Hearing Device Speech Quality Analysis via Articulatory Properties

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing noise suppression algorithms in hearing devices often deteriorate sound quality by applying unnecessary noise reduction, even when speech is still intelligible, and fail to accurately assess speech quality in noisy environments, leading to reduced voice quality.

Innovation Solution

A method and device that objectively evaluate speech quality by analyzing articulatory and prosodic properties of the speech signal, using an acousto-electric input transducer and signal processing to derive a quantitative measure based on parameters like formant precision, consonant dominance, and prosodic features, independent of external noise factors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If noise suppression algorithms are applied to improve speech intelligibility, then speech intelligibility is improved, but sound quality deteriorates due to artifacts and unnatural auditory impression

Engineering Contradiction:
Improvespeech intelligibilityVSAvoidnoise suppression artifacts
Core Design Contradiction:
Loss of informationVSObject-generated harmful factors

Solution Approach 1:

The patent changes the control parameter from signal-to-noise ratio (SNR) to speech quality parameters such as formant precision, consonant dominance, and articulation clarity. This allows the noise suppression algorithm to adapt its strength based on the actual speech quality needs rather than just noise levels, reducing artifacts while maintaining intelligibility

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system continuously analyzes speech quality parameters in real-time and uses this feedback to dynamically adjust the noise suppression algorithm. The speech quality analyzer provides feedback about formant precision and articulation clarity, which controls the intensity of noise suppression to prevent degradation of natural sound quality

Inventive Principle:
Principle #23Feedback

2Object-affected harmful factors

If noise suppression is applied based on signal-to-noise ratio, then noise reduction is achieved, but unnecessary noise suppression is applied when speech remains intelligible, deteriorating sound quality

Engineering Contradiction:
Improvebackground noiseVSAvoidunnecessary noise suppression
Core Design Contradiction:
Object-affected harmful factorsVSObject-generated harmful factors

Solution Approach 1:

The patent replaces SNR-based control with speech quality parameter-based control. Instead of suppressing noise based solely on signal-to-noise ratio thresholds, the system monitors formant precision, consonant dominance, and articulation clarity to determine when noise suppression is actually needed, avoiding unnecessary processing that degrades sound quality

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary analysis of speech quality parameters before applying noise suppression. By evaluating formant precision and articulation clarity in advance, the system can predict when noise suppression would be beneficial and when it would be unnecessary, preventing premature or inappropriate noise reduction

Inventive Principle:
Principle #10Preliminary action

3Object-generated harmful factors

If speech quality assessment is performed to control noise suppression, then sound quality is preserved, but measurement complexity increases due to need for articulatory property analysis

Engineering Contradiction:
Improvesound quality deteriorationVSAvoidsignal processing complexity
Core Design Contradiction:
Object-generated harmful factorsVSDevice complexity

Solution Approach 1:

The patent segments the speech signal analysis into distinct components: formant detection, consonant dominance measurement, and articulation clarity assessment. Each component is processed separately using dedicated algorithms, which simplifies the overall complexity compared to attempting to analyze all speech properties simultaneously

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces speech quality parameters as intermediary measures between the raw audio signal and the noise suppression control. These parameters (formant precision, consonant dominance, articulation clarity) serve as intermediate representations that simplify the control task while still capturing the essential speech quality characteristics

Inventive Principle:
Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach improves speech quality assessment by focusing on intrinsic speech production properties, reducing unnecessary noise reduction and enhancing intelligibility, especially in quiet environments, while maintaining natural sound perception.

Implementation Method 1

a sound containing the speech signal is recorded from an environment of the hearing device by means of an acousto-electrical input transducer of the hearing device and converted into an input audio signal

Methodology Applied
Scientific EffectAcousto-electrical transduction: Electromagnetic Induction

Data Source

PatentEP3962115B1Method for evaluating the speech quality of a speech signal by means of a hearing device
Publication Date: 2024.12.18 SIVANTOS PTE LTD
  • EP3962115B1 patent drawingFigure 1
  • EP3962115B1 patent drawingFigure 2

AI summary

The invention relates to a method for evaluating the speech quality of a speech signal (18) using a hearing device (1), wherein a sound (6) containing the speech signal (18) is picked up from an environment of the hearing device (1) by means of an acousto-electrical input transducer (4) of the hearing device (1) and converted into an input audio signal (8), wherein at least one articulatory and/or prosodic property of the speech signal (18) is quantitatively recorded by analyzing the input audio signal (8) using signal processing, and wherein a quantitative measure (30) for the speech quality is derived depending on the at least one articulatory or prosodic property.The invention further relates to a hearing device (1) comprising an acousto-electrical input transducer (4) which is configured to receive a sound (6) from an environment of the hearing device (1) and convert it into an input audio signal (8), and a signal processing device (10) which is configured to quantitatively detect at least one articulatory and/or prosodic property of a portion of a speech signal (18) contained in the input audio signal (8) by means of an analysis of the input audio signal (8) and to derive a quantitative measure (30) for speech quality depending on the at least one articulatory or prosodic property.