Voice Control Interface for Low Power Mode Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems in mobile devices require waking the main processor to provide visual notifications when in sleep mode, consuming more power and being less responsive to user interactions.
Innovation Solution
Implementing a voice control user interface that allows progressive command engagement through speech command phrase segments, enabling low-power interactions without waking the main processor, and using a secondary processor to perform control operations and update display data without fully awakening the device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the main processor is woken to provide visual notifications during sleep mode, then the user can view notifications and interact with the device, but power consumption increases
Solution Approach 1:
The voice command is segmented into multiple parts: a wake word that triggers display activation, followed by additional command segments that can be processed. This allows the system to provide notifications with partial processor activation rather than full wake-up, reducing power consumption while maintaining notification delivery.
Solution Approach 2:
Instead of fully waking the main processor to handle notifications, the system performs partial action by activating only the display and basic voice recognition capabilities. This partial activation suffices for notification delivery without the excessive power consumption of a complete processor wake-up.
2Loss of information
If the display is turned on to show visual indications during sleep mode, then the user can see notifications, but battery life is reduced
Solution Approach 1:
The notification system is segmented into visual display components and processor-intensive components. The display can be activated independently to show notifications without requiring the main processor to fully wake, thereby providing information visibility while minimizing energy loss.
Solution Approach 2:
A low-power voice recognition subsystem acts as an intermediary between the sleeping main processor and the display. This intermediary can activate the display for notification visibility without requiring full processor activation, reducing the energy cost while maintaining information delivery.
3Ease of operation
If voice recognition is implemented during low-power mode, then user interaction is maintained, but system complexity increases
Solution Approach 1:
The voice recognition system is segmented into a lightweight low-power mode recognizer and a full-power mode processor. The low-power recognizer handles basic commands and wake words, maintaining user interaction capability without requiring the complex full voice recognition system to be active, thus limiting the increase in system complexity.
Solution Approach 2:
The essential voice recognition functionality is extracted from the main processor and implemented as a separate low-power subsystem. This extraction allows basic user interaction to be maintained during sleep mode without burdening the main processor, while the complex full voice recognition capabilities remain available when needed but are not required for basic operation.
Data Source
AI summary
A method include placing a first processor in a sleep operating mode and running a second processor that is operative to wake the first processor from the sleep operating mode in response to a speech command phrase. The method includes identifying, by the second processor, a speech command phrase segment and performing a control operation in response to detecting the segment in detected speech. The control operation is performed while the first processor is maintained in the sleep operating mode.