Nara proposes AI voice control for an accessible metaverse

AI system

System: Nara's proposed AI voice-control function for a metaverse and Braille interface
Model: Not assessed
Release: Not assessed
Application developer: Humanities Artificial Intelligence Research Center of Nara Knowledge Information Co.
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: The patent proposes a deep-learning speech-recognition model that converts spoken input from a Braille terminal into control of the computing device supporting the metaverse interface.
Human oversight: Not assessed
Relation to AI: Nara’s patent specifies deep-learning speech recognition for user control. Its use in the Blind Metaverse demo and effect on users remain unverified. The demo also integrates Google Cloud speech synthesis, but the exact Korean Standard voice model is unverified.
AI contribution: Not assessed

Outcome identifiers: Not assessed
Benefit: Nara's patent specifies AI voice control for an accessible metaverse. The Blind Metaverse demo uses speech synthesis; deployment of the patented speech recognition is unverified.
Category: Improved Accessibility
Status: Intended benefit
Beneficiary groups: People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Participants: Developer: Humanities Artificial Intelligence Research Center of Nara Knowledge Information Co.
Jurisdictions: Benefit: South Korea.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: The proposed design requires speech recognition, compatible audio input and Braille interfaces, and integration with the virtual environment. Conditions sufficient to improve access remain unknown.
Replication attempts: Not assessed
Later findings: Not assessed
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People.
Depth: Not assessed
Reasons: People: Blind users are intended to navigate virtual spaces through spoken commands and tactile interfaces. Effects on access and independence remain unverified.
Observed or intended: Intended benefit
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The makers' claim

Kind: Not assessed
Related entries: Not assessed
Field: Accessibility.
Purpose: Use AI speech recognition to provide blind users with voice control of an accessible virtual environment.
Dates: Source information as of: June 2025. Updated: 22 October 2026.
Stage: Not assessed
Version: SHA-256: 53d42b9ffbbd…