Voice Recognition Microphone Array State-Based Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent assistance services face challenges in improving utterance recognition rates while minimizing power consumption, as using multiple microphones for processing leads to high power consumption and limited processing capabilities with sub-processors.
Innovation Solution
An electronic device with multiple microphone arrays and processors, where a wake-up utterance is received using first group microphones in a sleep mode, transitioning to a wake-up mode to process subsequent utterances with second group microphones, allowing efficient power management and enhanced processing capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple microphones are used for utterance processing, then utterance recognition rate is improved, but power consumption increases
Solution Approach 1:
The patent divides the microphone system into multiple groups (first group microphones and second group microphones) that can be selectively activated based on operational state. During sleep mode, only the first group microphones are active for wake-up detection, while the second group microphones remain inactive to conserve power. When fully operational, the second group microphones are activated for comprehensive utterance processing, thus resolving the contradiction between recognition accuracy and power consumption.
2Use of energy by moving object
If sub-processor is used for pre-processing, then power consumption is reduced, but processing capability is limited
Solution Approach 1:
The patent implements a dynamic system where the processing capability adapts to the operational state. In sleep mode, the sub-processor handles basic wake-up detection with limited processing. Upon detecting a wake-up utterance, the system transitions to wake-up mode where the main processor takes over, providing full processing capability for subsequent utterances. This dynamic adjustment allows the system to have high processing capability when needed while consuming low power during idle periods.
3Measurement precision
If main processor is activated continuously, then utterance recognition rate is improved, but power consumption increases
Solution Approach 1:
The patent employs periodic activation of the main processor rather than continuous operation. The system alternates between sleep mode (low power) and wake-up mode (high performance) based on wake-up detection. The first group microphones periodically monitor for wake-up utterances using the sub-processor, and only when a wake-up event is detected does the main processor activate for full utterance processing. This periodic action pattern maintains high recognition rates during active periods while dramatically reducing power consumption during sleep periods.
Data Source
AI summary
Various embodiments of the present invention relate to an electronic device for performing voice recognition using microphones selected on the basis of the operation state, and an operation method of same. According to an embodiment, the electronic device includes: one or more microphone arrays which include a plurality of microphones; at least one processor operatively connected to the microphone arrays; and at least one memory electrically connected to the processor, wherein the memory may store instructions for the processor to, at the time of execution; receive wake-up utterances, for calling designated voice services, by using a first group of microphones among the plurality of microphones when operating in a first state; operate in a second state in response to the wake-up utterances; and receive subsequent utterances using a second group of microphones among the plurality of microphones when operating in the second state. Various other embodiments are also possible.