Reading-Aloud Determination Using Sound and Silent Time Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing devices struggle to accurately determine when a user has completed reading aloud a target, especially when there are silent periods or varying reading speeds, leading to potential errors in determining the completion of the task.
Innovation Solution
The device employs a system with a presentation section, sound input section, and reading-aloud determination section that measures sound input time and silent time, using threshold values to determine completion, allowing for continued presentation and user control over terminating the task based on accumulated sound input and silent periods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the device uses simple sound detection to determine reading-aloud completion, then the device complexity is reduced, but the measurement precision of reading-aloud completion deteriorates due to silent periods or slow reading speeds
Solution Approach 1:
The patent applies dynamics by making the determination criteria flexible and adaptive rather than fixed. The reading-aloud determination section dynamically adjusts the completion criteria based on accumulated sound input time and continuous silent time periods, allowing the system to adapt to varying reading speeds and natural pauses in speech, thereby maintaining high measurement precision without excessive complexity
Solution Approach 2:
The patent changes the parameters used for determination from simple presence/absence of sound to cumulative time-based parameters. By tracking accumulated sound input time and continuous silent time as variable parameters, the system achieves more precise measurement of reading-aloud completion while keeping the determination logic relatively simple
2Measurement precision
If the device requires continuous sound input without silent periods to determine reading-aloud completion, then the measurement precision is improved, but the reliability deteriorates due to natural pauses in reading
Solution Approach 1:
The system dynamically distinguishes between acceptable pauses (continuous silent time not exceeding threshold) and actual completion of reading-aloud. This dynamic approach allows natural reading pauses without false negatives while still detecting genuine completion when silent time continues beyond the threshold, thereby maintaining both precision and reliability
Solution Approach 2:
The patent segments the reading-aloud process into distinct phases: active reading (sound input), acceptable pause (continuous silent time within threshold), and completion (continuous silent time exceeding threshold). This segmentation allows the system to treat different time periods differently, improving reliability by not penalizing natural pauses while still detecting true completion
3Productivity
If the device terminates presentation immediately upon detecting reading-aloud completion, then the productivity is improved, but the ease of operation deteriorates because users cannot control the presentation flow
Solution Approach 1:
The presentation termination behavior is made dynamic based on user interaction. When reading-aloud completion is detected, the system does not immediately terminate but waits for user confirmation through input operation. This dynamic approach maintains productivity by detecting completion accurately while improving ease of operation by allowing users to control when the presentation actually terminates
Solution Approach 2:
The system implements feedback by detecting reading-aloud completion and presenting it to the user for confirmation before termination. This feedback loop allows users to review the detected completion and confirm or correct it through input operation, thereby maintaining both productivity (through accurate detection) and ease of operation (through user control)
Data Source
AI summary
A new information processing device for presenting information and allowing a user to input sound in relation to the presented information is provided. An information processing device 10 includes: a display section 104 that displays a sentence that is a reading-aloud target; a sound input section 102 to which sound is input; a time measuring section 105 that measures a sound input time in which the sound is input to the sound input section 102; and a test execution section 103 that determines whether or not the reading-aloud target is read aloud based on the sound input time and a silent time after the sound is input to the sound input section.


