Adaptive Noise Suppression for Spatial Audio Object Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current spatial audio capture systems face challenges in optimally setting tuning parameters for object separation and noise suppression, leading to suboptimal output quality due to tradeoffs and compromises in manual tuning, which can result in amplified noise and artifacts.
Innovation Solution
An adaptive control mechanism is implemented to adjust noise suppression and object separation parameters based on the spectral characteristics of audio objects and ambient sounds, using techniques like beamforming and machine learning to separate and process audio signals from multiple microphones, ensuring improved perceptual quality and reducing artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If noise suppression techniques are applied to spatial audio signals, then noise sources such as wind noise, background noise, motor noise, and handling noise are suppressed, but noise removal artifacts are introduced and audio quality is degraded
Solution Approach 1:
The system dynamically adjusts noise suppression parameters based on the detected audio scene characteristics. By changing parameters adaptively rather than using fixed settings, the system optimizes noise suppression effectiveness while minimizing artifact introduction for different acoustic environments
Solution Approach 2:
The noise suppression system transitions from static parameter settings to dynamic adaptation. The system continuously monitors the audio input and adjusts suppression levels in real-time, allowing it to respond to changing noise conditions while preserving audio quality and reducing artifacts
2Object-affected harmful factors
If manual tuning is used to set parameters for object separation and noise suppression, then some level of noise suppression is achieved, but suboptimal output quality results due to tradeoffs and compromises
Solution Approach 1:
The system implements a feedback mechanism that analyzes the output audio quality and adjusts noise suppression parameters accordingly. By continuously monitoring the results and making adjustments based on this feedback, the system achieves optimal balance between noise suppression and audio quality without manual trial-and-error tuning
Solution Approach 2:
The noise suppression system becomes self-adjusting by automatically analyzing the audio scene and optimizing its own parameters. The system serves itself by detecting noise characteristics and independently configuring the appropriate suppression level, eliminating the need for manual intervention and achieving consistent optimal performance
3Object-affected harmful factors
If strong noise suppression is applied to remove noise sources, then noise levels are reduced, but artifacts are amplified and audio quality deteriorates
Solution Approach 1:
The system applies noise suppression selectively to specific frequency bands and time periods where noise is actually present. By targeting only the problematic regions rather than applying uniform suppression across the entire audio signal, the system reduces noise effectively while preserving audio quality and minimizing artifact introduction in clean regions
Data Source
AI summary
An apparatus including circuitry configured to: obtain at least two audio signals; determine, with respect to the at least two audio signals, an audio object part and an ambience audio part; determine a level parameter based on the ambience audio part; apply a noise suppression to the audio object part, wherein the noise suppression is configured to be controlled based on the determined level parameter; and generate a noise suppressed audio object part based on the applied noise suppression.