Voice Command Determination with Threshold and Repetition Logic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in accurately issuing voice commands for recording video or still images while engaging in activities like biking or driving, leading to delayed timing due to difficulty in uttering precise voice commands, especially when voice commands are complex and less frequently used.
Innovation Solution
A voice operation control device with a voice command determination unit that recognizes utterances and accepts voice commands based on a preset threshold, allowing for accurate determination and acceptance of voice commands even with lower recognition rates if detected multiple times within a predetermined period, ensuring timely recording.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a high recognition threshold is used for voice commands, then false recognition is reduced, but accurate voice commands with lower recognition rates are rejected, causing delayed recording
Solution Approach 1:
The system performs preliminary voice recognition attempts before final command execution. When the first recognition attempt fails to meet the threshold, the system continues to monitor and recognize subsequent utterances of the same command, preparing to execute once the threshold is met, thus avoiding immediate rejection while maintaining accuracy standards
Solution Approach 2:
The system implements a feedback mechanism where recognition results are continuously evaluated. When a voice command is initially recognized below the threshold, the system provides feedback by continuing to monitor for repeated utterances, and upon repeated recognition meeting the threshold, triggers the recording action, thereby resolving the timing delay while maintaining reliability
2Reliability
If complex voice commands are used to prevent malfunction, then system safety is improved, but user ability to instantly utter accurate commands decreases
Solution Approach 1:
The system performs preliminary recognition attempts for complex voice commands. When a user attempts to utter a complex command and initially fails to meet the recognition threshold, the system continues to monitor for repeated utterances, allowing the user additional opportunities to correctly pronounce the command without immediate system rejection
Solution Approach 2:
The system provides a cushioning mechanism by allowing multiple recognition attempts for complex voice commands. This beforehand cushioning accommodates user difficulty in instantly uttering accurate complex commands while maintaining system safety through continued threshold-based validation across multiple attempts
3Reliability
If redundant voice commands are required to prevent malfunction, then system reliability is improved, but command frequency of use decreases
Solution Approach 1:
The system performs preliminary recognition monitoring for redundant voice commands. When a voice command is uttered but initially fails to meet the recognition threshold, the system continues to monitor for repeated utterances of the same command, allowing the redundant command structure to function safely while reducing the practical impact on usage frequency
Solution Approach 2:
The system implements feedback monitoring that tracks repeated voice command utterances. This feedback mechanism allows the system to validate redundant commands through repeated recognition attempts, maintaining system reliability while improving the practical usability and frequency of command usage by accommodating natural variations in user pronunciation
Data Source
AI summary
A voice operation control device includes: a voice command determination unit configured to recognize an utterance of a user and determine whether the recognized utterance is a voice command; and a voice command accepting unit configured to accept the accepted voice command. The voice command determination unit is configured to, when the accepted utterance indicates that an utterance coincident with a preset voice command at a level equal to or larger than a first threshold has been detected, determine that the recognized utterance is the voice command. The voice command determination unit is configured to, when the accepted utterance indicates that an utterance that is equal to or larger than a second threshold, which indicates a lower degree of coincidence than the first threshold, but less than the first threshold has been detected more than once within a predetermined time period, determine that the recognized utterance is the voice command.