Research on Speech Emotion Recognition Analysis Based on Deep Learning
DOI:
https://doi.org/10.54097/fcis.v3i1.6025Keywords:
Speech spectrogram, Residual network, Speech emotion recognitionAbstract
This paper combines two aspects of feature selection and building deep neural networks to carry out targeted research to improve recognition accuracy. Firstly, speech preprocessing techniques are introduced to extract the speech spectrogram and lay the foundation for building the speech emotion recognition network model study. The focus is on building a speech emotion recognition network model based on residual network improvement and comparing experiments with AlexNet model network and ResNet-18 network model.
Downloads
References
Hong Zhaogin,Wei Chenyang,Zhuang Yuan,Wang Ying,Wang Yiting,Zhao Li. Speech emotion recognition and personality analysis based on deep neural network[J]. Information Technology Research,2020,46(01):48-53.
Tao, H.W., Cha, C., Liang, R.Y., et al. A speech spectrogram feature extraction algorithm for speech emotion recognition. Journal of Southeast University (Natural Science Edition),2015,45(5):817-827.
Irsoy O, Cardie C. Deep recursive neural networks for compositionality in language[J]. Advances in neural information processing systems, 2014(3).2096-2104.
Shah A, Bhowmik T. A Comparative Study on MFCC and Fundamental Frequency Based Speech Emotion Classification[C]//International Conference on Distributed Computing and Internet Technology. springer, Cham, 2022: 173-184.
Han WJ, Li HF, Ruan HB, et al. A review of research advances in speech emotion recognition[J]. Journal of Software,2019,25(1):37-50.
Qiu Xue. Research on multimodal fusion for student emotion recognition and state analysis[D]. Supervisor: Li Mingyong. Chongqing Normal University,2021.
Gao L, Qi L, Chen E, et al. Discriminative multiple canonical correlation analysis for information fusion[J]. IEEE Transactions on Image Processing, 2017, 27(4): 1951-1965.
New T L, Foo S w, De Silva LC. Speech emotion recognition using hidden Markov models[J]. Speech communication, 2003, 41(4): 603-623.
Liu, Jingjing, Wu, Xiaofeng. Multimodal sentiment recognition and spatial annotation based on long and short term memory networks [J]. Journal of Fudan (Natural Science Edition),2020,59(05):565-574.
Chen Jia. Speech emotion recognition based on deep learning [D]. Nanjing University of Posts and Telecommunications, 2019. 000586.
