Deep Residual Local Feature Learning for Speech Emotion Recognition
Preprint
Abstract
Speech Emotion Recognition (SER) is becoming a key role in global business today to improve service efficiency, like call center services. Recent SERs were based on a deep learning approach. However, the efficiency of deep learning depends on the number of layers, i.e., the deeper layers, the higher efficiency. On the other hand, the deeper layers are causes of a vanishing gradient problem, a low learning rate, and high time-consuming. Therefore, this paper proposed a redesign of existing local feature learning block (LFLB). The new design is called a deep residual local feature learning block (DeepResLFLB). DeepResLFLB consists of three cascade blocks: LFLB, residual local feature learning block (ResLFLB), and multilayer perceptron (MLP). LFLB is built for learning local correlations along with extracting hierarchical correlations; DeepResLFLB can take advantage of repeatedly learning to explain more detail in deeper layers using residual learning for solving vanishing gradient and reducing overfitting; and MLP is adopted to find the relationship of learning and discover probability for predicted speech emotions and gender types. Based on two available published datasets: EMODB and RAVDESS, the proposed DeepResLFLB can significantly improve performance when evaluated by standard metrics: accuracy, precision, recall, and F1-score.Keywords
All Related Versions
- Version 1, 2020-11-19, ArXiv
- Published version: , 241.
This publication has 21 references indexed in Scilit:
- Implementation of wavelet packet transform and non linear analysis for emotion classification in stroke patient using brain signalsBiomedical Signal Processing and Control, 2017
- RETRACTED ARTICLE: Application of fuzzy C-means clustering algorithm to spectral features for emotion classification from speechNeural Computing and Applications, 2016
- On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks2016
- Identity Mappings in Deep Residual Networks2016
- Weighted spectral features based on local Hu moments for speech emotion recognitionBiomedical Signal Processing and Control, 2015
- Automatic analysis of speech F0 contour for the characterization of mood changes in bipolar patientsBiomedical Signal Processing and Control, 2015
- Detection of emotions in Parkinson's disease using higher order spectral features from brain's electrical activityBiomedical Signal Processing and Control, 2014
- Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011Artificial Intelligence Review, 2012
- Acoustic feature selection and classification of emotions in speech using a 3D continuous emotion modelBiomedical Signal Processing and Control, 2011
- Study of empirical mode decomposition and spectral analysis for stress and emotion classification in natural speechBiomedical Signal Processing and Control, 2011