Microphone Array Dynamic Mode Switching for Voice Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Electronic devices equipped with a single microphone suffer from noise contamination in audio data, leading to decreased accuracy in voice recognition.

Innovation Solution

The use of multiple microphones that can be selectively activated based on audio data analysis, employing a method that switches between power-saving and detail recognition modes to optimize voice recognition accuracy and power efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple microphones are activated continuously, then voice recognition accuracy is improved, but power consumption increases

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the number of active microphones based on operational conditions. A first microphone operates continuously in a first mode for basic operations, while additional microphones are activated in a second mode when voice recognition accuracy is determined to be insufficient, thereby optimizing the balance between accuracy and power consumption in real-time

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the operational parameters of the microphone system by switching between different operational modes. In the first mode, only one microphone is active; in the second mode, multiple microphones are activated. This parameter change allows the system to adapt to varying voice recognition requirements while managing power consumption effectively

Inventive Principle:
Principle #35Parameter changes

2Loss of energy

If one microphone is used, then power efficiency is improved, but noise interference increases

Engineering Contradiction:
Improvepower efficiencyVSAvoidnoise interference
Core Design Contradiction:
Loss of energyVSObject-affected harmful factors

Solution Approach 1:

The system dynamically switches between single-microphone and multi-microphone operation based on the determined voice recognition accuracy. When noise interference degrades accuracy below a threshold, the system activates additional microphones to suppress noise, thereby maintaining power efficiency during clear conditions while mitigating noise interference when necessary

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If multiple microphones are used, then audio data quality is improved, but device complexity increases

Engineering Contradiction:
Improveaudio data qualityVSAvoidmicrophone system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The microphone system is segmented into different operational configurations. The device includes multiple microphones but operates with one microphone as the primary unit for most functions, activating additional microphones only when audio data quality requires enhanced performance. This segmentation allows high audio quality when needed while maintaining simplicity for routine operations

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3576085B1Operating method for microphones and electronic device supporting the same
Publication Date: 2023.03.15 SAMSUNG ELECTRONICS CO LTD
  • EP3576085B1 patent drawingFigure 1
  • EP3576085B1 patent drawingFigure 2~3
  • EP3576085B1 patent drawingFigure 4~5

AI summary

An electronic device which includes a plurality of microphones and an audio data processing module is provided. The plurality of microphones is operatively coupled to the electronic device, and the audio data processing module is capable of being implemented with at least one processor. The audio data processing module recognizes a specified command, based on first audio data collected using a portion of the plurality of microphones and executes a function or an application corresponding to second audio data collected using all the plurality of microphones, when the specified command is recognized.