Deep neural networks have achieved great success in almost every field of artificial intelligence. However, several weaknesses keep bothering researchers due to its hierarchical structure, particularly when large-scale parallelism, faster learning, better performance, and high reliability are required. Inspired by the parallel and large-scale information processing structures in the human brain, a shallow broad neural network model is proposed on a specially designed multi-order Descartes expansion operation. Such Descartes expansion acts as an efficient feature extraction method for the network, improve the separability of the original pattern by transforming the raw data pattern into a high-dimensional feature space, the multi-order Descartes expansion space. As a result, a single-layer perceptron network will be able to accomplish the classification task. The multi-order Descartes expansion neural network (MODENN) is thus created by combining the multi-order Descartes expansion operation and the single-layer perceptron together, and its capacity is proved equivalent to the traditional multi-layer perceptron and the deep neural networks. Three kinds of experiments were implemented, the results showed that the proposed MODENN model retains great potentiality in many aspects, including implementability, parallelizability, performance, robustness, and interpretability, indicating MODENN would be an excellent alternative to mainstream neural networks.
In this paper, we focus on the problems of single granularity in feature extraction, loss of temporal information and inefficient use of frame features in discrete speech emotion recognition. Firstly, preliminary cognitive mechanism of auditory emotion is explored through cognitive experiments, and then a multi-granularity fusion feature extraction method inspired by the mechanism for discrete emotional speech signals is proposed. The method can extract 3 different granularity features, including short-term dynamic features of frame granularity, dynamic features of segment granularity and long-term static features of global granularity. Finally, we use the LSTM network model to classify emotions according to the long-term and short-term characteristics of the fusion features. We implement experiment on the discrete emotion datasets of CHEAVD (CASIA Chinese Emotional Audio-Visual Database) released by the Institute of automation, China Research Academy of Sciences, and achieved improvement in recognition rate, increasing the MAP by 6.48%.
At present, there are very few analysis methods for long-term electroencephalogram (EEG) components. Temporal information is always ignored by most of the existing techniques in cognitive studies. Therefore, a new analysis method based on time-varying characteristics was proposed. First of all, a regression model based on Lasso was proposed to reveal the difference between acoustics and physiology. Then, Permutation Tests and Gaussian fitting were applied to find the highest correlation. A cognitive experiment based on 93 emotional sounds was designed, and the EEG data of 10 volunteers were collected to verify the model. The 48-dimensional acoustic features and 428 EEG components were extracted and analyzed together. Through this method, the relationship between the EEG components and the acoustic features could be measured. Moreover, according to the temporal relations, an optimal offset of acoustic features was found, which could obtain better alignment with EEG features. After the regression analysis, the significant EEG components were found, which were in good agreement with cognitive laws. This provides a new idea for long-term EEG components, which could be applied in other correlative subjects.