Voice Recognition Gain Control for Distance-Dependent Speech Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices often misrecognize voice commands due to variations in distance and intensity of the user's voice, requiring users to adjust their position or voice volume, causing inconvenience.
Innovation Solution
An electronic apparatus adjusts the intensity of sound signals based on the distance between the user and the device, as well as the intensity of the user's voice, to improve voice recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voice recognition is performed without adjusting for distance and voice intensity, then the system operation is simple, but the voice recognition accuracy deteriorates
Solution Approach 1:
The system performs preliminary detection of voice intensity and distance estimation before the main voice recognition process. By measuring the intensity of the first sound signal and estimating user distance in advance, the system prepares appropriate gain values to ensure optimal recognition conditions are established before processing the actual voice command, thereby improving accuracy without significantly increasing overall system complexity
Solution Approach 2:
The system implements feedback by using the detected voice intensity and estimated distance to dynamically adjust the gain value applied to the sound signal. The processor continuously monitors the first sound signal's intensity, compares it against reference values, and automatically adjusts the second sound signal's intensity through gain modification, creating a closed-loop control system that maintains optimal recognition conditions
2Measurement precision
If the user adjusts distance or voice intensity to improve recognition, then the voice recognition accuracy improves, but the ease of operation deteriorates
Solution Approach 1:
The system performs self-adjustment by automatically detecting the user's voice intensity and distance, then autonomously modifying the sound signal processing parameters. The processor identifies the need for adjustment based on the first sound signal characteristics and automatically applies the appropriate gain value, eliminating the need for manual user intervention and maintaining high recognition accuracy while preserving ease of operation
Solution Approach 2:
The system dynamically changes the processing parameters (gain value) based on detected conditions. By modifying the intensity parameter of the second sound signal according to the measured voice intensity and distance estimates, the system adapts to varying user positions and voice strengths without requiring users to manually adjust their behavior, thus maintaining both accuracy and convenience
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic apparatus is provided. The electronic apparatus includes a microphone, a communication interface including circuitry and a processor configured to, based on identifying that a trigger word is included in a first sound signal received through the microphone, enter a voice recognition mode, identify a gain value for adjusting an intensity of the first sound signal to be in a predetermined intensity range based on the intensity of the first sound, adjust an intensity of a second sound signal received through the microphone in the voice recognition mode based on the identified gain value, and control the communication interface to transmit a user command obtained based on voice recognition regarding the adjusted second sound signal, to an external apparatus.