ID 原文 译文
25175 借助交替方向乘子法(Alternating Direction Method of Multipliers，ADMM)，将多变量正则化最小二乘拟合问题，分解为多个可并行执行的标量优化问题，并引入可调步长因子加速算法，得到一个高度并行的最大分划广义ADMM 算法，并应用于正则化超限学习机。 By virtue of the alternating direction method of multipliers (ADMM ), the multivariate regularized least-squares model fitting problem is decomposed into multiple univariate subproblems that are solvable in parallel. By introducing a tunable step size to accelerate the algorithm, a highly parallel maximally split generalized ADMM (MS-GADMM) is developed for the regularized extreme learning machine (RELM)．
25176 建立了算法的收敛条件，分析了算法的计算复杂度，通过基准现实数据集实验与新近文献方法———最大分划松弛 ADMM 进行了收敛率比较。 The convergence condition of the MS-GADMM is established and the computational complexity of the MS-GADMM-based RELM is analyzed. Through experiments on real-world benchmark datasets, the MS-GADMM is compared with a maximally split relaxed ADMM recently presented in the literature．
25177 在 GPU 并行加速实验中，基于最大分划广义ADMM 的正则化超限学习机获得的大 GPU 加速比，表明了该算法的高度并行性。 In the GPU implementation experiments, the MS-GADMM has obtained very large GPU acceleration ratios, which demonstrates the high parallelism of the proposed MS-GADMM-based RELM．
25178 基于语音的手机来源识别是近年来多媒体取证领域中的一个研究热点，但已有研究大都局限于纯净语音或人工背景噪声语音。 Identifying cell-phones using recorded speech has become a hot topic in the field of multimedia forensics inrecent years. However, most of the existing studies focus on the clean speech or the speech with unnaturally artificial noise．
25179 本文以自然环境背景噪声下的手机语音为研究对象，提出一种基于低维深度特征的手机来源识别方法。 In this paper, the speech with background noise is taken into account and a source cell-phone identification method is presented on the basis of the low-dimensional deep features．
25180 首先提取对数域的 Mel 滤波器组系数作为基本的声学特征，然后输入到时间卷积网络中进行训练，进一步提取能够表征语音设备的深度特征，并利用线性判别分析进行降维，去除高维深度特征中的冗余。 First, the logarithmic Mel-filter bank coefficients are extracted as the main acoustic features and input to the temporal convolutional network for training and further extracting the deep features of speech devices. Then, the linear discriminant analysis is used to reduce the size of the high-dimensional deep features and remove the redundancy.
25181 最后，将得到的低维深度特征输入到支持向量机中进行分类和识别。 Finally, the low-dimensional deep features are used as input to the support vector machine classifier．
25182 在 47 种不同型号手机录制的 37600 条自然环境背景噪声语音样本库上的测试结果表明，本文所提方法在自然环境背景噪声下具有更优的识别性能，且对不同品牌、相同品牌不同型号、不同样本长度、不同数据集规模和不同采样率都具有很好的适应性。 The experimental results on 47 models of mobile phones and 37600 speech samples with background noise show that the proposed method has better recognition performance and better adaptability to different brands, different models of the same brand, different sampling lengths, different sizes of the dataset, and different sampling rates．
25183 新一代增强平面栅软穿通型(Soft Punch Through + ，SPT + )IGBT 采用了阴极侧载流子浓度增强技术，降低了通态损耗。 The new generation enhanced planar gate soft through (Soft Punch Through + , SPT + ) IGBT adopts the cathode-side carrier concentration enhancement technology, which reduces the on-state loss．
25184 现有仿真模型大多是基于典型穿通型(Punch Through，PT)IGBT 建立的，无法准确描述 SPT + 型 IG-BT 的通态特性。 The existing simulation models are mostly based on typical punch through (PT) IGBTs, which cannot accurately describe the on-state characteristics of SPT + IGBT．