Audio Interference Cancellation via Subband Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-controlled devices face performance degradation due to audio interference from sources like televisions and other appliances, which can negatively impact signal-to-interference ratios and affect keyword detection and speech recognition accuracy.
Innovation Solution
The implementation of acoustic echo cancellation, acoustic beamforming, noise reduction, and interference cancellation techniques to mitigate audio interference, including subband analysis, adaptive filtering, spatial filtering, and scene analysis to differentiate between user speech and interference sources, thereby enhancing signal-to-interference ratios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice-controlled devices operate in proximity to televisions and other audio interference sources, then the device can be placed in convenient locations for user interaction, but the audio interference degrades signal-to-interference ratios and reduces keyword detection and speech recognition accuracy
Solution Approach 1:
The audio signal is segmented into multiple frequency subbands using subband analysis. This allows the system to process different frequency components separately, identifying and suppressing interference in specific bands while preserving speech frequencies, thereby maintaining detection accuracy even in noisy environments
Solution Approach 2:
An adaptive filter acts as an intermediary between the noisy microphone input and the speech recognition system. The filter processes the audio signal by estimating and subtracting interference components, producing a cleaned signal that improves keyword detection accuracy without requiring physical separation from interference sources
2Measurement precision
If acoustic echo cancellation and noise reduction techniques are applied, then signal-to-interference ratios improve by up to 40 dB, but the processing complexity and computational requirements increase
Solution Approach 1:
By dividing the audio spectrum into subbands, the system can apply targeted processing to each band rather than processing the entire spectrum uniformly. This segmentation reduces the computational burden per band while achieving cumulative interference reduction across all bands, improving signal-to-interference ratio with manageable complexity
Solution Approach 2:
The system uses adaptive filtering with feedback mechanisms that continuously adjust filter coefficients based on the measured interference characteristics. This feedback approach allows the system to automatically adapt to changing acoustic environments without requiring manual reconfiguration, reducing the operational complexity while maintaining high signal-to-interference ratios
Data Source
AI summary
Methods and systems for audio interference cancellation are disclosed. A first beamforming zone associated with a location of a first audio source may be determined. A second beamforming zone associated with a location of a second audio source may be determined. Based on determining that first audio associated with the first audio source dominates a first frequency band associated with the first beamforming zone and the second beamforming zone, prevention of attenuation of audio output in the first beamforming zone and within the first frequency band may be caused. Based on determining that second audio associated with the second audio source dominates a second frequency band associated with the first beamforming zone and the second beamforming zone, attenuation of audio output in the first beamforming zone and within the second frequency band may be caused.