| ID | 原文 | 译文 |
| 18955 | 实验结果验证了所提算法的有效性，且具有对系统关键参数鲁棒性的优点。 | Experiment results show the proposed channel method has a better performance on the estimation accuracythan the state-of-art method, meanwhile it works robustly against the dynamic system key parameters. |
| 18956 | 在LTE-V2X系统中，针对车载用户切换过程中蜂窝链路及SideLink(SL)链路质量不高以及SL辅助切换过程中SL链路易中断的问题，该文提出一种基于SL的联合切换方案，主要包含：联合切换流程设计、联合切换信令流程设计以及联合切换判决算法设计。 | For LTE-V2X(Long Term Evolution-Vehicle to Everything) system, the cellular link and theSideLink (SL) are usually unstable in the handover process, and the situation is even deteriorating when the SLis employed to assist the normal handover process. To solve these problems, an SL-assisted joint handover scheme is proposed for vehicles in the network, which mainly includes: joint handover procedure design, signaling design, and the joint handover decision algorithm. |
| 18957 | 首先，在联合切换流程中利用SL技术实现联合切换，并对执行联合切换的SL链路质量进行筛选，以保证联合切换的可靠性； | Firstly, the SL is established for the vehicles thatare about to request for handover. The SL is set up between the pair of vehicles with the best channel quality to ensure the link reliability. |
| 18958 | 其次，对联合切换信令流程进行了完善，以优化SL辅助切换过程中SL链路易中断问题； | Secondly, in order to tackle the perplexing problem of SL being vulnerable in the fast changing radio environment, the joint handover signaling procedure is optimized with respect to two different realistic circumstances. |
| 18959 | 最后，在联合切换判决算法中将车载用户的移动方向纳入切换判决条件，从而减少不必要的切换。 | Finally, the vehicle’s moving direction is further included in making thehandover decision, thus reducing unnecessary handover operations. |
| 18960 | 仿真结果显示，该文所提方案能有效提升切换成功率，与此同时还能有效减少执行LTE切换的次数。 | Simulation results illustrate that the SL-assisted joint handover scheme can effectively ameliorate the handover success rate and reduce significantly then umber of LTE handovers. |
| 18961 | 为了挖掘说话人识别领域中人脸和语音的相关性，该文设计多模态生成对抗网络(GAN)，将人脸特征和语音特征映射到联系更加紧密的公共空间， | In order to explore the correlation between face and audio in the field of speaker recognition, a novelmultimodal Generative Adversarial Network (GAN) is designed to map face features and audio features to amore closely connected common space. |
| 18962 | 随后利用3元组损失对两个模态的联系进一步约束，拉近相同个体跨模态样本的特征距离，拉远不同个体跨模态样本的特征距离。 | Then the Triplet-loss is used to constrain further the relationshipbetween the two modals, with which the intra-class distance of the two modals is narrowed, and the inter-classdistance of the two modals is extended. |
| 18963 | 最后通过计算公共空间特征的跨模态余弦距离判断人脸和语音是否匹配，并使用Softmax识别说话人身份。 | Finally, the cosine distance of the common space features of the twomodals is calculated to judge whether the face and the voice are matched, and Softmax is used to recognize the speaker identity. |
| 18964 | 实验结果表明，该方法能有效地提升说话人识别准确率。 | Experimental results show that this method can effectively improve the accuracy of speaker recognition. |