Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorit...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-03, Vol.22 (6), p.2378
Main Authors: Aggarwal, Apeksha, Srivastava, Akshat, Agarwal, Ajay, Chahal, Nidhi, Singh, Dilbag, Alnuaim, Abeer Ali, Alhadlaq, Aseel, Lee, Heung-No
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Audio data
Datasets
Decision trees
Deep Learning
Emotion recognition
Emotions
Humans
machine learning
neural network
Neural networks
Neural Networks, Computer
Principal components analysis
Speech
speech emotion recognition
Speech recognition
Two dimensional models
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22062378