ID 原文 译文
21235 首先，将声音数据转化为gammatone频谱，并计算其多频带能量分布； First, by using gammatone spectrogram analysis, sound signal is transformed into multi-band power distribution image.
21236 接着，对多频带能量分布图进行8×8分块与离散余弦变换； Next, 8×8 size blocking and discrete cosine transform are applied to analyze themulti-band power distribution image.
21237 然后，对8×8的离散余弦变换系数进行Zigzag扫描，抽取离散余弦变换系数的主要系数作为声音事件的特征； Based on the main Zigzag coefficients which are scanned from the discretecosine transform coefficients, features of sound event are constructed.
21238 最后，利用随机森林分类器对特征建模与检测。 Finally, features are modeled anddetected through random forests classifier.
21239 实验结果表明，在低信噪比及各种噪声环境下，该文提出的方法具有良好的检测效果。 The results show that the proposed method achieves a better detection performance in low SNR comparing to other methods.
21240 针对云无线接入网络(C-RAN)的资源分配问题，该文采用max-min公平准则作为优化准则，以C-RAN用户的能量效率作为优化目标函数，在满足最大发射功率和最小传输速率约束条件下，通过最大化最差链路的能量效率来实现用户发射功率和无线远端射频单元(RRHs)波束成形向量的联合优化。 The resource allocation for Cloud Radio Access Network (C-RAN) is investigated. The max-minfairness criterion is used as the optimization criterion and the Energy Efficiency (EE) of C-RAN users is takenas the optimization objective function, by maximizing the EE of the worst link under the constraints ofmaximum transmit power and minimum transmit rate, the user transmit power and Remote Radio Heads(RRHs) beamforming vectors are jointly optimized.
21241 上述优化问题属于非线性、分式规划问题，为了方便求解，首先将原优化问题转化为差分形式的优化问题， The above optimization problem belongs to the nonlinearand fractional programming problem. First, the original nonconvex optimization problem is transformed into anequivalent optimization problem in subtractive form.
21242 然后通过引入变量将差分形式的、非平滑优化问题转化为平滑优化问题。 Then, by introducing a new variable, non-smoothequivalent optimization problem is transformed into a smooth optimization problem.
21243 最终，提出一种双层迭代功率分配和波束成形算法。 Finally, a two-layeriterative power allocation and beamforming algorithm is proposed.
21244 在仿真实验中，将该文算法与传统的非能效资源分配算法和能量效率最大化算法进行了比较， The proposed algorithm is compared with traditional non-EE resource allocation algorithm and EE maximization algorithm.