Voice Recognition Sound Output Control by Device Proximity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The integration of multiple electronic devices in the same space can reduce the voice recognition rate of voice recognition devices due to noise from other devices, necessitating a method to selectively control sound output to enhance recognition performance.

Innovation Solution

A sound output control system that uses a server to transmit sound output stop commands to electronic devices connected via a network, allowing for selective control of sound based on the location of the voice recognition device, thereby reducing noise interference.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If sound output is reduced from all electronic devices to improve voice recognition rate, then voice recognition performance is improved, but sound output functionality is degraded

Engineering Contradiction:
Improvevoice recognition rateVSAvoidsound output interference
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The system segments electronic devices by their physical location relative to the voice recognition device. Devices are divided into two groups: those in the same space (which may cause interference) and those in different spaces (which generally do not interfere). This segmentation allows selective sound output control - muting only devices in the same space while preserving sound output from devices in different spaces, thus improving voice recognition without completely degrading sound output functionality.

Inventive Principle:
Principle #1Segmentation

2Reliability

If sound output is muted from electronic devices in the same space to reduce noise interference, then voice recognition rate is improved, but sound output functionality is degraded

Engineering Contradiction:
Improvevoice recognition rateVSAvoidsound output control
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system applies different sound output control policies to different locations. Electronic devices in the same physical space as the voice recognition device are subjected to sound output restriction, while devices in different spaces maintain normal sound output functionality. This local differentiation ensures that voice recognition performance is improved in the critical near-field area without unnecessarily degrading sound output functionality elsewhere.

Inventive Principle:
Principle #3Local quality

3Reliability

If location-based selective sound control is implemented, then voice recognition rate is improved while maintaining sound output from distant devices, but system complexity is increased

Engineering Contradiction:
Improvevoice recognition rateVSAvoidcontrol system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces a server as an intermediary component that coordinates between the voice recognition device and multiple electronic devices. The server receives information about the voice recognition device's location and current operation state, then automatically determines which electronic devices should have their sound output restricted. This intermediary approach distributes the control logic complexity to the server, keeping the individual electronic devices relatively simple while achieving sophisticated location-based sound control.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3640790B1Electronic device, control method thereof, and sound output control system of the electronic device
Publication Date: 2023.12.13 SAMSUNG ELECTRONICS CO LTD
  • EP3640790B1 patent drawingFigure 1
  • EP3640790B1 patent drawingFigure 2
  • EP3640790B1 patent drawingFigure 3

AI summary

Provided are an electronic device, a control method thereof, and a sound output control system of the electronic device, for example, a technique for controlling sound that is output from an electronic device located in the same space as a voice recognition device. The electronic device according to an embodiment of the disclosure includes: a communication device comprising communication circuitry configured to detect a voice recognition device within a specified distance of the electronic device; a storage device comprising a memory configured to store identification information of the detected voice recognition device; and a controller configured to compare, based on the communication device receiving identification information from a server of a voice recognition device that has received a voice command from a user, the received identification information with the identification information stored in the storage device, and to control, based on the controller determining that the received identification information is identical to the stored identification information, the electronic device to stop outputting sound.