Dynamic Noise Reduction for Speech Clarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech enhancement systems in vehicles fail to effectively improve speech intelligibility and quality in high noise conditions due to equal noise suppression across all frequencies, leading to residual noise and degradation of the desired signal, especially at lower frequencies, and often compromise the clarity of the signal by attenuating the first formant frequency.
Innovation Solution
A dynamic noise reduction system that selectively attenuates background noise more aggressively at lower frequencies around the first formant and less at the second formant, using a dynamic suppression factor based on the noise power spectrum, allowing for real-time adaptation to changing noise conditions and minimizing residual noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If equal noise suppression is applied across all frequencies, then noise reduction is achieved, but residual noise increases and signal quality degrades
Solution Approach 1:
The patent applies different noise suppression gains to different frequency bands. Specifically, it uses a first gain for frequencies below a threshold and a second gain for frequencies above the threshold, where the gains are different. This local differentiation allows aggressive noise suppression in low frequencies while preserving signal quality in high frequencies, resolving the contradiction between noise reduction and signal quality.
2Object-affected harmful factors
If aggressive noise suppression is applied at low frequencies, then noise reduction is improved, but signal clarity is degraded
Solution Approach 1:
The patent dynamically changes the suppression gain parameter based on the estimated noise power spectrum and signal characteristics. The system adjusts the gain values adaptively, using higher suppression at low frequencies when noise is present while maintaining lower suppression at high frequencies to preserve signal clarity. This parameter adaptation resolves the contradiction between noise reduction and signal clarity.
3Device complexity
If uniform suppression factor is used, then system complexity is reduced, but adaptability to changing noise conditions is lost
Solution Approach 1:
The patent implements a dynamic noise suppression system where the suppression gains are continuously adapted based on real-time noise estimation. The system updates the noise power spectrum estimate and recalculates the optimal gains for different frequency bands, allowing it to adapt to changing noise conditions. This dynamic approach maintains reasonable complexity while achieving high adaptability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A speech enhancement system improves the speech quality and intelligibility of a speech signal. The system includes a time-to-frequency converter that converts segments of a speech signal into frequency bands. A signal detector measures the signal power of the frequency bands of each speech segment. A background noise estimator measures a background noise detected in the speech signal. A dynamic noise reduction controller dynamically models the background noise in the speech signal. The speech enhancement renders a speech signal perceptually pleasing to a listener by dynamically attenuating a portion of the noise that occurs in a portion of the spectrum of the speech signal.