Sign language is mainly the method of communication among deaf people. Its essence is basically dependent on visual and gestural elements that are to be used effectively. Generating realistic and natural sequences of sign languages has been one of the major challenges in the fields of computer vision and natural language processing for a long time. This paper proposes a novel GAN-based model that shall solve the challenge. It employs adversarial training such that the cooperative generator and discriminator yield highly accurate sign language with a natural feel. Experimental evaluations attest that the GAN-based approach is superior to its conventional counterpart, considering the aspects of gesture accuracy and fluency besides overall visual quality. It’s a huge potential for innovation to revolutionize tools of communication with deaf people through seamless and easy interactions, and that might just start something in this regard for other future sign language technologies.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Enhancing Sign Language Generation Using Generative Adversarial Network: A Deep Learning Perspective

  • Pragya Tewari,
  • Karuna Gupta,
  • Anurag Singh Baghel

摘要

Sign language is mainly the method of communication among deaf people. Its essence is basically dependent on visual and gestural elements that are to be used effectively. Generating realistic and natural sequences of sign languages has been one of the major challenges in the fields of computer vision and natural language processing for a long time. This paper proposes a novel GAN-based model that shall solve the challenge. It employs adversarial training such that the cooperative generator and discriminator yield highly accurate sign language with a natural feel. Experimental evaluations attest that the GAN-based approach is superior to its conventional counterpart, considering the aspects of gesture accuracy and fluency besides overall visual quality. It’s a huge potential for innovation to revolutionize tools of communication with deaf people through seamless and easy interactions, and that might just start something in this regard for other future sign language technologies.