Bidirectional Sign Language Communication Based on Variational and Adversarial Learning

22 Pages Posted: 20 Mar 2023

See all articles by Qinkun Xiao

Qinkun Xiao

Xi’an Technological University

Lu Li

Xi’an Technological University

Yilin Zhu

Xi’an Technological University

Abstract

Most studies on sign language recognition (SLR) focus on deaf-to-hearing communication, while hearing-to-deaf communication, which can be realized through sign language generation (SLG), has been largely ignored. To address this issue, this paper combines SLR with SLG to construct a skeletonbased bidirectional sign language communication framework. In the SLR stage, a bidirectional long short-term memory (BiLSTM) network is used for the sign language skeleton sequence classifier. In the SLG stage, a novel sign language skeleton sequence generator called SeqαGAN is proposed. Based on variational and adversarial learning, SeqαGAN produces a more flexible posterior distribution and diverse human-recognizable data. The generated samples can be used for data argumentation and improving classifier performance. A series of tests are conducted on three datasets, and the evaluation results indicate that the skeleton-based bidirectional communication framework is effective.

Keywords: SLR, SLG, generation, recognition, bidirectional communication

Suggested Citation

Xiao, Qinkun and Li, Lu and Zhu, Yilin, Bidirectional Sign Language Communication Based on Variational and Adversarial Learning. Available at SSRN: https://ssrn.com/abstract=4383371 or http://dx.doi.org/10.2139/ssrn.4383371

Qinkun Xiao (Contact Author)

Xi’an Technological University ( email )

Lu Li

Xi’an Technological University ( email )

Yilin Zhu

Xi’an Technological University ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
56
Abstract Views
246
Rank
807,872
PlumX Metrics