Image Processing Device Speech Recognition Noise Amplification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current image processing devices using single microphones in remote controllers for speech recognition face limitations in noise removal and performance, especially in noisy environments, leading to reduced recognition accuracy and increased power consumption due to the need for additional hardware like ADCs and DSP chips.

Innovation Solution

An image processing device with a speech acquirer and processor that performs preprocessing operations using speech amplification and noise amplification on signals from internal and external microphones, respectively, to enhance recognition accuracy and efficiency, allowing for both far and near field speech recognition without the need for additional hardware.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a multi-channel microphone array is embedded in the remote controller to improve speech recognition accuracy, then speech acquisition performance is improved, but device complexity and manufacturing cost increase due to additional ADCs and DSP chips

Engineering Contradiction:
Improvespeech recognition accuracyVSAvoidhardware complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines the speech processing functions of multiple microphones into a unified system where the TV's main processor handles all signal processing tasks. Instead of distributing ADCs and DSP chips across multiple devices, the system merges processing capabilities into a single centralized unit, reducing overall hardware complexity while maintaining multi-channel speech acquisition through the television's built-in microphones.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The TV set is designed to serve multiple functions: it acts as both the display device and the speech recognition system. The television's existing processor and microphones are utilized for speech processing, eliminating the need for dedicated speech processing hardware in the remote controller. This multi-functional approach reduces device complexity while improving speech recognition capabilities.

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

2Object-affected harmful factors

If a multi-channel microphone array with separate DSP chip is used to improve speech recognition, then noise removal performance is improved, but manufacturing cost increases

Engineering Contradiction:
Improvenoise removal performanceVSAvoidmanufacturing cost
Core Design Contradiction:
Object-affected harmful factorsVSEase of manufacture

Solution Approach 1:

The patent merges the noise removal processing function into the TV's main processor, eliminating the need for separate DSP chips in each remote controller. By combining speech acquisition and noise removal processing into a single centralized system, the manufacturing cost is reduced while maintaining effective noise removal performance through software-based signal processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

Instead of physically embedding multiple microphones and processing chips in each remote controller, the system uses the TV's existing microphones and processor to create a virtual multi-channel speech processing system. This software-based approach copies the functionality of hardware multi-microphone systems without the associated manufacturing costs.

Inventive Principle:
Principle #26Copying

3Measurement precision

If additional hardware components are added to improve speech recognition performance, then recognition accuracy is improved, but power consumption increases

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

Solution Approach 1:

The patent merges speech processing functions into the TV's main processor, which is already powered and operational. By consolidating speech processing with the television's existing computing resources, the system avoids the additional power consumption that would result from separate DSP chips or microcontrollers in the remote controller, while maintaining high recognition accuracy.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3474557B1Image processing device, operation method of image processing device, and computer-readable recording medium
Publication Date: 2023.12.13 SAMSUNG ELECTRONICS CO LTD
  • EP3474557B1 patent drawingFigure 1
  • EP3474557B1 patent drawingFigure 2
  • EP3474557B1 patent drawingFigure 3

AI summary

The present disclosure relates to an image processing device, an operation method of the image processing device, and a computer-readable recording medium. The image processing device according to an embodiment in the present disclosure may comprise: a voice-obtaining unit for obtaining the voice of a user and generating a first voice signal; a communication interface unit for receiving a second voice signal of the user from an external device; and a processor which, after the first voice signal is received from the voice-obtaining unit, performs a first pre-processing operation employing voice amplification of the received first voice signal, and, after the second voice signal is received via the communication interface unit, performs a second pre-processing operation employing noise amplification of the second voice signal.