CST: Complex Sparse Transformer for Low-SNR Speech Enhancement.

Speech enhancement tasks for audio with a low SNR are challenging. Existing speech enhancement methods are mainly designed for high SNR audio, and they usually use RNNs to model audio sequence features, which causes the model to be unable to learn long-distance dependencies, thus limiting its performance in low-SNR speech enhancement tasks. We design a complex transformer module with sparse attention to overcome this problem. Different from the traditional transformer model, this model is extended to effectively model complex domain sequences, using the sparse attention mask balance model's attention to long-distance and nearby relations, introducing the pre-layer positional embedding module to enhance the model's perception of position information, adding the channel attention module to enable the model to dynamically adjust the weight distribution between channels according to the input audio. The experimental results show that, in the low-SNR speech enhancement tests, our models have noticeable performance improvements in speech quality and intelligibility, respectively.

A fluid-structure interaction model accounting arterial vessels as a key part of the blood-flow engine for the analysis of cardiovascular diseases.

According to the classical Windkessel model, the heart is the only power source for blood flow, while the arterial system is assumed to be an elastic chamber that acts as a channel and buffer for blood circulation. In this paper we show that in addition to the power provided by the heart for blood circulation, strain energy stored in deformed arterial vessels in vivo can be transformed into mechanical work to propel blood flow. A quantitative relationship between the strain energy increment and functional (systolic, diastolic, mean and pulse blood pressure) and structural (stiffness, diameter and wall thickness) parameters of the aorta is described. In addition, details of blood flow across the aorta remain unclear due to changes in functional and other physiological parameters. Based on the arterial strain energy and fluid-structure interaction theory, the relationship between physiological parameters and blood supply to organs was studied, and a corresponding mathematical model was developed. The findings provided a new understanding about blood-flow circulation, that is, cardiac output allows blood to enter the aorta at an initial rate, and then strain energy stored in the elastic arteries pushes blood toward distal organs and tissues. Organ blood supply is a key factor in cardio-cerebrovascular diseases (CCVD), which are caused by changes in blood supply in combination with multiple physiological parameters. Also, some physiological parameters are affected by changes in blood supply, and vice versa. The model can explain the pathophysiological mechanisms of chronic diseases such as CCVD and hypertension among others, and the results are in good agreement with epidemiological studies of CCVD.

LPG-PCFG: An Improved Probabilistic Context- Free Grammar to Hit Low-Probability Passwords.

With the development of the Internet, information security has attracted more attention. Identity authentication based on password authentication is the first line of defense; however, the password-generation model is widely used in offline password attacks and password strength evaluation. In real attack scenarios, high-probability passwords are easy to enumerate; extremely low-probability passwords usually lack semantic structure and, so, are tough to crack by applying statistical laws in machine learning models, but these passwords with lower probability have a large search space and certain semantic information. Improving the low-probability password hit rate in this interval is of great significance for improving the efficiency of offline attacks. However, obtaining a low-probability password is difficult under the current password-generation model. To solve this problem, we propose a low-probability generator-probabilistic context-free grammar (LPG-PCFG) based on PCFG. LPG-PCFG directionally increases the probability of low-probability passwords in the models' distribution, which is designed to obtain a degeneration distribution that is friendly for generating low-probability passwords. By using the control variable method to fine-tune the degeneration of LPG-PCFG, we obtained the optimal combination of degeneration parameters. Compared with the non-degeneration PCFG model, LPG-PCFG generates a larger number of hits. When generating 107 and 108 times, the number of hits to low-probability passwords increases by 50.4% and 42.0%, respectively.