Lip-reading Session Triggering for Secure Data Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices face challenges in efficient data entry due to limited form factor and environmental noise interference, which can compromise sensitive information when using voice recognition technology.
Innovation Solution
Implementing lip-reading capabilities in computing devices to automatically initiate a lip-reading session based on triggering events, such as ambient noise or geographic location, allowing users to input data visually without audible speech, and personalizing the device using machine learning for improved accuracy and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If voice recognition technology is used for data entry, then user interaction efficiency is improved, but security of sensitive information is compromised
Solution Approach 1:
The patent introduces lip-reading technology as an intermediary between the user and the digital assistant. Instead of directly capturing audible speech, the system captures visual lip movements through a camera and processes them to generate text input. This intermediary approach maintains the convenience of voice-like interaction while eliminating the security risk of audible speech capture in sensitive situations
2Ease of operation
If voice recognition is used in noisy environments, then data entry capability is maintained, but accuracy and reliability deteriorate
Solution Approach 1:
The patent replaces the acoustic-based voice recognition system with a visual-based lip-reading system. Instead of relying on audio signals that are susceptible to noise interference, the system uses visual information from camera captures to detect and process lip movements. This substitution fundamentally changes the sensing modality from acoustic to optical, thereby eliminating noise-related reliability issues
3Ease of operation
If automatic triggering of lip-reading session is implemented, then user interaction seamlessness is improved, but device complexity increases
Solution Approach 1:
The patent implements automatic triggering mechanisms that enable the system to self-manage lip-reading session initiation and termination based on contextual cues. The device monitors environmental noise levels, detects sensitive information keywords, and automatically activates or deactivates lip-reading mode without requiring explicit user commands. This self-service approach maintains operational simplicity while managing the underlying complexity through automated decision-making algorithms
Data Source
AI summary
Techniques for lip-reading session triggering events are described. A computing device is equipped with lip-reading capability that enables the device to “read the lips” (i.e., facial features) of a user. The computing device determines when a triggering event occurs to automatically cause the computing device to switch from one input type to a lip-reading session. Lip-reading is also used in conjunction with other types of inputs to improve accuracy of the input. Machine learning is used to personalize the lip-reading capability of the computing device for a particular user.