A primary challenge for the Deaf community stems from the communication gaps with the hearing society, which can greatly impact their daily lives and result in social exclusion. To foster inclusivity in society, our endeavor focuses on developing a cost-effective, resource-efficient, and open technology based on Artificial Intelligence (AI), with a particular focus on American Sign Language (ASL). The main scientific contributions of this paper are: the collection and open release of a new high-quality dataset for ASL alphabet classification, an extensive comparative study of several deep learning models for addressing this task, together with the release of the code for promoting reproducibility, and a real-time computer-vision web-based system designed to assist people in learning and using the ASL alphabet signs. The overall analysis presented in this paper intends to enrich the recent scientific literature on sign language solutions based on AI, which can lay the groundwork for future innovations.