Short Sound Messages for Enhancing Digital Accessibility and Reducing Digital Divide

As digital services increasingly rely on visual and touch-based interaction, users with visual or motor impairments are often excluded from seamless access to information. Despite ongoing progress in assistive technologies, accessibility gaps persist across public and private contexts, limiting independent access to digital content. To address this issue, we investigate the potential of TISCODE, a sound-based system that employs Short Sound Messages (SSMs) to retrieve digital content. These audio cues enable passive interactions, allowing users to receive relevant information directly on their smartphones without visual scanning or physical input. TISCODE leverages generative AI to synthesize distinct audio messages and employs a dual-stage decoding pipeline to ensure reliable classification across varying acoustic conditions. We evaluate the application prototype across multiple smartphones and test environments: indoor, outdoor, and noisy. Preliminary results are promising and support the system’s suitability for real-world deployment. TISCODE represents a step toward inclusive, audio-driven interaction paradigms within the Internet of Audio Things (IoAuT), contributing to digital equity and accessible design.