networks Computational efficiency Computational efficiency
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cui, Zi-Hao , Bao, Chang-Chun . Auto-Regressive Coefficient Estimation Based on the GABS and DNN [J]. | Acta Electronica Sinica , 2021 , 49 (1) : 29-39 . |
| MLA | Cui, Zi-Hao et al. "Auto-Regressive Coefficient Estimation Based on the GABS and DNN" . | Acta Electronica Sinica 49 . 1 (2021) : 29-39 . |
| APA | Cui, Zi-Hao , Bao, Chang-Chun . Auto-Regressive Coefficient Estimation Based on the GABS and DNN . | Acta Electronica Sinica , 2021 , 49 (1) , 29-39 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
自回归(AR)模型是一类描述时序序列相关性的有效方法,经典的AR系数估计方法对残差信号做了简单的假设,在噪声干扰等复杂场景中难以准确估计AR系数,而基于深度神经网络(DNN)的AR(DNN-AR)系数估计方法在训练中容易受到莱文逊-杜宾迭代(LDR)解法的数值稳定性的影响.为改善DNN-AR系数训练的稳定性和整体性能,在保证系统稳定性的前提下,本文利用精度转化提高系统运算速度的思路,提出了基于广义合成分析(GABS)模型的深度网络结构改善方法,提高了AR系数在含噪环境下估计的准确性和网络训练的稳定性.组合DNN的GABS(GABS-DNN)的模型由三个主要部分组成:修正器的谱增强网络、编码器的...
Keyword ：
深度神经网络 深度神经网络 广义合成分析 广义合成分析 AR系数 AR系数 莱文逊-杜宾迭代解 莱文逊-杜宾迭代解
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 崔子豪 , 鲍长春 . 基于广义合成分析和深度神经网络的自回归系数估计方法 [J]. | 电子学报 , 2021 , 49 (01) : 29-39 . |
| MLA | 崔子豪 et al. "基于广义合成分析和深度神经网络的自回归系数估计方法" . | 电子学报 49 . 01 (2021) : 29-39 . |
| APA | 崔子豪 , 鲍长春 . 基于广义合成分析和深度神经网络的自回归系数估计方法 . | 电子学报 , 2021 , 49 (01) , 29-39 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
基于广义合成分析和深度神经网络的自回归系数估计方法
Keyword ：
广义合成分析 广义合成分析 莱文逊-杜宾迭代解 莱文逊-杜宾迭代解 深度神经网络 深度神经网络 AR系数 AR系数
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 崔子豪 , 鲍长春 , 电子学报 . 基于广义合成分析和深度神经网络的自回归系数估计方法 [J]. | 崔子豪 , 2021 , 49 (1) : 29-39 . |
| MLA | 崔子豪 et al. "基于广义合成分析和深度神经网络的自回归系数估计方法" . | 崔子豪 49 . 1 (2021) : 29-39 . |
| APA | 崔子豪 , 鲍长春 , 电子学报 . 基于广义合成分析和深度神经网络的自回归系数估计方法 . | 崔子豪 , 2021 , 49 (1) , 29-39 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
针对基于时频掩蔽的分离方法在多声源场景下的分离效果不佳的问题,论文提出一种利用概率混合模型的理想比率掩蔽多声源分离方法。首先,利用冯·米塞斯分布对时频点处方位角估计进行拟合以及拉普拉斯分布对归一化声压梯度信号向量进行拟合,由此建立概率混合模型。其次,利用期望最大化算法对模型参数进行求解,估计各声源对应的理想比率掩蔽。最后,利用估计出的理想比率掩蔽,从麦克风采集信号中分离得到各声源信号。实验结果表明,与现有基于时频掩蔽的多声源分离方法相比,论文所提方法在欠定场景下具有更好的分离效果。
Keyword ：
概率混合模型 概率混合模型 多声源分离 多声源分离 理想比率掩蔽 理想比率掩蔽
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 贾怡恬 , 杨淇善 , 贾懋珅 et al. 利用概率混合模型的理想比率掩蔽多声源分离方法 [J]. | 信号处理 , 2021 , 37 (10) : 1806-1815 . |
| MLA | 贾怡恬 et al. "利用概率混合模型的理想比率掩蔽多声源分离方法" . | 信号处理 37 . 10 (2021) : 1806-1815 . |
| APA | 贾怡恬 , 杨淇善 , 贾懋珅 , 许文杰 , 鲍长春 . 利用概率混合模型的理想比率掩蔽多声源分离方法 . | 信号处理 , 2021 , 37 (10) , 1806-1815 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
