Audio Distractor Attenuator for Speech Intelligibility
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio devices face challenges in improving audio quality and intelligibility, particularly in voice pick-up, due to variations in microphone sensitivity, finite production tolerances, and the presence of different noise types simultaneously. Additionally, beamforming with multiple beamformers struggles with stability and computational load.
Innovation Solution
The audio device comprises an interface, memory, and a processor configured to obtain and process multiple microphone input signals. It determines distractor indicators and attenuation parameters to apply noise suppression schemes, enhancing speech quality and intelligibility while reducing processing requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If beamforming with multiple beamformers is used to improve audio quality and noise suppression, then speech intelligibility is improved, but computational load and processing complexity increase
Solution Approach 1:
The audio signal is divided into multiple frequency bands, with different beamforming processing applied to each band. This segmentation allows complex beamforming to be broken down into manageable frequency-specific operations, reducing overall computational load while maintaining speech intelligibility across the full audio spectrum
Solution Approach 2:
Different beamforming strategies and parameters are applied to different frequency bands based on their specific characteristics. Speech-critical frequency bands receive more aggressive beamforming processing, while other bands use lighter processing, optimizing the balance between speech intelligibility and computational efficiency
2Measurement precision
If multiple beamformers are used to suppress different noise types, then audio quality is improved, but system stability deteriorates
Solution Approach 1:
The beamforming system dynamically adjusts its parameters and processing intensity based on real-time noise detection and classification. When multiple noise types are detected, the system adaptively modifies beamformer weights and processing depth, maintaining stability by avoiding overly aggressive processing that could cause oscillations or divergence
Solution Approach 2:
The system continuously monitors the output of beamforming operations and uses this feedback to adjust processing parameters. When instability is detected in the beamformed signal, the system reduces processing intensity or adjusts weights to restore stability, creating a closed-loop control mechanism that maintains reliable operation
3Measurement precision
If aggressive noise suppression is applied to improve speech quality, then speech intelligibility is improved, but processing requirements and computational load increase
Solution Approach 1:
The system varies processing parameters such as beamforming depth, frequency band selection, and noise suppression intensity based on the detected noise level and speech characteristics. This allows aggressive processing to be applied only when and where it is most beneficial, reducing overall computational energy requirements while maintaining speech intelligibility in critical scenarios
Data Source
AI summary
An audio device comprising an interface, memory, and a processor is disclosed. A first microphone input signal and a second microphone input signal is processed for provision of an output audio signal; and output the output audio signal, wherein to process the microphone signals determine a first distractor indicator based on features associated with the input signals; determine a first distractor attenuation parameter based on the first distractor indicator; determine a second distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal; determine a second distractor attenuation parameter based on the second distractor indicator; determine an attenuator gain based on the first distractor attenuation parameter and the second gain compensation parameter; and apply a noise suppression scheme to a first beamforming output signal according to the attenuator gain for provision of the output audio signal.