No abstract

Singing voice detection is still a challenging task because the voice can be obscured by instruments having the same frequency band, and even the same timbre, produced by mimicking the mechanism of human singing. Because of the poor adaptability and complexity of feature engineering, there is a recent trend towards feature learning in which deep neural networks play the roles of feature extraction and classification. In this paper, we present two methods to explore the channel properties in the convolution neural network to improve the performance of singing voice detection by feature learning. First, channel attention learning is presented to measure the importance of a feature, in which two attention mechanisms are exploited, i.e., the scaled dot-product and squeeze-and-excitation. This method focuses on learning the importance of the feature map so that the neurons can place more attention on the more important feature maps. Second, the multi-scale representations are fed to the input channels, aiming at adding more information in terms of scale. Generally, different songs need different scales of a spectrogram to be represented, and multi-scale representations ensure the network can choose the best one for the task. In the experimental stage, we proved the effectiveness of the two methods based on three public datasets, with the accuracy performance increasing by up to 2.13 percent compared to its already high initial level.

A conformal radio frequency identification tag antenna can be integrated into printed circuit board (PCB) is presented. The simulation and experiment results indicate that the proposed tag can be reached as being applied on stacked PCB boards or separated PCB board. The design area of the proposed tag is 6 × 46 mm, which is small enough for most PCB boards. And it is also proved that the proposed tag can be used in PCB boards with different thicknesses. The maximum read range is measured to be 2.7 and 3.5 m as the tag is deployed on stacked PCB boards and separately placed PCB boards.

a b s t r a c tObjective: To evaluate the effect of Internet technology on continuing nursing in elderly patients with diabetic feet. Method: From January 2015 to July 2016, 12 elderly patients with diabetic foot ulcers were enrolled from the Endocrinology Department in our hospital. We used "WeChat", "E nursing" and other Internet technologies to perform remote extended care and to observe the foot ulcer outcomes. Results: All foot ulcers healed with a wound healing time between 38 and 73 days (average 57.08 ± 12.69 days). Patients did not need to travel long distances to seek medical treatment for foot ulcers, improving their satisfaction. Conclusions: The implementation of extended care for elderly patients with diabetic foot ulcers was based on the application of Internet technology. It is helpful to facilitate medical treatment, share high quality health resources and promote disease rehabilitation.

요 약 이 논문에서는 인간 청각 시스템에 기반한 모음 개시 지점 (VOP)탐지Abstract This paper presents a vowel onset point (VOP) detection method based on the human auditory system. This method maps the "perceptual" frequency scale, i.e. Mel scale onto a linear acoustic frequency, and then establishes a series of Triangular Mel-weighted Filter Bank simulate the function of band pass filtering in human ear. This nonlinear critical-band filter bank helps greatly reduce the data dimensionality, and eliminate the effect of harmonic waves to make the formants more prominent in the nonlinear spaced Mel spectrum. The sum of mel spectrum peaks energy is extracted as feature for each frame, and the instinct at which the energy amplitude starts rising sharply is detected as VOP, by convolving with Gabor window. For the single-word database which contains 12 vowels articulated with different kinds of consonants, the experimental results showed a good average detection rate of 72.73%, higher than other vowel detection methods based on short-time energy and zero-crossing rate.