ID 原文 译文
21995 最后，设计了仿真实验对算法在闪烁噪声分布未知和非平稳条件下的跟踪性能进行了验证，同时对算法的计算复杂度进行了仿真分析。 In order to validate the performance of this algorithm, comparative experiments are carried out from two aspects of tracking accuracy and computational complexity.
21996 仿真结果表明，在量测噪声分布未知和非平稳条件下，VB-IMM具有较高的跟踪精度，且算法复杂度较小，易于实现。 Simulation results verify good performance of tracking error and low computational complexity of the proposed algorithm.
21997 跨模态说话人标注旨在利用说话人的不同生物特征进行相互匹配和互标注，可广泛应用于各种人机交互场合。 Cross-modal speaker tagging aims to learn the latent relationship between different biometrics for mutual annotation, which can potentially be utilized in various human-computer interactions.
21998 针对人脸和语音两种不同模态生物特征之间存在明显的“语义鸿沟”问题，该文提出一种结合有监督联合一致性自编码器的跨音视频说话人标注方法。 In order to solve the "semantic gap" between the face and audio modalities, this paper presents an efficient supervised joint correspondence auto-encoder to link the face and audio counterpart, where by the speaker can be crosswise tagged.
21999 首先分别利用卷积神经网络和深度信念网络分别对人脸图像和语音数据进行判别性特征提取，接着在联合自编码器模型的基础上，提出一种新的有监督跨模态神经网络模型，同时嵌入softmax 回归模型以保证模态间和模态内样本的相似性，进而扩展为 3 种有监督一致性自编码器神经网络模型来挖掘音视频异构特征之间的潜在关系，从而有效实现人脸和语音的跨模态相互标注。 First, Convolutional Neural Network (CNN) and Deep Belief Network (DBN) are used to extract the discriminative features of the face and the audio samples respectively. Then, a supervised neural network model associated with softmax regression is embedded into a joint auto-encoder model, which can discriminatively preserving the inter-modal and intra-modal similarities. Accordingly, three different kinds of supervised joint correspondence auto-encoder models are presented to correlate the semantic relationships between the face and the audio counterparts, and the speaker can be crosswise annotated efficiently.
22000 实验结果表明，该文提出的网络模型能够有效的对说话人进行跨模态标注，效果显著，取得了对姿态变化和样本多样性的鲁棒性。 The experimental results show that the proposed supervised joint auto-encoder is able to perform cross-modal speaker tagging with outstanding performance, and demonstrate the robustness to facial posture variations and sample diversities.
22001 近阈值电压技术通过降低晶体管的电源电压来降低芯片能耗和提升能效。 Near-threshold voltage computing enables transistor voltage scaling to continue with Moore's Law projection and dramatically improves power and energy efficiency.
22002 但是，近阈值电压技术会在 Cache中引起大量位错误，严重影响末级缓存的功能。 However, a great number of bit-cell errors occur in large SRAM structures, such as Last-Level Cache (LLC).
22003 针对近阈值电压下超过 1%的位错误率造成的 Cache 故障问题，该文提出一种基于传统 6T SRAM 单元的可容错的末级缓存结构(FTLLC)。 A Fault-Tolerant LLC (FTLLC) design with conventional 6T SRAM cells is proposed to deal with a higher failure rate which is more than 1% at near-threshold voltage.
22004 该策略对缓存条目中的错误进行了低错纠正和多错压缩，提高了 Cache 中数据保存的可靠性。 FTLLC improves the reliability of data stored in Cache by correcting the single-error and compressing multi-errors in Cache entry.