This paper proposes a novel method for speech emotion recognition. Empirical mode decomposition (EMD) isapplied in this paper for the extraction of emotional features from speeches, and a deep neural network (DNN)is used to classify speech emotions. This paper enhances the emotional components in speech signals by usingEMD with acoustic feature Mel-Scale Frequency Cepstral Coefficients (MFCCs) to improve the recognition ratesof emotions from speeches using the classifier DNN. In this paper, EMD is first used to decompose the speechsignals, which contain emotional components into multiple intrinsic mode functions (IMFs), and then emotionalfeatures are derived from the IMFs and are calculated using MFCC. Then, the emotional features are used to trainthe DNN model. Finally, a trained model that could recognize the emotional signals is then used to identify emotionsin speeches. Experimental results reveal that the proposed method is effective.
%0 Journal Article
%1 sttzer2009lernen
%A Shing-Tai Pan, Ching-Fa Chen, Chuan-Cheng Hong
%C Kassel
%D 2022
%E Publishers, BOHR
%J BOHR International Journal of Internet of things,Artificial Intelligence and Machine Learning
%K emotion recognition speech
%N 2
%P 1-10
%R 10.54646/bijiam.2023.11
%T Emotion Recognition Based on Speech Signals by Combining Empirical Mode Decomposition and Deep Neural Network
%V 2
%X This paper proposes a novel method for speech emotion recognition. Empirical mode decomposition (EMD) isapplied in this paper for the extraction of emotional features from speeches, and a deep neural network (DNN)is used to classify speech emotions. This paper enhances the emotional components in speech signals by usingEMD with acoustic feature Mel-Scale Frequency Cepstral Coefficients (MFCCs) to improve the recognition ratesof emotions from speeches using the classifier DNN. In this paper, EMD is first used to decompose the speechsignals, which contain emotional components into multiple intrinsic mode functions (IMFs), and then emotionalfeatures are derived from the IMFs and are calculated using MFCC. Then, the emotional features are used to trainthe DNN model. Finally, a trained model that could recognize the emotional signals is then used to identify emotionsin speeches. Experimental results reveal that the proposed method is effective.
@article{sttzer2009lernen,
abstract = {This paper proposes a novel method for speech emotion recognition. Empirical mode decomposition (EMD) isapplied in this paper for the extraction of emotional features from speeches, and a deep neural network (DNN)is used to classify speech emotions. This paper enhances the emotional components in speech signals by usingEMD with acoustic feature Mel-Scale Frequency Cepstral Coefficients (MFCCs) to improve the recognition ratesof emotions from speeches using the classifier DNN. In this paper, EMD is first used to decompose the speechsignals, which contain emotional components into multiple intrinsic mode functions (IMFs), and then emotionalfeatures are derived from the IMFs and are calculated using MFCC. Then, the emotional features are used to trainthe DNN model. Finally, a trained model that could recognize the emotional signals is then used to identify emotionsin speeches. Experimental results reveal that the proposed method is effective.},
added-at = {2024-05-18T11:37:48.000+0200},
address = {Kassel},
author = {{Shing-Tai Pan, Ching-Fa Chen}, Chuan-Cheng Hong},
biburl = {https://www.bibsonomy.org/bibtex/2f3e07a99bab2442fd343fccb147b161d/bijiamjournal},
doi = {10.54646/bijiam.2023.11},
editor = {Publishers, BOHR},
groups = {public},
interhash = {a9248f25ecfdafe332fa9f69491eac34},
intrahash = {f3e07a99bab2442fd343fccb147b161d},
journal = {BOHR International Journal of Internet of things,Artificial Intelligence and Machine Learning},
keywords = {emotion recognition speech},
number = 2,
pages = {1-10},
school = {University of Kassel},
timestamp = {2024-05-18T11:39:48.000+0200},
title = {Emotion Recognition Based on Speech Signals by Combining Empirical Mode Decomposition and Deep Neural Network},
type = {Master Thesis},
username = {dbenz},
volume = 2,
year = 2022
}