No abstract

Speech information is the most important means of human communication, and it is crucial to separate the target voice from the mixed sound signals. This paper proposes a speech separation model based on convolutional neural networks and attention mechanism. The magnitude spectrum of the mixed speech signals, as the input, has its high dimensionality. By analyzing the characteristics of the convolutional neural network and attention mechanism, it can be found that the convolutional neural network can effectively extract low-dimensional features and mine the spatiotemporal structure information in the speech signals, and the attention mechanism can reduce the loss of sequence information. The accuracy of speech separation can be improved effectively by combining two mechanisms. Compared to the typical speech separation model DRNN-2 + discrim, this method achieves 0.27 dB GNSDR gain and 0.51 dB GSIR gain, which illustrates that the speech separation model proposed in this paper has achieved an ideal separation effect.

High-energy consumption in data centers has become a critical issue. The dynamic server consolidation has significant effects on saving energy of a data center. An effective way to consolidate virtual machines is to migrate virtual machines in real time so that some light load physical machines can be turned off or switched to low-power mode. The present challenge is to reduce the energy consumption of cloud data centers. In this paper, for the first time, a server consolidation algorithm based on the culture multiple-ant-colony algorithm was proposed for dynamic execution of virtual machine migration, thus reducing the energy consumption of cloud data centers. The server consolidation algorithm based on the culture multiple-ant-colony algorithm (CMACA) finds an approximate optimal solution through a specific target function. The simulation results show that the proposed algorithm not only reduces the energy consumption but also reduces the number of virtual machine migration.

For the problem of elderly people falling easily, it is very necessary to correctly detect the occurrence of falls and provide early warning, which can greatly reduce the injury caused by falls. Most of the existing fall detection algorithms require the monitored persons to carry wearable devices, which will bring inconvenience to their lives and few algorithms pay attention to the direction of the fall. Therefore, we propose a video-based fall detection and direction judgment method based on human posture estimation for the first time. We predict the joint point coordinates of each human body through the posture estimation network, and then use the SVM classifier to detect falls. Next, we will use the three-dimensional human posture information to judge the direction of the fall. Compared to the existing methods, our method has a great improvement in sensitivity, specificity, and accuracy which reaches 95.86, 99.5, and 97.52 on the Le2i fall dataset, respectively, whereas on the UR fall dataset, they are 95.45, 100, and 97.43, respectively.

The paper proposes an architecture of SIP-based network video surveillance system. Call mechanism of SIP gives a solution to the interconnection among multi-surveillance systems under complex networks. H.264 is adopted as encoding/decoding technology which has the higher compression rate than other technologies. The process of design and implementation are described and some key technologies are discussed. Using SIP in video surveillance system not only extends its physical scope, but also promotes intelligence of monitoring.