Dual Processor Voice Recognition Phased Activation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems in electronic devices face challenges in minimizing errors, increasing recognition rates, and reducing current consumption, as they either use low power chips leading to increased error rates due to limited memory and performance differences, or high power chips that consume more current when kept in an active state for seamless voice recognition.
Innovation Solution
An electronic device with a dual processor system where a first processor performs initial voice recognition and wakes up a second processor only when necessary, allowing for phased activation and efficient use of resources, thereby minimizing errors and reducing current consumption while enhancing recognition performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If a low power chip is utilized to reduce current consumption, then current consumption is reduced, but voice recognition error rate increases
Solution Approach 1:
The voice recognition system is segmented into two distinct processors: a first processor that performs initial voice recognition with lower power consumption, and a second processor that performs secondary voice recognition with higher accuracy. This segmentation allows the system to balance power consumption and recognition accuracy by distributing tasks across multiple components rather than relying on a single chip.
Solution Approach 2:
The first processor performs a partial voice recognition task initially, and only when recognition is not successful does the system activate the second processor for additional recognition attempts. This partial action approach ensures that the high-power second processor is activated only when necessary, optimizing the balance between power consumption and recognition success rate.
2Reliability
If a high performance chip is used to improve voice recognition error rate, then voice recognition accuracy is improved, but current consumption increases
Solution Approach 1:
The system divides the voice recognition workload between two processors with different performance characteristics. The high-performance second processor is segmented as a backup resource that is activated only when the first processor fails to recognize the voice, thereby utilizing high performance only when necessary rather than continuously.
Solution Approach 2:
The second processor is activated periodically or conditionally based on the success of the first processor's recognition. Instead of running continuously, the high-power second processor operates in periodic bursts only when recognition failures occur, reducing overall power consumption while maintaining high accuracy when needed.
3Speed
If seamless voice recognition is implemented with continuous system standby, then voice recognition responsiveness is improved, but current consumption losses increase
Solution Approach 1:
The continuous voice recognition system is segmented into hierarchical levels: the first processor handles routine recognition tasks during standby, while the second processor remains in a lower-power state and is activated only when needed. This segmentation enables responsive voice recognition while minimizing the power consumption of continuous operation.
Solution Approach 2:
Instead of fully activating both processors during standby, the system uses partial action by keeping only the first processor active for basic recognition tasks. The second processor remains in a reduced-power state, activating fully only when the first processor determines additional processing is needed, thereby reducing continuous power losses while maintaining responsiveness.
Data Source
AI summary
Provided is an electronic device that includes a first processor for receiving an audio signal, performing first voice recognition on the audio signal, and transferring a driving signal to a second processor based on a result of the first voice recognition. The second processor performs second voice recognition based on a voice signal by the first voice recognition or the audio signal, in response to the driving signal.