Multi-Microphone Echo Filtering for Voice Wake-Up Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional acoustic echo cancellation algorithms in electronic devices with microphones and speakers are inadequate in effectively filtering echoes, leading to suboptimal performance in voice assistant wake-up and call quality.
Innovation Solution
Implementing an echo filtering method that includes direct sound filtering, customized filtering models, and reverse audio cancellation using multiple microphones and speakers, along with preprocessing and adaptive filtering techniques to reduce echo components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional acoustic echo cancellation algorithm is used, then echo filtering is performed, but echo filtering effect is insufficient
Solution Approach 1:
The patent segments the echo cancellation process into two distinct stages: conventional AEC algorithm for initial echo removal, followed by direct sound filtering for residual echo elimination. This segmentation allows each filtering stage to address specific types of echo components, thereby improving overall echo filtering effect and voice assistant wake-up success rate
Solution Approach 2:
The patent performs preliminary action by conducting conventional AEC filtering before direct sound filtering. This preliminary echo cancellation prepares the signal by removing the majority of echo components, making the subsequent direct sound filtering more effective and efficient in eliminating residual echoes
2Measurement precision
If multiple filtering operations are performed, then echo filtering effect is improved, but computational overhead increases
Solution Approach 1:
The patent applies partial action by performing direct sound filtering selectively on specific signal components after conventional AEC. Instead of applying heavy filtering to the entire signal, it focuses computational resources on the residual echo components that remain after initial cancellation, achieving improved echo filtering effect with controlled computational overhead
Data Source
AI summary
An echo filtering method, an electronic device, a computer-readable storage medium, and an echo filtering apparatus are disclosed. The electronic device includes M microphones and N speakers. M and N are integers greater than 1. The method includes: obtaining N speaker signals corresponding to the N speakers; obtaining M microphone signals corresponding to the M microphones; and performing at least direct sound filtering on the N speaker signals and the M microphone signals to obtain a target signal. By using this method, better echo filtering effect can be obtained.