Speech Control System Selective Response for Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multifunctional image processing apparatuses using speech UI face challenges in reducing user burden due to recognition errors and redundant responses, which complicate user interaction and increase operational complexity.
Innovation Solution
A speech control system comprising a microphone, speaker, and controller that selectively outputs response speech based on the number of setting items, either reading all specified items or omitting at least one, to prevent redundant information and reduce user burden, using a reading condition to determine the appropriate response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system outputs all recognized setting items by speech, then the user can confirm the speech recognition results, but the response speech becomes redundant and increases user burden
Solution Approach 1:
The patent extracts only the necessary setting items for speech output based on a determination result, rather than outputting all recognized items. The controller selectively outputs setting items that need user confirmation, removing redundant information from the response speech.
Solution Approach 2:
The patent applies partial action by outputting only a subset of setting items (those determined to need confirmation) rather than all recognized items. This partial output approach reduces redundancy while maintaining necessary confirmation functionality.
2Loss of information
If the system provides comprehensive speech feedback, then the user can verify all settings, but the interaction complexity increases
Solution Approach 1:
The patent extracts and outputs only the specific setting items that require user confirmation, rather than providing comprehensive feedback on all settings. This selective extraction reduces interaction complexity while preserving essential information.
Solution Approach 2:
The patent segments the setting items into two groups: those that need speech output for confirmation and those that don't. This segmentation allows the system to manage information delivery more efficiently, reducing overall interaction complexity.
3Reliability
If the system reads all setting items, then recognition errors can be detected, but the response time increases
Solution Approach 1:
The patent extracts only the setting items that need confirmation for speech output, reducing the total time required to deliver the response while maintaining error detection capability for critical items.
Solution Approach 2:
The patent applies partial action by confirming only necessary setting items through speech rather than all items, thereby reducing response time while maintaining sufficient reliability for error detection.
Data Source
AI summary
There is provided a speech control system including: a microphone configured to acquire speech; a speaker configured to output speech; an image processing unit; and a controller configured to control settings of the image processing unit. The controller is configured to: specify one or more setting items represented by an input speech of a user acquired by the microphone that are to be set for the image processing unit, and depending on whether or not the specified one or more setting items satisfy a reading condition, cause the speaker to output a first response speech that reads the one or more setting items, or a second response speech that does not read at least one out of the one or more setting items.