Far End Audio Signal Modification for Conference Noise Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During video conferences, it is challenging to distinguish and remove unintended noise such as echo, background music, and the presenter's voice from shared audio, which affects the audio quality.
Innovation Solution
The implementation of a high-fidelity audio sharing (HAS) process that establishes a network connection between user equipment to identify and remove far-end audio (FEA) delays by sending calibration audio signals, allowing for the extraction of FEA data from mixed audio data, thereby enhancing audio quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If audio sharing is implemented during video conference, then attendees can share sound and music in real time, but unintended noise such as echo, background music, and presenter voice cannot be distinguished and removed
Solution Approach 1:
The patent segments the mixed audio signal into multiple components including far-end audio, near-end audio, echo, and noise. By dividing the audio processing into distinct stages (echo cancellation, noise suppression, audio separation), the system can target and remove specific unwanted components while preserving the desired shared audio content.
Solution Approach 2:
The patent extracts and removes the far-end audio component from the mixed audio signal. By identifying and separating the FEA data that causes echo and unintended noise, the system extracts only the necessary audio components for sharing while eliminating the harmful far-end audio that creates interference.
2Manufacturing precision
If calibration audio signals are sent to identify FEA delay, then audio quality is improved by removing delays, but system complexity increases due to additional calibration process
Solution Approach 1:
The patent performs calibration audio signal exchange before the main audio sharing session to pre-determine the FEA delay value. By conducting this calibration in advance, the system establishes the timing offset that needs to be compensated, simplifying the real-time audio processing during the actual sharing session.
Solution Approach 2:
The patent uses the calibration audio signals to create a feedback mechanism where the system measures the actual delay introduced by the far-end audio path and uses this information to adjust and compensate for the delay in real-time processing, improving audio synchronization.
Data Source
AI summary
Techniques for modification of far end audio signals are provided. In an example method, a computing device establishes a conference meeting including a first user equipment (UE) among a plurality of UE. The computing device then receives far end audio (FEA) data from the first UE. The computing device generates first modified FEA comprising determining a time-domain sum-of-absolute-difference (SAD) from the FEA data and determines a difference between the first modified FEA and a predefined value. Responsive to the difference exceeding a predefined threshold, the computing device determines a second modified FEA comprising determining a frequency-domain SAD from the FEA data and stores the second modified FEA in a buffer. The second modified is then output from the buffer.