An AI-driven, wearable, conformal ring system for real-time and user-independent sign language interpretation.

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: 88.3% accuracy for American Sign Language, 88.5% for International Sign Language

• Primary Outcome: Recognition accuracy for sign language word translation

• Nnt Or Sensitivity: Sensitivity and specificity for individual gestures not reported

• Confidence Interval: Not reported

Clinical Application

Requires further validation for clinical deployment, cost-effectiveness analysis, and integration with healthcare communication systems Could support Auslan (Australian Sign Language) users in healthcare settings, potentially relevant for NDIS assistive technology funding, requires TGA evaluation for medical device classification Deaf and hard-of-hearing individuals, healthcare workers, interpreters, and family members requiring sign language communication support

Abstract

Sign language translation systems have long aimed to bridge the communication between signers and nonsigners. However, preliminary systems rely on glove-type wearables or wired sensor arrays, which constrain hand movement, reduce comfort, and require nonpersonalized sensor positions that limit adaptability across users. Here, we introduce a wirelessly connected, ring-type sign language translator (WRSLT) designed to overcome these limitations by enabling full finger mobility through independent sensor rings and multilink communication. The system supports static and dynamic gesture detection using selected fingers via quantitative relevance analysis and achieves robust user-independent performance without per-user calibration. WRSLT demonstrated high recognition accuracy on large-scale datasets comprising 100 American Sign Language and 100 International Sign Language words, achieving 88.3 and 88.5% accuracy, respectively, under unseen-user conditions (i.e., test users not included in model training). Furthermore, a custom sequential word detection framework enables sentence-level translation from continuous signing input without requiring separate training on entire sentence structures.

References

1. 1.Park, J., Shin, Y., Min, I. S., Lee, Y., Lee, J., Hong, J. H., Park, S., Park, S. H., Baek, J., Kim, T., Kim, K., Kim, D., Park, Y., Kim, J., Cho, Y. U., Choi, Y., Jeon, B., Kang, K., Hwang, D., & Yu, K. J. (2026). An AI-driven, wearable, conformal ring system for real-time and user-independent sign language interpretation. Science Advances. https://doi.org/10.1126/sciadv.aec8995