MMSE Determiner With Externally Estimated SNR Modifiers

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The OLSA modification of Log-MMSE noise estimation suffers from increased musical noise in low signal-to-noise ratio situations and over-suppression of weak speech in noisy conditions.

Innovation Solution

An enhanced MMSE determiner is introduced, which modifies the speech presence probability using a sigmoid function responsive to real-time signal-to-noise ratios to reduce over-attenuation and improve noise suppression, particularly in low SNR conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the OLSA modification of Log-MMSE noise estimation is used to achieve maximum attenuation, then noise suppression performance is improved, but musical noise increases in low SNR situations and weak speech is over-suppressed

Engineering Contradiction:

Improvenoise suppression performanceVSAvoidmusical noise

Core Design Contradiction:

ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent applies dynamics by making the speech presence probability modification adaptive to real-time SNR conditions. The system dynamically adjusts the modification factor based on current SNR measurements, transitioning between different suppression strategies depending on whether the environment is noisy or clean, thereby avoiding fixed-parameter drawbacks

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of speech presence probability modification based on SNR conditions. By using an external SNR estimator to determine when to apply the OLSA modification and adjusting the modification factor accordingly, the system optimizes noise suppression while preventing musical noise and over-suppression of weak speech

Inventive Principle:

Principle #35Parameter changes

2Reliability

If the OLSA modification of Log-MMSE noise estimation is used to achieve maximum attenuation, then noise suppression performance is improved, but weak speech is over-suppressed in noisy conditions

Engineering Contradiction:

Improvenoise suppression performanceVSAvoidweak speech

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent changes the speech presence probability parameter based on external SNR estimation. When SNR is low, the modification factor is reduced or disabled, preventing over-suppression of weak speech while maintaining effective noise suppression when SNR is high

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from an external SNR estimator to control the application of OLSA modification. The SNR measurement provides real-time feedback about acoustic conditions, allowing the system to adjust its suppression strategy and avoid losing weak speech information in noisy environments

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS9761245B2Externally estimated SNR based modifiers for internal MMSE calculations

Publication Date: 2017.09.12 CONTINENTAL AUTOMOTIVE SYSTEMS INC

AI summary

Acoustic noise in an audio signal is reduced by calculating a speech probability presence (SPP) factor using minimum mean square error (MMSE). The SPP factor, which has a value typically ranging between zero and one, is modified or warped responsive to a value obtained from the evaluation of a sigmoid function, the shape of which is determined by a signal-to-noise ratio (SNR), which is obtained by an evaluation of the signal energy and noise energy output from a microphone over time. The shape and aggressiveness of the sigmoid function is determined using an extrinsically-determined SNR, not determined by the MMSE determination.