Voice Mixing Device Noise Suppression Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multipoint conference services, especially when participants use mobile terminals, background noise is often superimposed on voice signals, leading to increased computation in noise suppression processing and a risk of abnormal sounds due to nonconformity in past noise suppression information.
Innovation Solution
A voice mixing device with a speaker selection unit, full signal adder, common and individual noise suppression units, and memory switching unit that selects and mixes voice signals based on power or voice activity, reducing noise suppression processes and ensuring consistent noise suppression information across speaker changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If noise suppression processing is performed on speech of all participants, then noise reduction effect is improved, but computation amount increases
Solution Approach 1:
The patent divides noise suppression processing into two segments: common noise suppression applied to mixed speech of all participants, and individual noise suppression applied only to the detected speaker's speech. This segmentation reduces the overall computation amount while maintaining noise reduction effectiveness.
Solution Approach 2:
Instead of applying individual noise suppression to all participants, the patent applies it partially only to the detected speaker. This partial action reduces computation while still achieving acceptable noise reduction for the active speaker.
2Productivity
If individual noise suppression is applied to detected speaker only, then computation amount is reduced, but abnormal sounds occur due to nonconformity in past noise suppression information
Solution Approach 1:
The patent merges the common noise suppression information (obtained from mixed speech) with individual noise suppression information (obtained from detected speaker speech) by adding them together. This merging ensures continuity and consistency of noise suppression information across speaker transitions, preventing abnormal sounds.
Solution Approach 2:
The patent uses common noise suppression information as an intermediary to bridge between different individual noise suppression processes. When speakers switch, the common noise suppression maintains continuity, acting as a mediator that prevents discontinuities and abnormal sounds.
3Speed
If speaker switching is performed without merging noise suppression information, then responsiveness is improved, but noise suppression consistency deteriorates
Solution Approach 1:
The patent merges common noise suppression information with individual noise suppression information in real-time during speaker transitions. This merging operation maintains noise suppression consistency while allowing rapid speaker switching, as the common component provides continuous background noise estimation.
Data Source
AI summary
A voice mixing device for mixing a plurality of voice signals, comprises: a speaker selection unit selecting at least one voice signal among said plurality of voice signals; a full signal adder unit adding all of at least one voice signal selected by said speaker selection unit; respective subtractor unit subtracting only one of said selected voice signals from an addition result of said full signal adder unit; a common noise suppression unit suppressing noise of a common voice signal, being an addition result of said full signal adder unit; individual noise suppression unit suppressing noise of respective individual voice signals, being subtraction results of said subtractor unit; and memory switching unit copying information of noise suppression obtained in said common noise suppression unit based on a selection result of said speaker selection unit, to information of noise suppression in said individual noise suppression unit.