Adaptive Gain Control for Vehicle Sound Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing sound recognition systems in vehicles face challenges in accurately recognizing user commands amidst high levels of noise, such as engine noise, which affects the performance and reliability of noise elimination and sound recognition.

Innovation Solution

An apparatus and method that utilize a gain acquisition unit to determine a gain and correction value based on the signal-to-noise ratio (SNR) of input signals, employing noise component estimation using algorithms like MCRA and MMSE, and frequency band division for noise processing, to effectively eliminate noise and improve sound recognition rates with minimal computational resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If noise elimination processing is applied to improve sound recognition accuracy, then sound recognition rate is improved, but device complexity increases

Engineering Contradiction:
Improvesound recognition accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the noise elimination process into distinct functional modules: SNR calculation unit, gain calculation unit, and noise elimination processing unit. This segmentation allows each module to perform a specific function independently, improving sound recognition accuracy while keeping the overall system complexity manageable through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic gain adjustment based on real-time SNR calculations. The gain value is dynamically modified according to the calculated SNR, allowing the noise elimination process to adapt to varying noise conditions. This dynamic approach improves recognition accuracy without requiring complex fixed-structure processing.

Inventive Principle:
Principle #15Dynamics

2Reliability

If advanced noise elimination algorithms are used to improve sound recognition in noisy environments, then sound recognition rate is improved, but computational resources increase

Engineering Contradiction:
Improvesound recognition reliabilityVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies noise elimination selectively based on SNR thresholds rather than processing all audio signals uniformly. When SNR exceeds certain thresholds, the system adjusts gain or skips processing, performing partial noise elimination only when necessary. This approach improves reliability in noisy conditions while reducing unnecessary computational resource consumption in quiet environments.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent changes processing parameters (gain values) based on calculated SNR metrics. By adjusting the gain parameter dynamically according to noise levels, the system achieves reliable sound recognition in varying acoustic conditions while optimizing computational resource usage through parameter-based control rather than complex algorithmic changes.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS9472204B2Apparatus and method for eliminating noise, sound recognition apparatus using the apparatus and vehicle equipped with the sound recognition apparatus
Publication Date: 2016.10.18 HYUNDAI MOTOR CO LTD
  • US9472204B2 patent drawing
  • US9472204B2 patent drawing
  • US9472204B2 patent drawing

AI summary

An apparatus for eliminating noise includes: a gain acquisition unit that determines a gain and a correction value of the gain using a signal to noise ratio (SNR) of an input signal; and a gain application unit that acquires an output signal corresponding to the input signal using the determined gain and the determined correction value, wherein the output signal includes an input signal of which noise is eliminated and an input signal of which noise is not eliminated, and a proportion of the input signal of which noise is eliminated and a proportion of the input signal of which noise is not eliminated are determined according to the determined correction value.