Search

In this paper, a new speech feature fusion method is proposed for speaker recognition on the basis of the cross gate parallel convolutional neural network (CG-PCNN). The Mel filter bank features (MFBFs) of different frequency resolutions can be extracted from each speech frame of a speaker's speech by several Mel filter banks, where the numbers of the triangular filters in the Mel filter banks are different. Due to the frequency resolutions of these MFBFs are different, there are some complementaries for these MFBFs. The CG-PCNN is utilized to extract the deep features from these MFBFs, which applies a cross gate mechanism to capture the complementaries for improving the performance of the speaker recognition system. Then, the fusion feature can be obtained by concatenating these deep features for speaker recognition. The experimental results show that the speaker recognition system with the proposed speech feature fusion method is effective, and marginally outperforms the existing state-of-the-art systems.

Cucumber, cabbage(Brassica oleracea L.), and cowpea as acceptor materials, the effects of four concentrations of (0.01 g/ml, 0.02g/ml, 0.03 g/ml and 0.04g/ml) root, stem and leaf aqueous extracts of pepper on the allelopathy of recipient vegetable and the enzyme activity in rhizosphere soil were studied. The results showed that the allelopathic effect of different tissue extracts of pepper was leaf > root > stem, and the greater the concentration of treatment solution, the stronger the inhibitory effect on the recipient vegetables. According to the value of the comprehensive membership function, the order of the allelopathic effect of different tissue extracts of capsicum on the recipient vegetables is cucumber > cabbage > cowpea. The concentration of the pepper extract, the extraction site, and the difference of the acceptor materials can affect the soil enzyme activity. The urease activity increases with the increase of the concentration, and the catalase and sucrase activities increase first and then decrease.

The experiment was carried out with pumpkin ‘JingXinZhen NO.3’ as the rootstock, thin-skin melon ‘IVF09’ as the scion, and self-rooted seedling as the control. The effect of grafting on the sugar metabolism of melon seedlings under copper stress was studied. The results showed that under the condition of copper stress, the growth of melon seedlings was inhibited, the sugar content of leaves decreased, and the sucrose content decreased significantly, and the total activity of sugar metabolism related enzymes changed. However, under the same conditions, the biomass of the grafted seedlings is greater than that of the self-rooted seedlings, and the greater the stress concentration, the greater the grafting promoting effect; Glucose and fructose in grafted leaves were significantly higher than those in self-rooted seedlings, raffinose and stachyose were significantly lower than self-rooted seedlings, the highest ratio of glucose to fructose increased by 5.26% and 32%; and the total activity of sucrose synthase (SS) in the leaves of grafted seedlings was lower than that of self-rooted seedlings. The total activity of sucrose phosphate synthase (SPS), neutral invertase (NI) and acid invertase (AI) was greater than that of self-rooted seedlings. The results showed that grafting could change the sugar activity of seedling leaves by changing the total activity of sugar metabolism related enzymes in melon seedling leaves, and then change the sugar metabolism of melon seedlings to reduce the toxicity of copper stress on melon seedlings.

Some highly ordered compounds of graphene oxide (GO), e.g., the so-called clamped and unzipped GO, are shown to have piezoelectric responses via first-principles density functional calculations. By applying an electric field perpendicular to the GO basal plane, the largest value of in-plane strain and strain piezoelectric coefficient, d31 are found to be 0.12% and 0.24 pm/V, respectively, which are comparable with those of some advanced piezoelectric materials. An in-depth molecular structural analysis reveals that deformation of the oxygen doping regions in the clamped GO dominates its overall strain output, whereas deformation of the regions without oxygen dopant in the unzipped GO determines its overall piezoelectric strain. This understanding explains the observed dependence of d31 on oxygen doping rate, i.e., higher oxygen concentration giving rise to a larger d31 in the clamped GO whereas leading to a reduced d31 in the unzipped GO. As the thinnest two-dimensional piezoelectric materials, GO has a great potential for a wide range of MEMS/NEMS actuators and sensors., 10 pages, 4 figures