期刊
CMC-COMPUTERS MATERIALS & CONTINUA
卷 67, 期 3, 页码 4039-4059出版社
TECH SCIENCE PRESS
DOI: 10.32604/cmc.2021.015070
关键词
Affective computing; one-dimensional dilated convolutional neural network; emotion recognition; gated recurrent unit; raw audio clips
资金
- National Research Foundation of Korea - Korean Government through the Ministry of Science and ICT [NRF-2020R1F1A1060659]
- 2020 Faculty Research Fund of Sejong University
Researchers have developed new techniques in emotion recognition field, utilizing one-dimensional convolutional neural network and bidirectional gated recurrent unit to improve emotion recognition accuracy. Their model achieved different recognition rates on three benchmark datasets.
Emotion recognition from speech data is an active and emerging area of research that plays an important role in numerous applications, such as robotics, virtual reality, behavior assessments, and emergency call centers. Recently, researchers have developed many techniques in this field in order to ensure an improvement in the accuracy by utilizing several deep learning approaches, but the recognition rate is still not convincing. Our main aim is to develop a new technique that increases the recognition rate with reasonable cost computations. In this paper, we suggested a new technique, which is a one-dimensional dilated convolutional neural network (1D-DCNN) for speech emotion recognition (SER) that utilizes the hierarchical features learning blocks (HFLBs) with a bi-directional gated recurrent unit (BiGRU). We designed a one-dimensional CNN network to enhance the speech signals, which uses a spectral analysis, and to extract the hidden patterns from the speech signals that are fed into a stacked one-dimensional dilated network that are called HFLBs. Each HFLB contains one dilated convolution layer (DCL), one batch normalization (BN), and one leaky_relu (Relu) layer in order to extract the emotional features using a hieratical correlation strategy. Furthermore, the learned emotional features are feed into a BiGRU in order to adjust the global weights and to recognize the temporal cues. The final state of the deep BiGRU is passed from a softmax classifier in order to produce the probabilities of the emotions. The proposed model was evaluated over three bench marked datasets that included the IEMOCAP, EMO-DB, and RAVDESS, which achieved 72.75%, 91.14%, and 78.01% accuracy, respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据