Dynamic Speech Recognition Display Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition systems display recognizable words continuously, even when the speech recognition function is not in use, leading to redundant and undesirable information for users operating the systems through other means.
Innovation Solution
A method and apparatus where speech recognition words are displayed only in response to a user's voice input operation, using a detecting unit to initiate display control when the speech processing start instruction is performed, and terminating the display when voice input ends, allowing users to focus on speech recognition only when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If speech recognition words are displayed continuously, then users can always see recognizable words, but redundant information is displayed when speech recognition is not in use
Solution Approach 1:
The display state of speech recognition words is made dynamic rather than static. The display controlling unit changes the display state based on detected operation types: displaying speech recognition words when voice input operation is detected, and not displaying them when other operations are detected. This dynamic adaptation eliminates redundant information display while ensuring visibility when needed.
Solution Approach 2:
The display parameters (visibility, highlighting) of speech recognition words are changed based on the operation context. When voice input operation is detected, the display parameter changes to show speech recognition words; when other operations are detected, the display parameter returns to normal state. This parameter change resolves the contradiction between continuous visibility and redundant display.
2Ease of operation
If speech recognition words are displayed all the time, then users have constant access to recognizable words, but user operability is reduced due to redundant information
Solution Approach 1:
The system dynamically adjusts information display based on operational context. The detecting unit identifies the type of operation being performed, and the display controlling unit accordingly adjusts whether to display speech recognition words. This dynamic approach improves ease of operation by eliminating redundant information while maintaining access to speech recognition words when voice input is intended.
3Loss of information
If recognizable words are highlighted continuously, then users can always identify speech recognition words, but the display becomes cluttered and less useful
Solution Approach 1:
The display parameters (highlighting, styling) of recognizable words are conditionally changed based on operation type. When voice input operation is detected, the display parameter changes to highlight speech recognition words for easy identification. When other operations are detected, the highlighting parameter is removed or reduced, eliminating display clutter while preserving identifiability when needed.
Data Source
AI summary
An apparatus and method for speech information processing includes detecting a first operation of a speech processing start instruction element, controlling a display so that speech recognition information is displayed in response to the detection of the first operation, detecting a second operation of the speech processing start instruction element, acquiring speech information in response to detection of the second operation, and performing speech recognition processing on the speech information.