Speech reflects people’s mental state and using a microphone sensor is a potential method for human–computer interaction. Speech recognition using this sensor is conducive to the diagnosis of mental illnesses. The gender difference of speakers affects the process of speech emotion recognition based on specific acoustic features, resulting in the decline of emotion recognition accuracy. Therefore, we believe that the accuracy of speech emotion recognition can be effectively improved by selecting different features of speech for emotion recognition based on the speech representations of different genders. In this paper, we propose a speech emotion recognition method based on gender classification. First, we use MLP to classify the original speech by gender. Second, based on the different acoustic features of male and female speech, we analyze the influence weights of multiple speech emotion features in male and female speech, and establish the optimal feature sets for male and female emotion recognition, respectively. Finally, we train and test CNN and BiLSTM, respectively, by using the male and the female speech emotion feature sets. The results show that the proposed emotion recognition models have an advantage in terms of average recognition accuracy compared with gender-mixed recognition models.

Noninvasive fetal ECG (FECG) monitoring holds significant importance in ensuring the normal development of the fetus. Since FECG is usually submerged by maternal ECG (MECG) and background noise in abdominal ECG (AECG), it is challenging to exactly restore the waveform details of FECG from AECG. To address this issue, a temporal convolutional generative adversarial network (TCGAN) is proposed for FECG extraction using single-channel AECG. In order to utilize both the global and local ECG features in time domain, we built an encoder-decoder architecture for designing generator. The model architecture consists of temporal convolution blocks, transpose convolutions and skip connections. The skip connections attempt to achieve the purpose of amalgamating information from feature maps extracted by convolutional layers using transpose convolution operations, which facilitates the decoder for extracting more detail information. TCGAN is rigorously evaluated using both synthetic dataset FECGSYDB and real-world dataset ADFECGDB. The experimental results on above datasets demonstrate the outstanding performance of TCGAN in terms of fetal QRS complex detection, achieving PPV of 99.54% and 99.02%, respectively. Comparing with the state-of-the-art methods, TCGAN could extract FECG with well-preserved waveform details. This helps doctors achieve more accurate assessment of fetal development. For reproducibility, all code and data have been made available at https://github.com/zhwt-xidian/TCGAN .

Consecutive interpreting involves a demanding language task where mental workload (MWL) is crucial for assessing interpreters' performance. An elevated cognitive load in interpreters may lead to the interpretation failures. The widely used NASA-TLX questionnaire effectively measures MWL. However, a global score was employed in previous interpretation studies, overlooking the distinct contributions of MWL components to the interpreters' performance. Accordingly, we recruited twenty novice interpreters who were postgraduate students specializing in interpreting to complete the consecutive interpreting task. Throughout the process, we used functional near-infrared spectroscopy (fNIRS) to monitor the hemodynamic response in participants' brains. The NASA-TLX was used to measure the MWL during interpreting with six components, including mental demand, physical demand, temporal demand, performance, effort, and frustration. Five interpretation experts were invited to assess the interpretation quality. The Bayes factor approach was employed to explore the components that contributes the most to the interpretation quality. It indicated that mental demand strongly contributed to the interpretation quality. Moreover, the mediation analysis revealed a positive correlation between mental demand and brain activation in three brain areas, which, in turn, was negatively correlated with interpretation quality, indicating the predictive role of mental demand in interpretation quality through the mediating of brain activation. The functions of the mediating brain areas, including the inferior frontal gyrus, middle temporal gyrus, and inferior temporal gyrus, aligned with the three efforts proposed by Gile's effort model, which emphasizes the significance of three fundamental efforts in achieving successful interpreting. These findings have implications for interpreter learning and training.