# Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspective

**Authors:** Danielle Bragg, Oscar Koller, Mary Bellard, Larwan Berke, Patrick Boudrealt, Annelies Braffort, Naomi Caselli, Matt Huenerfauth, Hernisa Kacorri, Tessa Verhoef, Christian Vogler, Meredith Ringel Morris  
**arXiv:** [1908.08597](https://arxiv.org/abs/1908.08597)  
**Date:** 2019-08-22  
**Summary page:** https://www.summarizepaper.com/en/paper/1908.08597v1/

## Key points

- Developing successful sign language recognition, generation, and translation systems requires expertise in various fields
- Existing research in this area often occurs in separate disciplinary silos
- A diverse group of experts came together for a two-day interdisciplinary workshop to address the challenges faced by the field
- The paper presents the results of that workshop and provides key background information overlooked by computer scientists
- It offers a review of the state-of-the-art in sign language recognition, generation, and translation systems
- Collaboration across different disciplines is needed to overcome existing limitations in this field
- Pressing challenges include improving accuracy and robustness of sign language recognition algorithms, enhancing naturalness and expressiveness in sign language generation systems, developing effective translation techniques between spoken languages and sign languages, addressing issues related to cultural sensitivity and inclusivity in system design, and promoting accessibility for individuals with hearing impairments
- Researchers are urged to prioritize user-centered design approaches that involve active participation from Deaf communities and consider their unique linguistic and cultural needs

## Summary

Developing successful sign language recognition, generation, and translation systems is a complex task that requires expertise in various fields such as computer vision, computer graphics, natural language processing, human-computer interaction, linguistics, and Deaf culture. However, existing research in this area often occurs in separate disciplinary silos and focuses on specific aspects of the sign language processing pipeline. To gain a comprehensive understanding of the current landscape and address the challenges faced by the field, a diverse group of experts came together for a two-day interdisciplinary workshop. This paper presents the results of that workshop and provides key background information that is often overlooked by computer scientists. It offers a review of the state-of-the-art in sign language recognition, generation, and translation systems. The interdisciplinary perspective highlights the need for collaboration across different disciplines to overcome the existing limitations in this field. The paper also identifies pressing challenges that need to be addressed. These challenges include improving accuracy and robustness of sign language recognition algorithms; enhancing naturalness and expressiveness in sign language generation systems; developing effective translation techniques between spoken languages and sign languages; addressing issues related to cultural sensitivity and inclusivity in system design; and promoting accessibility for individuals with hearing impairments. To encourage progress in this field, the paper concludes with a call to action for researchers working on sign language processing. It emphasizes the importance of interdisciplinary collaboration and knowledge sharing among researchers from different domains. The research community is urged to prioritize user-centered design approaches that involve active participation from Deaf communities and consider their unique linguistic and cultural needs. In summary, this paper provides an interdisciplinary perspective on sign language recognition, generation, and translation systems which highlights the need for collaboration across various fields to overcome existing limitations. By addressing pressing challenges identified during the workshop such as improving accuracy of algorithms or promoting accessibility for individuals with hearing impairments researchers can contribute towards developing more accurate, expressive culturally sensitive inclusive sign language processing systems catering to those needs.