Display Audio Volume Control for Accurate Voice Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image display apparatuses face decreased voice recognition performance due to background noise interference, as they struggle to distinguish user voice commands from ambient audio signals, leading to reduced operational accuracy.
Innovation Solution
The implementation of a voice recognition system within the image display apparatus that includes a first voice input unit, an audio output unit, and a controller to decrease the audio signal volume to a predetermined level when a voice recognition start command is received, along with an optional background sound canceller to isolate user voice signals, and a command word generator to optimize voice recognition command words.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If the audio signal volume is increased for better audio output quality, then the audio output quality is improved, but the voice recognition accuracy deteriorates due to background noise interference
Solution Approach 1:
The patent applies dynamics by making the audio output volume adjustable and changeable over time. The controller dynamically adjusts the audio signal volume to a predetermined level during voice recognition operations and restores it after recognition completes. This temporal variation in volume allows the system to optimize for voice recognition accuracy during recognition phases while maintaining good audio output quality during playback phases.
Solution Approach 2:
The patent changes the volume parameter of the audio signal based on the operational state of the device. When voice recognition is active, the volume parameter is reduced to minimize background noise interference with the microphone input. When voice recognition is inactive, the volume parameter is restored to its normal level for optimal audio output. This parameter adjustment directly resolves the contradiction between audio quality and recognition accuracy.
2Measurement precision
If the volume of audio signal output is decreased to improve voice recognition, then voice recognition accuracy is improved, but the audio output quality deteriorates
Solution Approach 1:
The patent implements periodic action by alternating between two volume states: a reduced volume state during voice recognition operations and a normal volume state during audio playback. The controller periodically adjusts the audio signal volume based on whether voice recognition is currently active. This periodic switching allows the system to maintain both high voice recognition accuracy (during recognition phases) and high audio output quality (during playback phases) without permanent compromise to either function.
3Measurement precision
If background sound is cancelled to improve voice recognition, then voice recognition accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent extracts and removes the harmful background noise component from the audio signal received by the microphone. The controller identifies the audio signal output as background noise and cancels it out, leaving only the user's voice input for recognition. This extraction approach improves voice recognition accuracy by eliminating the interfering background sound without requiring complex additional hardware, as it utilizes the existing audio output path for cancellation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are an image display apparatus (1) able to improve voice recognition performance by decreasing the volume of an audio signal output from the image display apparatus (1) to a predetermined level or less when the image display apparatus (1) recognizes user voice, and a method of controlling the same. The image display apparatus (1) enabling voice recognition includes a first voice input unit (112) to receive a user-side audio signal, an audio output unit (122) to output an audio signal processed by the image display apparatus (1), a first voice recognizer (210) to recognize the user-side audio signal received through the first voice input unit (112), and a controller (220) to decrease the volume of the audio signal output through the audio output unit (122) to a predetermined level if a voice recognition start command is received.