Multi-scale discrepancy adversarial network for cross-corpus speech emotion recognition

Background One of the most critical issues in human-computer interaction applications is recognizing human emotions based on speech.In recent years,the challenging problem of cross-corpus speech emotion recognition(SER)has generated extensive research.Nevertheless,the domain discrepancy between training data and testing data remains a major challenge to achieving improved system performance.Methods This paper introduces a novel multi-scale discrepancy adversarial(MSDA)network for conducting multiple timescales domain adaptation for cross-corpus SER,i.e.,integrating domain discriminators of hierarchical levels into the emotion recognition framework to mitigate the gap between the source and target domains.Specifically,we extract two kinds of speech features,i.e.,handcraft features and deep features,from three timescales of global,local,and hybrid levels.In each timescale,the domain discriminator and the feature extrator compete against each other to learn features that minimize the discrepancy between the two domains by fooling the discriminator.Results Extensive experiments on cross-corpus and cross-language SER were conducted on a combination dataset that combines one Chinese dataset and two English datasets commonly used in SER.The MSDA is affected by the strong discriminate power provided by the adversarial process,where three discriminators are working in tandem with an emotion classifier.Accordingly,the MSDA achieves the best performance over all other baseline methods.Conclusions The proposed architecture was tested on a combination of one Chinese and two English datasets.The experimental results demonstrate the superiority of our powerful discriminative model for solving cross-corpus SER.

TaMADS2-3D,a MADS transcription factor gene,regulates phosphate starvation responses in plants

Soil inorganic phosphate(Pi)levels are frequently suboptimal for the growth and development of crop plants.Although MADS-box genes participate in diverse plant developmental processes,their involvement in phosphate starvation responses(PSRs)remains unclear.We identified a type I MADS-box transcription factor gene,Ta MADS2-3 D,which was rapidly induced under low-Pi stress in roots of wheat(Triticum aestivum).A Ta MADS2-3 D-GFP fusion protein was found located in the nucleus.Transgenic Arabidopsis plants overexpressing Ta MADS2-3 D(Ta MADS2-3 DOE)showed shortened primary roots,increased lateral root density,and retarded seedling growth under high-Pi(HP)conditions,accompanied by increased Pi contents in their shoots and roots.The Arabidopsis Ta MADS2-3 DOE plants showed similar PSR phenotypes under low Pi(LP)conditions.These results indicate constitutive activation of PSRs by overexpression of Ta MADS2-3 D in Arabidopsis.Reactive oxygen species(ROS),H_(2)O_(2)and O_(2)^(-),levels were increased in root tips of Arabidopsis Ta MADS2-3 DOE plants under HP conditions.Transcriptome analysis of Arabidopsis Ta MADS2-3 DOE plants under different Pi regimes revealed expression changes for a variety of PSR genes including At ZAT6.Overexpression of Ta MADS2-3 D in wheat also led to constitutive activation of PSRs.We propose that Ta MADS2-3 D regulates plant PSRs probably by modulating ROS homeostasis,root development,PSR gene expression,and Pi uptake.This study increases our understanding of plant PSR regulation and provides a valuable gene for improving phosphorus-use efficiency in wheat and other crops.

Reactions of Triticum urartu accessions to two races of the wheat yellow rust pathogen

Triticum urartu(AA,2n=2x=14),a wild grass endemic to the Fertile Crescent(FC),is the progenitor of the A subgenome in common wheat.It belongs to the primary gene pool for wheat improvement.Here,we evaluated the yellow rust(caused by Puccinia striiformis f.sp.tritici,Pst)reactions of 147 T.urartu accessions collected from different parts of the FC.The reactions varied from susceptibility to strong resistance.In general,there were more accessions with stronger resistance to race CYR33 than to CYR 32.In most cases the main form of defense was a moderate resistance characterized by the presence of necrotic/chlorotic lesions with fewer Pst uredinia on the leaves.Forty two accessions displayed resistance to both races.Histological analysis showed that Pst growth was abundant in the compatible interaction but significantly suppressed by the resistant response.Gene silencing mediated by Barley stripe mosaic virus was effective in two T.urartu accessions with different resistance responses,indicating that this method can expedite future functional analysis of resistance genes.Our data suggest that T.urartu is a valuable source of resistance to yellow rust,and represents a model for studying the genetic,genomic and molecular basis underlying interaction between wheat and Pst.

A Fiber Tractography Study of Social-Emotional Related Fiber Tracts in Children and Adolescents with Autism Spectrum Disorder

The symptoms of autism spectrum disorder(ASD) have been hypothesized to be caused by changes in brain connectivity. From the clinical perspective, the‘‘disconnectivity'' hypothesis has been used to explain characteristic impairments in ‘‘socio-emotional'' function.Therefore, in this study we compared the facial emotional recognition(FER) feature and the integrity of socialemotional-related white-matter tracts between children and adolescents with high-functioning ASD(HFA) and their typically developing(TD) counterparts. The correlation between the two factors was explored to find out if impairment of the white-matter tracts is the neural basis of social-emotional disorders. Compared with the TD group,FER was significantly impaired and the fractional anisotropy value of the right cingulate fasciculus was increased in the HFA group(P \ 0.01). In conclusion, the FER function of children and adolescents with HFA was impaired and the microstructure of the cingulate fasciculus had abnormalities.