Oral function evaluation device, oral function evaluation system, and oral function evaluation method

An oral function evaluation system that evaluates a deterioration state of oral function of an evaluatee from a voice uttered by the evaluatee, the oral function evaluation system comprising:

• a terminal;
• and
• an oral function evaluation device connected to the terminal, wherein
• the terminal includes:
• a sound collection device used for collecting a voice uttered by the evaluatee;
• and
• a presentation device that presents the deterioration state of the oral function of the evaluatee evaluated,
• the oral function evaluation device includes:
• an obtainer that obtains voice data obtained by collecting the voice uttered by the evaluatee;
• an extractor that extracts one or more features from the voice data obtained;
• an S/N ratio calculator that, using the voice data obtained, calculates a first average intensity of a sound collected in a period in which the evaluatee does not utter a voice and a second average intensity of a sound collected in a period in which the evaluatee utters a voice, and calculates a signal-to-noise (S/N) ratio that is a ratio of the second average intensity to the first average intensity;
• a determiner that determines an estimating equation to be used for evaluation of the oral function of the evaluatee;
• a calculator that calculates an estimate value of the oral function of the evaluatee, based on the estimating equation determined and the one or more features extracted;
• and
• an evaluator that evaluates the deterioration state of the oral function of the evaluatee by assessing the estimate value using an oral function evaluation indicator, and
• the determiner:
• determines a first estimating equation as the estimating equation when the S/N ratio calculated is greater than a first threshold, the first estimating equation being an estimating equation that includes a feature related to sound pressure among the one or more features extracted from the voice data;
• and
• determines a second estimating equation as the estimating equation when the S/N ratio calculated is less than or equal to the first threshold, the second estimating equation being an estimating equation that does not include the feature related to sound pressure.

An oral function evaluation method of evaluating a deterioration state of oral function of an evaluatee from a voice uttered by the evaluatee, the oral function evaluation method being a method to be performed by a terminal and an oral function evaluation device and comprising:

• obtaining voice data by the terminal collecting a voice uttered by the evaluatee;
• obtaining, by the oral function evaluation device, the voice data;
• extracting, by the oral function evaluation device, one or more features from the voice data obtained;
• calculating, by the oral function evaluation device, using the voice data obtained, a first average intensity of a sound collected in a period in which the evaluatee does not utter a voice and a second average intensity of a sound collected in a period in which the evaluatee utters a voice, and calculating an S/N ratio that is a ratio of the second average intensity to the first average intensity;
• determining, by the oral function evaluation device, an estimating equation to be used for evaluation of the oral function of the evaluatee;
• calculating, by the oral function evaluation device, an estimate value of the oral function of the evaluatee, based on the estimating equation determined and the one or more features extracted;
• evaluating, by the oral function evaluation device, the deterioration state of the oral function of the evaluatee by assessing the estimate value using an oral function evaluation indicator;
• and
• presenting, by the terminal, the deterioration state of the oral function of the evaluatee evaluated, wherein
• the determining of the estimating equation includes:
• determining a first estimating equation as the estimating equation when the S/N ratio calculated is greater than a first threshold, the first estimating equation being an estimating equation that includes a feature related to sound pressure among the one or more features extracted from the voice data;
• and
• determining a second estimating equation as the estimating equation when the S/N ratio calculated is less than or equal to the first threshold, the second estimating equation being an estimating equation that does not include the feature related to sound pressure.