International Journal of Applied and Advanced Multidisciplinary Research (IJAAMR)
Vol. 1 No. 1 (2023): September 2023

A Hybrid Acoustic And Deep Learning Approach For Enhanced Speech Emotion Recognition

Bharshankar, Gargi (Unknown)
Meenakshi Thalor (Unknown)

Article Info

Publish Date
29 Sep 2023

Abstract

Emotion recognition in speech is a key research topic in human-computer interaction. Understanding emotions in conversations can shed light on a person's well-being. This study introduces a hybrid architecture that combines acoustic and deep features for improved speech emotion recognition. Acoustic features like RMS energy and MFCC are extracted from voice records. Additionally, sound spectrogram images are processed using deep networks like VGG16 and ResNet to obtain deep features. These are merged into a hybrid feature vector, refined by the ReliefF algorithm. For classification, the Support Vector Machine is employed. Testing on datasets like RAVDESS and EMO-DB yielded accuracy rates up to 90.21%. Our method consistently outperformed existing techniques in accuracy.

Copyrights © 2023




Citation Download
RIS
EndNote, Reference Manager, ProCite
BibTex
Latex, Jabref
Original Source
Download Original
Google Scholar
Check in Google Scholar
Journal Info
International Journal of Applied and Advanced Multidisciplinary Research (IJAAMR)
Website

Abbrev

ijaamr

Publisher

MULTITECH PUBLISHER

Subject

Humanities Civil Engineering, Building, Construction & Architecture Economics, Econometrics & Finance Education Social Sciences

Description

International Journal of Applied and Advanced Multidisciplinary Research (IJAAMR) is a multidisciplinary journal that publishes high quality research papers in the areas of Business Management, Agriculture, Information Technology, Engineering, Health & Life Science, Zoology, Humanities, Applied ...