Beta
ManageSearchChatDiscover
254979

A Deep Learning Approach for Gloss Sign Language Translation using Transformer

Article

Last updated: 24 Dec 2024

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

One of the most recent applications of machine learning is to translate sign language into natural language. Many studies have attempted to classify sign language based on whether it is gesture or facial expression. These efforts, however, ignore genuine sentences' linguistic structure and context. The quality of traditional translation methods is poor, and their underlying models are not salable. They also take a long time to complete. The contribution of this paper is that it suggests utilizing a transformer to perform bidirectional translation using a deep learning approach. The proposed models experiment on the ASLG-PC12 corpus. The experimental results reveal that the proposed models outperform other approaches to the same corpus in both directions of translation, with ROUGE and BLEU  scores of  98.78% and 96.89%, respectively, when translating from text to gloss. Additionally, the results indicate that the model with two layers achieves the best result with ROUGE and BLEU scores of  96.90% and 84.82% when translating from gloss to text.

DOI

10.21608/jocc.2022.254979

Keywords

neural machine translation, Sequence to Sequence Model, Sign Language, Deep learning, Transformer

Authors

First Name

Ammar

Last Name

Mohamed

MiddleName

-

Affiliation

Faculty of Graduate Studies for Statistical Research Cairo University

Email

ammar@cu.edu.eg

City

-

Orcid

-

First Name

Hesham

Last Name

Hefny

MiddleName

-

Affiliation

Department of Computer Science, Faculty of Graduate Studies for Statistical Research, Cairo University

Email

dramamcu@gmail.com

City

-

Orcid

-

First Name

mohamed

Last Name

Amin

MiddleName

-

Affiliation

Department of Computer Science, Faculty of Graduate Studies for Statistical Research, Cairo University, Cairo, Egypt

Email

mohamed.amin@cu.edu.eg

City

-

Orcid

-

Volume

1

Article Issue

2

Related Issue

36206

Issue Date

2022-08-01

Receive Date

2022-04-27

Publish Date

2022-08-15

Page Start

1

Page End

8

Online ISSN

2636-3577

Article File

JOCC_Volume 1_Issue 2_Pages 1-8.pdf

PDF . 676.2kB

Link

https://jocc.journals.ekb.eg/article_254979.html

Detail API

https://jocc.journals.ekb.eg/service?article_code=254979

Order

1

Type

Original Article

Type Code

731

Publication Type

Journal

Publication Title

Journal of Computing and Communication

Publication Link

https://jocc.journals.ekb.eg/

MainTitle

A Deep Learning Approach for Gloss Sign Language Translation using Transformer

Details

Type

Article

Created At

22 Jan 2023