Multi-mode Guard for Voice Commands in Wearables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable computing devices with near-eye displays face challenges in implementing voice command systems that reduce false-positive detections while maintaining a user-friendly interface.
Innovation Solution
The device employs a multi-modal guard phrase that enables or disables speech commands based on different interface modes, using a single guard phrase to activate different speech commands in various UI states, and incorporates visual cues to inform users when speech commands are available.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a guard phrase is used to disable speech commands, then false-positive detections are reduced, but the interface complexity increases
Solution Approach 1:
A single guard phrase is used across multiple interface modes to enable speech commands, providing a universal trigger that works consistently regardless of the current mode. This reduces the need for multiple different guard phrases or complex configuration settings, thereby reducing interface complexity while maintaining reliability through consistent guard phrase-based activation.
2Reliability
If speech commands are disabled by default, then false-positive detections are reduced, but user convenience deteriorates
Solution Approach 1:
The system performs preliminary action by automatically enabling speech commands when the guard phrase is detected, without requiring users to manually configure or switch modes. This preliminary automatic activation based on guard phrase detection maintains reliability by keeping commands disabled until explicitly activated, while improving convenience by eliminating manual configuration steps.
3Measurement precision
If multiple guard phrases are used for different interface modes, then speech command accuracy is improved, but the device complexity increases
Solution Approach 1:
A single guard phrase serves multiple functions across different interface modes, eliminating the need for multiple mode-specific guard phrases. This universal guard phrase approach maintains speech command detection accuracy by providing consistent activation logic while reducing the complexity of the guard phrase system by using only one phrase instead of multiple.
Data Source
AI summary
Embodiments may be implemented by a computing device, such as a head-mountable display, in order to use a single guard phrase to enable different voice commands in different interface modes. An example device includes an audio sensor and a computing system configured to analyze audio data captured by the audio sensor to detect speech that includes a predefined guard phrase, and to operate in a plurality of different interface modes comprising at least a first and a second interface mode. During operation in the first interface mode, the computing system may initially disable one or more first-mode speech commands, and respond to detection of the guard phrase by enabling the one or more first-mode speech commands. During operation in the second interface mode, the computing system may initially disable a second-mode speech command, and to respond to the guard phrase by enabling the second-mode speech command.