ID 原文 译文
25385 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。 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．
25386 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。 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-synthes is combing DNN (GABS-DNN) model is proposed for improving the accuracy of AＲcoefficient estimation and stability of the DNN training in the noisy environment.
25387 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 DNN 预处理及 LDＲ 参数估计和解码器的 AＲ 系数到功率谱的转换。 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．
25388 在优化目标函数的过程中，引入了增强谱和观测谱的误差，减少了反向传播时LDＲ 的梯度对增强网络的影响，实现了稳定估计含噪语音的 AＲ 系数。 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 co-efficients of noisy speech．
25389 设计了一种基于不同半径的二氧化钒(VO2)圆环加载于介质层上的宽带可调超材料吸波器，利用 VO2随温度变化的相变特性，实现了外部温度对吸收曲线的动态调节。 A broad and tunable metamaterial absorber based on vanadium dioxide (VO2) rings with different radiusloaded on the dielectric layer is designed. The phase transition characteristics of VO2 with temperature are used to realize the dynamic adjustment of the absorption curve of external temperature.
25390 通过仿真计算表明，该吸波器在外部温度为 350K 时在8.09 ～11. 23THz 带宽范围内吸收率可达 90% 以上，表现出高吸收特性;而外部温度为 300K 时在相同频段内吸收率始终低于 20% ，从而实现了对电磁波吸收的可调功能。 Simulation calculations show that the absorber can reach more than 90% in the bandwidth of 8. 09 ～ 11. 23THz when the external temperature is 350K, showing high absorption characteristics; while the absorption coefficient in the same frequency band is always lower than 20% when the external temperature is 300K, achieving the adjustable function of electromagnetic wave absorption．
25391 进一步对吸波器的等效阻抗和电场分布进行分析讨论，阐明 VO2对吸收性能的调节机制。 The equivalent impedance and electricfield distribution of the absorber are further analyzed and discussed, and the adjustment mechanism of VO2 on the absorptionis clarified．
25392 此外，文章讨论了结构参数、偏振角以及入射角对吸收的影响。 In addition, the article discusses the effects of structural parameters, polarization angles, and angles of incidence on the absorptivity.
25393 其结果表明，合理选择结构参数可实现吸收性能与偏振角、入射角的无关性。 The results show that reasonable selection of parameters of the structure can achieve the independence of the absorbing performance from the polarization angle and the angle of incidence．
25394 本文的结论对于设计其它类型的超宽带可调吸波器具有重要的指导意义。 The conclusions of this paper have promising potential for designing other types of ultra-wideband tunable absorbers．