Training apparatus, method of the same and program

A training device for performing utterance training upon a subject, the training device comprising a processor configured to execute a method comprising:

• determining, based on a picked-up speech signal, a first formant frequency and a second formant frequency;
• converting the picked-up speech signal using a lowpass filter with a cutoff frequency being a first predetermined value or a second predetermined value greater than the first predetermined value to the picked-up speech signal;
• adding high-pass noise to the converted speech signal;
• feeding back the converted speech signal with the high-pass noise added to a subject;
• and
• determining an evaluation based on:
• pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted by application of the first predetermined value as the cutoff frequency to the subject, and
• pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted by application of the second predetermined value as the cutoff frequency to the subject,
• wherein whether to make the subject conduct utterance training with a same utterance content repeatedly or not is determined based on a relation of magnitude between the evaluation and a predetermined threshold.

A computer implemented method for training utterance of a subject, comprising:

• determining, based on a picked-up speech signal, a first formant frequency and a second formant frequency;
• converting, based on a use of a lowpass filter with a cutoff frequency being a first predetermined value with or without change of feedback formant frequencies which are formant frequencies of the picked-up speech signal, the picked-up speech signal;
• adding high-pass noise to the converted speech signal;
• feeding back the converted speech signal with the high-pass noise added to a subject;
• calculating a compensatory response vector by using:
• pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted with change of the feedback formant frequencies to the subject, and
• pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted without change of the feedback formant frequencies to the subject;
• and
• determining an evaluation based on the compensatory response vector and a correct compensatory response vector, wherein whether to make the subject conduct utterance training with a same utterance content repeatedly or not is determined based on a relation of magnitude between the evaluation and a predetermined threshold.