Adaptive Microphone Array for Distance-Based Voice Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice recognition systems for portable devices face challenges in accurately processing audio signals depending on the user's utterance distance, leading to potential voice distortion and impaired recognition when noise canceling processing is performed in a fixed manner without considering the distance.

Innovation Solution

A portable device equipped with two microphones and a signal processing unit that determines the user's utterance distance through audio signal analysis, employing noise canceling and amplitude correction techniques tailored to the specific distance to ensure accurate voice recognition, using beamforming and non-voice canceling processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If noise canceling processing is performed in a fixed manner without considering utterance distance, then ambient noise can be reduced, but user voice may be distorted

Engineering Contradiction:
Improveambient noiseVSAvoidvoice recognition accuracy
Core Design Contradiction:
Object-affected harmful factorsVSReliability

Solution Approach 1:

The patent applies dynamics by making the noise canceling processing adaptive rather than fixed. The system dynamically adjusts the noise canceling algorithm based on the detected utterance distance, switching between different processing modes (e.g., aggressive noise canceling for far-field, minimal processing for near-field) to optimize both noise reduction and voice preservation under varying conditions.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes processing parameters based on utterance distance. By detecting the distance between the user and the portable device, the system adjusts parameters such as noise reduction intensity, gain compensation, and filter characteristics to match the appropriate processing level, thereby preventing voice distortion while maintaining noise reduction effectiveness.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If two microphones are embedded for general state utterance, then coverage of user utterance is improved, but ambient noise introduction increases

Engineering Contradiction:
Improveutterance distance coverageVSAvoidambient noise
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The patent uses the relative signal strengths and phase differences from multiple microphones as intermediaries to determine utterance distance. By analyzing these intermediate measurements, the system infers the user's distance and selects appropriate noise canceling strategies, effectively using the microphone array data as a mediator between the physical setup and the noise reduction decision.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically selects which microphones to use and how to process their signals based on the detected utterance distance. For near-field utterances, it may prioritize microphones closer to the expected user position and apply minimal noise canceling. For far-field utterances, it activates all microphones and applies more aggressive noise reduction algorithms to handle the increased ambient noise.

Inventive Principle:
Principle #15Dynamics

3Device complexity

If only one microphone is used for short distance utterance, then device complexity is reduced, but adaptability to different utterance scenarios is limited

Engineering Contradiction:
Improvemicrophone configurationVSAvoidutterance scenario coverage
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent makes a single microphone serve multiple functions by implementing distance-based adaptive processing. The same microphone is used for both near-field and far-field scenarios, with the system adjusting its processing parameters (gain, noise filtering, echo cancellation) based on detected utterance characteristics, thereby achieving multi-scenario adaptability without adding hardware complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP3480812B1Portable device for controlling external device, and audio signal processing method therefor
Publication Date: 2020.06.10 SAMSUNG ELECTRONICS CO LTD
  • EP3480812B1 patent drawingFigure 1A(a)~1A(b)
  • EP3480812B1 patent drawingFigure 1B(a)~1B(b)
  • EP3480812B1 patent drawingFigure 1C(a)~1C(c)

AI summary

Disclosed is a portable device for controlling an external device. The portable device comprises: a first microphone, disposed on one surface of a portable device, for receiving an audio signal including user voice uttered by a user; a second microphone, disposed on the other surface of the portable device opposite to the one surface of the portable device, for receiving the audio signal including the user voice; a signal processing unit for processing the audio signal; a communication unit for communicating with an external device; and a processor which determines the user utterance distance between the portable device and the user on the basis of the audio signal received through the first and second microphones, if it is determined that the user utterance distance is a short distance utterance, controls the signal processing unit to process only the audio signal received through the microphone disposed at a relatively further distance from the user from among the first and second microphones, and controls the communication unit to transmit the processed audio signal to the external device.