Preprocessing signal for Speech Emotion Recognition

Abstract: In this paper, we introduce and study preprocessing signal for speech emotion recognition. The aim of our work is to get pure signal which is created by sampling the signal from speaker. The discrimination between speech and music waves was achieved. A good signal is obtained by using pre...

Full description

Saved in:
Bibliographic Details
Main Authors: Bashar M. Nema, Ahmed A. Abdul-Kareem
Format: Article
Language:English
Published: Mustansiriyah University 2018-07-01
Series:Al-Mustansiriyah Journal of Science
Subjects:
Online Access:http://mjs.uomustansiriyah.edu.iq/ojs1/index.php/MJS/article/view/48
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract: In this paper, we introduce and study preprocessing signal for speech emotion recognition. The aim of our work is to get pure signal which is created by sampling the signal from speaker. The discrimination between speech and music waves was achieved. A good signal is obtained by using preprocessing then it used for feature extraction. The files we used in this paper are wave-type for male, female and music have sample rate 48000, bit resolution is 16-bits and Mono channel. The Berlin dataset and RAVDESS dataset are used in this work.
ISSN:1814-635X
2521-3520