Noise Estimation Device for Moving Object Sound Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing noise estimation methods fail to accurately distinguish noise from moving object sounds due to not considering acoustic characteristics, leading to decreased detection accuracy.

Innovation Solution

A noise estimation device that performs frequency analysis on observation signals to separate noise and moving object sounds using acoustic characteristic information, estimating noise amounts in specific time-frequency domains and removing noise to enhance detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If noise suppression is performed based on general noise data without considering acoustic characteristics of moving object sound, then noise suppression can be applied, but noise cannot be stably suppressed and detection accuracy decreases

Engineering Contradiction:

Improvedetection accuracyVSAvoidnoise suppression stability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent applies local quality by estimating noise characteristics specifically in time-frequency domains where moving object sound is present, rather than applying uniform noise suppression across all frequencies. The noise estimation is localized to regions affected by moving object sound based on acoustic characteristic information, enabling precise noise suppression that preserves the target sound while removing background noise effectively

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent changes the parameters of noise estimation by using acoustic characteristic information of moving object sound to adaptively estimate noise characteristics. Instead of using fixed noise models, the system dynamically adjusts noise estimation parameters based on the presence and characteristics of moving object sound, improving both detection accuracy and suppression stability

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If noise suppression is performed using general noise data, then some noise reduction is achieved, but the noise amount cannot be accurately estimated in domains containing moving object sound

Engineering Contradiction:

Improvenoise amount estimation accuracyVSAvoidapplicability to moving object sound environments

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent performs preliminary action by estimating noise characteristics in advance in time-frequency domains where moving object sound is present. By using acoustic characteristic information to identify these domains beforehand, the system can pre-estimate noise amounts and apply appropriate suppression, improving both accuracy and adaptability to moving object sound environments

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11996077B2Noise estimation device, moving object sound detection device, noise estimation method, moving object sound detection method, and non-transitory computer-readable medium

Publication Date: 2024.05.28 NEC CORP

AI summary

Provided is a noise estimation device capable of appropriately estimating the amount of noise in an observation signal. The noise estimation device includes: frequency analysis processing means for receiving an input of an observation signal that includes a moving object sound output from an moving object and noise and transforming the observation signal into a feature in each of time-frequency domains; noise range estimation means for estimating a first feature in a first time-frequency domain to which only the noise belongs based on acoustic characteristic information of the moving object sound and the feature; and amount-of-noise estimation means for estimating an amount of noise in a second time-frequency domain to which the moving object sound belongs based on the first feature.