Oral Function Evaluation via Voice Prosody Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for evaluating oral function, such as those requiring appliances or visual inspections, can be uncomfortable and may overlook deterioration in elderly individuals, leading to undernutrition and increased risk of aspiration pneumonia due to inadequate assessment.
Innovation Solution
An oral function evaluation method that involves obtaining voice data from an individual uttering specific syllables or phrases, extracting prosody features, and calculating an estimated oral function value using an oral function estimating equation to assess deterioration state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an appliance is put on the neck to evaluate oral function, then evaluation accuracy is improved, but ease of operation deteriorates due to discomfort and burden on the evaluatee
Solution Approach 1:
The patent replaces the mechanical appliance worn on the neck with an acoustic evaluation system that uses voice analysis. Instead of mechanical sensors contacting the body, the system captures voice signals and extracts prosody features to assess oral function, thereby eliminating the discomfort and burden of wearing an appliance while maintaining evaluation capability
Solution Approach 2:
The patent introduces voice as an intermediary medium to indirectly assess oral function. Rather than directly measuring oral parameters with contact-based appliances, the system uses voice characteristics (prosody features) as a mediator that reflects oral function state, enabling non-contact evaluation
2Ease of operation
If visual inspection or interview is used to evaluate oral function, then ease of operation is improved, but measurement precision deteriorates leading to overlooked deterioration
Solution Approach 1:
The patent replaces subjective visual inspection and interview methods with an objective acoustic analysis system. Instead of relying on specialist observation and patient reporting, the system automatically extracts and analyzes prosody features from voice data, providing quantifiable and consistent measurements that reduce the risk of overlooking deterioration
Solution Approach 2:
The patent implements an automated feedback mechanism where the evaluation system continuously analyzes voice characteristics and provides objective assessment results. This feedback loop enables consistent monitoring of oral function changes over time, reducing reliance on intermittent specialist assessments and helping detect deterioration that might be missed during casual observation
Data Source
AI summary
An oral function evaluation method includes: obtaining voice data obtained by collecting a voice of an evaluatee uttering a syllable or a fixed phrase that includes (i) two or more morae including a change in a first formant frequency or a change in a second formant frequency or (ii) at least one of a flap, a plosive, a voiceless sound, a double consonant, or a fricative; extracting a prosody feature from the voice data obtained; calculating an estimated value of an oral function of the evaluatee, based on the prosody feature extracted and an oral function estimating equation calculated based on a plurality of training data items; and evaluating an oral function deterioration state of the evaluatee by assessing the estimated value using an oral function evaluation indicator.