Speech emotion recognition based on improved masking EMD and convolutional recurrent neural network

Abstract

Speech emotion recognition (SER) is the key to human-computer emotion interaction. However, the nonlinear characteristics of speech emotion are variable, complex, and subtly changing. Therefore, accurate recognition of emotions from speech remains a challenge. Empirical mode decomposition (EMD), as an effective decomposition method for nonlinear non-stationary signals, has been successfully used to analyze emotional speech signals. However, the mode mixing problem of EMD affects the performance of EMD-based methods for SER. Various improved methods for EMD have been proposed to alleviate the mode mixing problem. These improved methods still suffer from the problems of mode mixing, residual noise, and long computation time, and their main parameters cannot be set adaptively. To overcome these problems, we propose a novel SER framework, named IMEMD-CRNN, based on the combination of an improved version of the masking signal-based EMD (IMEMD) and convolutional recurrent neural network (CRNN). First, IMEMD is proposed to decompose speech. IMEMD is a novel disturbance-assisted EMD method and can determine the parameters of masking signals to the nature of signals. Second, we extract the 43-dimensional time-frequency features that can characterize the emotion from the intrinsic mode functions (IMFs) obtained by IMEMD. Finally, we input these features into a CRNN network to recognize emotions. In the CRNN, 2D convolutional neural networks (CNN) layers are used to capture nonlinear local temporal and frequency information of the emotional speech. Bidirectional gated recurrent units (BiGRU) layers are used to learn the temporal context information further. Experiments on the publicly available TESS dataset and Emo-DB dataset demonstrate the effectiveness of our proposed IMEMD-CRNN framework. The TESS dataset consists of 2,800 utterances containing seven emotions recorded by two native English speakers. The Emo-DB dataset consists of 535 utterances containing seven emotions recorded by ten native German speakers. The proposed IMEMD-CRNN framework achieves a state-of-the-art overall accuracy of 100% for the TESS dataset over seven emotions and 93.54% for the Emo-DB dataset over seven emotions. The IMEMD alleviates the mode mixing and obtains IMFs with less noise and more physical meaning with significantly improved efficiency. Our IMEMD-CRNN framework significantly improves the performance of emotion recognition.

Facial and speech Emotional Recognition based on Improved Deep Model

“…The creators stack two parallel CNNs to speak to spatial highlights in parallel with a change encoder to speak to transient highlights, in this manner at the same time extending the channel profundity and reducing the include outline by expressive progressive highlight representation with less computational cost. To overcome the issues, in [22] proposed a modern SER system, called IMEMD-CRNN, based on the combination of an progressed adaptation of envelope signal-based EMD (IMEMD) and convolutional repetitive neural organize (CRNN). To begin with, IMEMD is proposed for discourse parsing.…”

Research on the Strong Generalization of Coal Gangue Recognition Technology Based on the Image and Convolutional Neural Network under Complex Conditions

“…Since 2012, the convolutional neural network has made major breakthroughs in the field of image recognition, and its recognition capabilities have surpassed humans . Therefore, the convolutional neural network is also widely used in emotion classification, , speech recognition, , agricultural engineering, , defect detection, fault diagnosis, and other fields and has made significant breakthroughs and improvements. Taking coal gangue recognition as an example, the convolutional neural network has been widely used and has achieved important research results.…”

Engineering archive management model based on big data analysis and deep learning model

“…Data are transitional electronic documents where documentary information can be stored in a medium and the corresponding electronic device identifies the physical symbol, a new form of representation of data, facts, concepts or instructions [13][14][15]. With the development of computer and network technology, data and information processing has improved efficiency and convenience [16].…”