Speech Emotion Recognition Using Deep Learning

Speech Emotion Recognition Using Deep Learning
Author(s):
Jennifer C Saldanha, Rohan Pinto
Keywords:
Speech Emotion Recognition, Mel Frequency Cepstral Coefficients, Convolutional Neural Network, Long Short Time Memory, Deep Belief Network, Recurrent Neural Network
Abstract
Speech emotion recognition a space-growing analysis domain in recent years. Unlike humans, machines lack the skills to understand and show emotions, however, human-machine interactions are often improved by automatic emotion recognition, thereby reducing the necessity of human intervention. An SER system is a group of techniques for classifying and processing speech signals in order to find any embedded emotions. In this work, the RAVDEES database for speech emotion recognition is selected from Kaggle. The MFCC feature is extracted. Deep learning algorithm, CNN is used which classifies the extracted relevant MFCC features of speech signals which are used and recognizes the emotion. The speech emotion recognition system eases the identification of the speaker’s emotion and mental status. CNN model implemented in this work can recognize the emotional state of the speaker. The project achieved training accuracy of 96% and testing accuracy of 85%. This results in an accurate identification of the emotion.
Article Details
Unique Paper ID: 160727 Publication Volume & Issue: Volume 10, Issue 1 Page(s): 1155 - 1161
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org