ID | 原文 | 译文 |
53887 | 最后,根据预测的具有较高权重的高斯分量的均值在每个簇上的投影,获得准确的量测集划分。 | Finally, according to the projection of the mean vectors of the predicted Gaussian component with higher weight on each cluster, an accurately measurement set partition is obtained. |
53888 | 实验结果表明,与现有的量测集划分方法相比,该算法在保持跟踪精度的同时,可以大大减少计算时间。 | The simulation results show that, compared with the existing measurement set partition methods, this proposed algorithm can greatly reduce the calculation time while maintaining tracking accuracy. |
53889 | 针对实际场景中存在的具有上下行双向传输任务的通信系统,本文提出了一种双向中继协作非正交多址接入(NOMA,non-orthogonal multiple access)传输方案,基于解码转发(DF,Decode and Forward)协议研究信号的上行和下行双向传输技术, | For the communication system with uplink and downlink bidirectional transmission task in the actual scene, this paper proposes a two-way relay cooperative non-orthogonal multiple access(NOMA) transmission scheme, which studies the uplink and downlink two-way transmission of signals based on decode and forward(DF) protocol. |
53890 | 与现有NOMA方案不同,本方案为近端用户分配较大的功率,利用网络编码(NC,network coding)原理在两个时隙内实现基站和用户之间的双向信息交换。 | This scheme allocates more power to the near user which different from the existing NOMA schemes, and realizes bidirectional information exchange between base station and users by network coding(NC) principle. |
53891 | 进一步考虑不完美信道状态信息(CSI,Channel State Information)条件,分析系统的传输性能并推导了系统中断概率以及遍历和速率闭合表达式。 | Further considering the imperfect channel state information(CSI) condition, the transmission performance of the system is analyzed, and the expressions of outage probability, ergodic sum rate are derived. |
53892 | 仿真结果表明,在完美CSI和不完美CSI条件下,相比于现有文献所提方案、单向中继(OWR,One-Way Relay)和正交多址(OMA,Orthogonal Multiple Access)网络,本文所提方案有效降低了系统的传输中断概率,提高了系统的遍历和速率以及系统吞吐量。 | Simulation results show that, compared with the scheme proposed in the existing literature, one-way relay(OWR)and orthogonal multiple access(OMA) networks, the proposed scheme can effectively reduce the transmission outage probability, improve the traversal rate and throughput of the system under perfect CSI and imperfect CSI conditions. |
53893 | 针对自组织麦克风网络,如何充分有效地利用多通道语音数据获得更好的语音分离性能是一个难题。 | For ad-hoc microphones, it is a challenge that how to make the best of multichannel audio data to achieve better performance in multi-talker speech separation tasks. |
53894 | 本文介绍了一种新的多通道语音分离方法,通过引入压缩激励脊髓模块,在麦克风位置未知时,也能显式地学习潜在的通道关系,自适应地更新各个通道对应特征的权重,以增加少量的额外计算代价达到增强语音分离的效果。 | This paper introduces a new multichannel speech separation method, i. e. , Squeeze-Excitation-Spinal(SES) module, which can explicitly learn latent channel-wise relationship and adaptively update the weights of each channel characteristics without knowing the positions of microphones in advance so that the enhanced effects of speech separation come at the least expense. |
53895 | 压缩激励脊髓模块通过将多通道的特征信息压缩到通道维度,获得全局通道依赖关系的表征,利用激活函数根据通道关系表征对瓶颈单元筛选出有价值的特征信息。 | SES module obtains the representation of global inter-channel dependency by squeezing multichannel feature information into the channel dimension and uses activation functions to screen out valuable feature information based on the representation in a bottleneck unit. |
53896 | 瓶颈单元由脊髓网络组成,通过逐步输入的方式生成全局信息和重新配置权重,更有效地处理数据。 | The bottleneck unit consists of spinal modules that generate global information and redistributes weights through step-by-step input. |