Research on Speech Emotion Recognition Analysis Based on Deep Learning

Authors

  • Chunhao Li
  • Ailiang Yin

DOI:

https://doi.org/10.54097/nkzgwh08

Keywords:

Human-computer emotional interaction, Preprocessing, Speech emotion recognition.

Abstract

 Speech is a common way of communication in human daily life, which is very natural and easy to understand. In the process of communication, one will also express their emotions to the other party. Through emotional expression, the distance between people is smaller and communication is more convenient. Speech emotion recognition is also the key to human-computer emotional interaction, and effective recognition of speech emotions can improve speech intelligibility. The number of speech datasets is usually large, with several G or even larger. This article proposes a method of preprocessing the speech dataset to extract feature data folders, and then using the feature data folder directory as input to train the model. This method helps to improve the efficiency, repeatability, and manageability of data processing.

Downloads

Download data is not yet available.

References

Zhang Shiqing, Zhao Zhijin, Dai Yuliang, etc Research on the Application of Support Vector Machine in Speech Emotion Recognition [J] Acoustic Technology, 2008, 27 (1): 87-90 ZHANG Shiqing, ZHAO Zhijin, DAI Yuliang, et al. A study of support vector machine for speech emotion recognition [J] Technical Acoustics, 2008, 27 (1): 87-90.

Tao Huawei Research on Several Issues of Speech Emotion Recognition Based on Spectral Features [D] Nanjing: Southeast University, 2017.

HINTON G E. Reducing the dimensionality of data with neural networks [J] Science, 2006, 313 (5786): 504-507. DOI: https://doi.org/10.1126/science.1127647

Zhou Yongdong, Zhang Yun, Cao Yanrong, etc Emotional Analysis Based on Feature Fusion Segmented Convolutional Neural Networks [J] Computer Engineering and Design, 2019, 40 (10): 3009-3013, 3029 Zhou Yongdong, ZHANG Yun, CAO Yanrong, et al. Sentiment analysis based on pipeline convolutional neural network combined with features [J] Computer Engineering and Design, 2019, 40 (10): 3009-3013, 3029.

MAO Q R, DONG M, HUANG Z W, et al. Learning salient features for speech emotion recognition using convolutional neural networks [J] IEEE Transactions on Multimedia, 2014, 16 (8): 2203-2213. DOI: https://doi.org/10.1109/TMM.2014.2360798

ZHANG S Q, ZHANG S L, HUANG T J, et al. Speech emotion recognition using deep convolutional neural network and discriminative temporary pyramid matching [J] IEEE Transactions on Multimedia, 2018, 20 (6): 1576-1590. DOI: https://doi.org/10.1109/TMM.2017.2766843

CHEN M Y, HE X J, YANG J, et al. 3-D convolutional recurrent neural networks with attention model for speech emotion recognition [J] IEEE Signal Processing Letters, 2018, 25 (10): 1440-1444. DOI: https://doi.org/10.1109/LSP.2018.2860246

Burkhardt F, Paeschke A, Rolves M, et al. A database of German emotional speech [C] INTERSPEECH, Lisbon, 2005: 1517-1520. DOI: https://doi.org/10.21437/Interspeech.2005-446

Chen Weiliang, Sun Xiao Speech emotion recognition based on MFCCG-PCA [J]. Journal of Peking University (Natural Science Edition), 2015, 51 (2): 269-274. CHEN Weiliang, SUN Xiao Mandarin speech emotion recognition based on MFCCG-PCA [J] Acta Scientiarum Naturalium University Pekinensis, 2015, 51 (2): 269-274.

Hann (Hanning) window - MATLAB Hann Www.mathworks.com. Retrieved 2020-02-12.

SIDDIQI M H. An improved Gaussian mixture hidden conditional random fields model for audio based emotions classification [J] Egyptian Informatics Journal, 2020,22 (1): 45-51. DOI: https://doi.org/10.1016/j.eij.2020.03.001

GERAVANCIZADEH M, FOROUHANDEH E, BASHIRPOUR M. Feature compensation based on the normalization of vocal tract length for the improvement of emotion ⁃ affected speech recognition [J] EURASIP Journal on Audio Speech and Music Processing, 2021 (1): 2-19. DOI: https://doi.org/10.1186/s13636-021-00216-5

KE X, ZHU Y, WEN L, et al. Speech emotion recognition based on SVM and ANN [J] International Journal of Machine Learning and Computing, 2018,8 (3): 198-202. DOI: https://doi.org/10.18178/ijmlc.2018.8.3.687

Pan Guozhuang. Research on rapid monitoring of controller fatigue status based on real-time land air communication emotion recognition [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2020.

PAN Guozhuang Research on rapid monitoring of controller fatigue based on real time land air communication emotion recognition [D] Nanjing: Nanjing University of Aeronautics and Astronautics, 2020.

Han Wenjing, Li Haifeng, Ruan Huabin, et al. Review of research progress on speech emotion recognition [J]. Journal of Software, 2014,25 (1): 37-50. HAN Wenjing, LI Haifeng, RUAN Huabin, et al. Review on speech emotion recognition [J] Journal of Software, 2014,25 (1): 37-50.

Rumelhart D E, Hinton G E, Williams R J. Learning presentations by back propagating errors [J] Nature, 1986, 323 (6088): 533-536. DOI: https://doi.org/10.1038/323533a0

Hochreiter S, Schmidhuber J. Long short term memory [J]. European Calculation, 1997, 9 (8): 1735-1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735

DANPOL R, ALASDOON A, PRASAD P, et al. Speech emotion recognition using convolutional neural network and long short term memory [J] Multimedia Tools and Applications, 2020,79 (43/44): 32917-32934. DOI: https://doi.org/10.1007/s11042-020-09693-w

Hu Tingting, Feng Yaqin, Shen Lingjie, et al. LSTM speech emotion based feature selection based on attention mechanism [J]. Acoustic Technology, 2019,38 (4): 414-421. HU Tingting, FENG Yaqin, SHEN Lingjie, et al. Main feature selection of LSTM speech emotion based on attention mechanism [J] Technical Acoustics, 2019,38 (4): 414-421.

Downloads

Published

23-02-2024

Issue

Section

Articles