Digital Microphone Interface Circuit for Voice Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In electronic devices, voice recognition in low-power mode is hindered by limited data usage due to power consumption issues, leading to decreased recognition rates, particularly because the gain of voice signals is distorted after processing, affecting the accuracy of voice recognition.
Innovation Solution
The implementation of a digital microphone interface circuit that tunes the maxscale gain of PCM signals based on the physical distance between the user and the device, using sensors to acquire distance information before voice recognition, ensuring optimal gain settings for accurate voice data capture in low-power mode.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the electronic device operates in low-power mode with limited data usage, then power consumption is reduced, but voice recognition rate decreases due to gain distortion
Solution Approach 1:
The patent applies preliminary action by acquiring distance information between the user and the electronic device before voice recognition processing. This distance information is used to pre-determine the appropriate maxscale gain value, which is then applied during PCM signal conversion. This preliminary setup ensures that the gain is optimally configured before voice data processing begins, preventing gain distortion while operating in low-power mode with limited data usage.
2Adaptability or versatility
If the gain of voice signal is adjusted after receiving the signal, then adaptation to different voice levels is achieved, but voice signal distortion occurs leading to decreased recognition accuracy
Solution Approach 1:
The patent determines the maxscale gain value in advance based on pre-acquired distance information before the voice signal is fully processed. This preliminary determination of gain settings eliminates the need for subsequent gain adjustments during voice signal processing, thereby preventing voice signal distortion while maintaining adaptability to different voice levels based on user distance.
3Reliability
If distance information is acquired in advance and maxscale gain is tuned accordingly, then voice recognition accuracy is improved, but additional processing steps are required
Solution Approach 1:
The patent introduces distance information as an intermediary parameter that bridges the gap between physical user-device distance and the appropriate maxscale gain setting. This intermediary approach allows the system to determine optimal gain values without complex real-time analysis of voice signal characteristics, simplifying the overall processing while improving recognition accuracy through physics-based distance-gain correlation.
Data Source
AI summary
Disclosed is an electronic device which includes an audio processing block for voice recognition in a low-power mode. The electronic device includes a digital microphone that receives a voice signal from a user and converts the received voice signal into a PDM signal, and a DMIC interface circuit. The DMIC interface circuit includes a PDM-PCM converting block that converts the PDM signal into a PCM signal, a maxscale gain tuning block that tunes a maxscale gain of the PCM signal received from the PDM-PCM converting block based on a distance information indicating a physical distance between the user and the electronic device acquired in advance of the converting of the PDM signal, and an anti-aliasing block that performs filtering for acquiring voice data of a target frequency band associated with a PCM signal output from the maxscale gain tuning block.