Open AccessA Review on Deep Learning Algorithms for Speech and Facial Emotion Recognition
Author(s) -
Charlyn Pushpa Latha,
M. Priya
Publication year - 2020
Publication title -
aptikom journal on computer science and information technologies
Language(s) - English
Resource type - Journals
eISSN - 2528-2425
pISSN - 2528-2417
DOI - 10.34306/csit.v1i3.55
Subject(s) - deep learning , artificial intelligence , computer science , convolutional neural network , deep belief network , restricted boltzmann machine , boltzmann machine , machine learning , artificial neural network , field (mathematics) , pattern recognition (psychology) , speech recognition , mathematics , pure mathematics
Deep Learning is the recent machine learning technique that tries to model high level abstractions in databy using multiple processing layers with complex structures. It is also known as deep structured learning,hierarchical learning or deep machine learning. The term “deep learning" indicates the method used in trainingmulti-layered neural networks. Deep Learning technique has obtained remarkable success in the field of facerecognition with 97.5% accuracy. Facial Electromyogram (FEMG) signals are used to detect the different emotionsof humans. Some of the deep learning techniques discussed in this paper are Deep Boltzmann Machine (DBM), DeepBelief Networks (DBN), Convolutional Neural Networks (CNN) and Stacked Auto Encoders respectively. This paperfocuses on the review of some of the deep learning techniques used by various researchers which paved the way toimprove the classification accuracy of the FEMG signals as well as the speech signals