EMOTION RECOGNITION THROUGH DEEP LEARNING IN VARIOUS MODES
Abstract
The man-machine interface encompasses a crucial area—emotion recognition through facial expressions. Despite its significance, emotion recognition faces challenges such as facial accessories, non- uniform illuminations, pose variations, audio speeches, text conversations, and hand and facial gestures. Understanding emotions like happiness, anger, anxiety, joy, and shock, along with their varying degrees and overlaps, is essential for accurate recognition. These nuances, inherent to humans, pose difficulties and costs in achieving standard results through facial recognition. Recognizing someone’s mood through facial expression, conversation, voice modulation, and gestures is a skill humans excel at. However, replicating this ability through facial recognition has proven challenging and costly. This paper addresses these challenges by proposing diverse approaches to emotion detection. By exploring various modes, including facial expressions, conversation analysis, voice modulation, and gestures, the paper tackles current research problems and holds practical applications in public experiments and exhaustive sentiment analysis. The paper presents a good combo of various modes of emotion recognition on multiple datasets (tried and tested widely before amalgamating all to produce an excellent optimal result as an output of the model).

Authors
Bharat Gupta, Manas Gupta
Ministry of Electronics and Information Technology, Government of India, India, Indian Institute of Technology Banaras Hindu University, Varanasi, India

Keywords
FER, ASR, MFCC, Multimodal Deep Learning
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
000000084600
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 15 , Issue: 1 , Pages: 3392 - 3399 )
Date of Publication :
July 2024
Page Views :
103
Full Text Views :
18

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.