Beta
ManageSearchChatDiscover
103754

Quality Evaluation of Reverberant Speech Based on Deep Learning

Article

Last updated: 04 Jan 2025

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

This paper presents an efficient approach for classification of speech signals as reverberant or not. The reverberation is a severe effect encountered in closed room. So, it may affect subsequent processes and deteriorate speech processing system performance. The spectrograms are utilized as images generated from speech signals to be classified with deep convolutional neural networks. Spectrogram and MFCC are used as features to be classified with Long Short Term Recurrent Neural Network (LSTM RNN). Two models are presented and compared. Simulation results up to 100% classification accuracy are obtained. This can help in perform an initial step in any speech processing system that comprises quality level classification.

DOI

10.21608/mjeer.2020.103754

Authors

First Name

Samia

Last Name

Abd El-Moneim

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

Mahmoud

Last Name

Saied

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

M. A.

Last Name

Nassar

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

Moawad I.

Last Name

Dessouky

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

N.

Last Name

Ismail

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

Adel

Last Name

Saleeb

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

aasaleeb@hotmail.com

City

-

Orcid

-

First Name

Adel S.

Last Name

El-Fishawy

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

First Name

Fathi E.

Last Name

Abd El-Samie

MiddleName

-

Affiliation

Electronics and Electrical Communications Engineering Department, Faculty of Electronic Engineering, Menouf 32951, Menoufia University.

Email

-

City

-

Orcid

-

Volume

29

Article Issue

2

Related Issue

15327

Issue Date

2020-07-01

Receive Date

2020-07-19

Publish Date

2020-07-01

Page Start

126

Page End

132

Print ISSN

1687-1189

Online ISSN

2682-3535

Article File

MJEER_Volume 29_Issue 2_Pages 126-132.pdf

PDF . 1.2MB

Link

https://mjeer.journals.ekb.eg/article_103754.html

Detail API

https://mjeer.journals.ekb.eg/service?article_code=103754

Order

11

Type

Original Article

Type Code

1,088

Publication Type

Journal

Publication Title

Menoufia Journal of Electronic Engineering Research

Publication Link

https://mjeer.journals.ekb.eg/

MainTitle

Quality Evaluation of Reverberant Speech Based on Deep Learning

Details

Type

Article

Created At

22 Jan 2023