Publications and Research
Document Type
Poster
Publication Date
12-4-2019
Abstract
Augmented Reality (AR) refers to the technologies that enhance the version of the physical environment with computer-generated sensory input such as sound and graphics overlaid on top of the user’s view of the real world. Artificial Intelligence (AI) studies how to make computer programs and machines "smart" and take decisions. Our research project focuses on exploring the Integration of AI in AR applications. Specifically, on using Speech Recognition or Natural Language Processing for controlling virtual AR objects and enhancing the human-computer interaction. It is obvious that integration of AI and AR is of great value. However, for developers, it is difficult to find the right tools to start building applications. We present an empirical study that compares currently available alternatives for creating voice-controlled systems. We compare several Speech Recognition services in terms of openness, usability, cost. We developed two applications to test these services, one that uses simple keyword-based voice commands and the second that uses more advances sentences. We present our experience while integrating these libraries/services with the game engine used to develop AR applications, and the services pros and cons.
Comments
This poster was presented at the 31st Semi-Annual Honors and Undergraduate Research Scholars Poster Presentation at New York City College of Technology, Dec. 4, 2019. Mentor: Benito Mendoza (Computer Engineering Technology).