The project explored various models (3D Convolutional Neural Network (CNN), 2D CNN + LSTM, 2D CNN) to be used in an American Sign Language (ASL) classification project with video input. This model is deployed via an interactive graphical user interface so that the model acts as an educational tool for users.

This project leverages Artificial Intelligence (AI) to create an educational interface for users first learning ASL. The datasets chosen for this project were those of ethical origins and significant diversity. Existing ASL models have been shown to demonstrate bias through class imbalances and underrepresentation of minority populations. The datasets chosen and the augmentation performed through this project aimed to reduce these common biases. Ultimately, the educational model was created to best represent individuals of all backgrounds, genders, and ages. In integrating well-performing video classification models with balanced and diverse datasets, the implementation of this platform can yield significant, not-yet-achieved benefits to the Deaf community and to all ASL learners.

Interactive educational platforms for learning standardized material, such as new languages or academic topics, have become increasingly popular. However, ASL educational tools remain limited, despite the need for accessible and effective ASL learning resources. AI advancements in interactive educational applications have greatly improved their functionality and versatility. AI is a highly viable and appropriate approach to creating a tool for ASL learning. In translating between text-based languages, there is a simple and consistent mapping between corresponding words and phrases. ASL requires analysis of spatial and temporal features, making AI integration uniquely challenging. This project explores the limitations of ASL education, particularly in the context of interpreter supports and technology. Our project explores various AI models that can effectively promote ASL learning and provides experimental results for the implementation of various 2D CNNs. Our research prioritizes ethical considerations by carefully selecting datasets to minimize bias, ensuring that AI-driven ASL tools promote inclusivity and accuracy in sign language learning.