INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Comparative Study of Classification Models for Emotion Detection from Speech
Authors Name:
Shibraj Basak
, Prolay Ghosh
Unique Id:
IJSDR2303133
Published In:
Volume 8 Issue 3, March-2023
Abstract:
The detection of emotions from speech is the aim of this paper. Speech consists of anger, joy and fear have very high and wide range in pitch, whereas Speech consists of sad and tired emotion have very low pitch. Speech Emotion detection technology can recognize human emotions to help machines better for understanding intentions of a user to improve the human-computer interaction. Classification models named Convolutional Neural Network (CNN), Support Vector Machine (SVM), Multilayer Perceptron (MLP) based on mainly Mel Frequency Cepstral Coefficient (MFCC) feature to detect emotion have been presented here. The models have been trained to distinguish eight different emotions such as calm, neutral, angry, sad, happy, disgust, fear, surprise. The proposed work shows that CNN works best on RAVDESS dataset rather than MLP, SVM and records an accuracy of 63.88%.
"Comparative Study of Classification Models for Emotion Detection from Speech", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 3, page no.837 - 840, March-2023, Available :http://www.ijsdr.org/papers/IJSDR2303133.pdf
Downloads:
000337072
Publication Details:
Published Paper ID: IJSDR2303133
Registration ID:204593
Published In: Volume 8 Issue 3, March-2023
DOI (Digital Object Identifier): http://doi.one/10.1729/Journal.33564
Page No: 837 - 840
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn