Context-Aware Voice Command Filtering for Multi-Input Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users experience frustration and inefficiency due to unintended voice commands being interpreted by systems while using multi-input techniques, such as voice and stylus or keyboard input, leading to unintended actions.
Innovation Solution
Implementing a method to detect voice input and determine if it corresponds to an enabled voice command, identifying the command's association with a specific application and characteristic, and performing the intended action only when the voice input matches both criteria, thereby distinguishing between intended commands and casual speech.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system continuously monitors all voice input to distinguish intended commands from casual speech, then accuracy of command recognition is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by continuously monitoring voice input characteristics and maintaining readiness states without fully processing every voice input as a potential command. This allows the system to quickly identify when voice input warrants full command processing versus when it can be dismissed as casual speech, improving accuracy without proportionally increasing processing time for all inputs.
2Reliability
If the system requires multiple criteria matching (enabled command status and characteristic matching) before executing voice commands, then reliability of command execution is improved, but device complexity increases
Solution Approach 1:
The system segments the voice command recognition process into distinct evaluation stages: first checking if the voice input corresponds to a known command structure, then checking if that command is currently enabled, and finally checking if voice characteristics match predetermined criteria. This segmentation allows each criterion to be evaluated independently with simple binary decisions, improving overall reliability without creating excessive system complexity.
3Object-affected harmful factors
If the system disables voice commands during certain input modes to prevent unintended actions, then error reduction is improved, but ease of operation decreases
Solution Approach 1:
The system dynamically adjusts voice command enablement based on current operational context and detected input patterns. Rather than permanently disabling voice commands in certain modes, the system monitors for characteristics of intended versus unintended voice input and selectively enables or disables command recognition in real-time. This dynamic approach reduces unintended actions while preserving input flexibility when voice input is genuinely intended.
Data Source
AI summary
One embodiment provides a method, including: detecting, at an input device of an information handling device, voice input; determining, using a processor, whether the voice input corresponds to a voice command; identifying, responsive to determining that the voice input corresponds to a voice command, that the voice command is associated with an enabled voice command; determining, using a processor, whether a characteristic of the voice command corresponds to a predetermined input characteristic; and performing, responsive to identifying that the voice command is associated with the enabled voice command and responsive to determining that the characteristic corresponds to the predetermined input characteristic, an action corresponding to the enabled voice command. Other aspects are described and claimed.