JP5360815B2 - Speech training support apparatus and program thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a vocalization training support device capable of training blowing force and timing of breath a trained person, as an assistant for an expert trainer. <P>SOLUTION: This vocalization training support device supports a training for a blowing intensity and the timing of the breath, when the trained person challenged in vocalization functions performs the vocalization training, and includes: a model storage means 17 for storing preliminarily prepared models of the blowing intensity and the timing of the breath; a display means 15 for displaying the prescribed model read out of the model storage means 17, and for stimulating the start of the training to the trained person, detecting means 12, 13, 14 for detecting the breath blown by the trained person according to the displayed model, and for measuring the blowing intensity and the timing of the blown breath; and a comparison-evaluation means 19 for comparing the displayed model with the blowing intensity and the timing of the breath detected by the detecting means, and for evaluating the degree attained of the training, based on a comparison result. <P>COPYRIGHT: (C)2011,JPO&amp;INPIT

Description

  The present invention relates to an utterance training support apparatus for a person with a disability in the utterance function and a program thereof.

Voices, such as those who are deaf or congenitally deaf, those who have lost their vocal cord function due to illness or accident such as stroke or throat cancer, or who have a mental illness such as autism At present, speech function recovery training for persons with functional disabilities is being conducted under a specialized trainer such as a speech auditor.
However, since there is a limit to the number of trainees a single trainer can handle, there is a need for the development of a speech training support device that can perform speech training with the assistance of trainers. Therefore, various utterance training support devices have been proposed to meet such demands (see, for example, Patent Documents 1 and 2).

By the way, in order to perform vocal training, it is indispensable to train articulators such as mouth, tongue, vocal cords, etc. In addition, training of breathing strength and timing is also important.
Focusing on such training, for example, Patent Document 3 discloses utterance pronunciation practice in which a specified vowel is pronounced, a breath is made continuously, or a voice is uttered at a certain volume. An apparatus is described.

JP-A-8-305277 JP-A-7-5807 JP-A-11-352875

However, the apparatus described in Patent Document 3 is premised on producing a voice, and cannot train breath blowing strength and timing, which are one of the important elements for utterance.
An object of the present invention is to provide an utterance training support apparatus and a program suitable for training the strength and timing of breath blowing necessary for utterance, and capable of utterance training by a trainee alone or as a trainee alone. And

The present invention has been made to meet the above requirements, and the invention according to claim 1 supports the training of breath blowing strength and timing when trainees with speech dysfunction perform speech training. An utterance training support device, which displays a model storage means for storing a breath blow strength and timing model prepared in advance, and a predetermined model read out from the model storage means, and starts training for a trainee. Display means for prompting, detecting means for detecting the breath blown by the trainee in accordance with the displayed model, and measuring the strength and timing of the blown breath; the displayed model and the breath detected by the detecting means; comparing means for comparing the strength and timing balloon, and evaluation means for evaluating the degree of achievement of training from the comparison result, each trainee including evaluation result by the evaluation means According to the history storage means for storing the training history and the training history for each trainee stored in the history storage means, the model to be used by the trainee for the next training is selected from the model storage unit. And a model selection means .
According to this configuration, the trainee can perform training according to the model displayed on the display means, and can check the achievement level after the training is completed.

As described in claim 2, by displaying the model and the detection result of the detection means on the display means, the result of training can be confirmed visually.
Further, as described in claim 3, wherein the model is more prepared from difficulty is low level to a high level, the model selecting means, the history of training for each trainee stored in the history storing means Accordingly, the trainee may select a model to be used for the next training from the model storage unit .
With this configuration, it is possible to automatically select an optimal model to be used for the current training in accordance with the degree of achievement of the trainee's training.

Furthermore, as described in claim 4 , the detection means may include a mouthpiece that is formed in the shape of a mouth of a voice to be uttered and a trainee holds in his mouth and blows out a breath. .
By using such a mouthpiece, it is possible to perform utterance training according to the shape of the mouth of the voice to be uttered.

According to a fifth aspect of the present invention, there is provided a voicing training support program that supports training of breath blowing strength and timing by a trainee having voicing dysfunction. A step of creating a model and storing it in a model storage unit, a step of reading out the model used for training from the model storage unit, and a display for displaying the read model and prompting a trainee to start training a step of displaying on the strength and timing balloon breath of the trainee, comparing the displayed said model, and evaluating the degree of achievement of the trainee training the comparison result, the evaluation A step of storing a history of training for each trainee including a result in the history storage means, and a trainee read out from the history storage means Depending on the history of training and, the trainees from the model storage unit and executes the steps of selecting a model to be used in the next training.
In addition, as described in claim 6 , it may include a step of displaying the model and the breathing strength and timing of the trainee on the display means. Further, as described in claim 8, the created model is classified from a low difficulty level to a high level and stored in the model storage unit, and the trainee stored in the history storage unit depending on the history of each training, the trainee may alternatively include the step of selecting the model to be used for the next training from the model storage unit.

  ADVANTAGE OF THE INVENTION According to this invention, the utterance training assistance apparatus which can perform utterance training on behalf of a speech auditor or as assistance of a speech auditor can be obtained. Therefore, a large number of trainees can perform training under a small number of trainees, and a trainee can also perform vocal training alone.

1 is a block diagram illustrating a schematic configuration according to an embodiment of an utterance training support apparatus of the present invention. FIG. It is the schematic which shows an example of the mouthpiece formed according to the shape of the mouth of the sound to be uttered. It is an example of the model memorize | stored in a model memory | storage part. It is a figure which shows an example of the display screen displayed on a display part. It is a comparison of timing charts between a model used by a trainee in this training (top) and the training result of the trainee (bottom). It is a flowchart concerning one Embodiment of the utterance training assistance program of this invention.

DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a block diagram illustrating a schematic configuration according to an embodiment of the utterance training support apparatus of the present invention.
The utterance training support device 1 displays a model storage unit 17 that stores a model used for training, a display unit 15 that displays a model read from the model storage unit, and prompts a trainee to start training, and the like. According to the model displayed on the display unit 15, a straw-like detector 12 for the trainee to breathe in, a measuring unit 13 for detecting the strength of the breath blown into the detector 12, and the measuring unit 13 The chart creation unit 14 creates a timing chart similar to the model by associating the strength of the breath measured by the timing (time passage), and the timing chart and chart creation unit 14 of the model displayed on the display unit 15. CPU 19 provided with a comparison / evaluation unit that compares the timing chart created by the above and evaluates the achievement level of training from the comparison result. Eteiru. Reference numeral 16 denotes an input unit such as a keyboard, a mouse, or a touch panel for inputting a model or a trainee's name, and reference numeral 20 denotes a history storage unit for storing a training history for each trainee.

  The detector 12 is for the trainee to hold his tip and breathe in. In this embodiment, the detector 12 is formed in a straw shape. The tip of the detector 12 may be formed in accordance with the shape of the mouth of the voice to be uttered. For example, as shown in FIG. 2, one or a plurality of mouthpieces that are formed according to the shape of the mouth of the voice to be uttered are prepared, and a predetermined mouthpiece is attached to the tip of the detector 12. Also good. FIG. 2 shows an example of the basic shape of the mouthpiece. (A) shows the shape of the mouth of “A” (left) and the basic shape of the mouthpiece (right) simulating this mouth shape, (b) It shows the shape of the mouth of “I” (left) and the basic shape of the mouthpiece (right) simulating this mouth shape. By using such a mouthpiece, it is possible to perform breathing and timing utterance training according to the shape of the mouth.

The measurement part 13 can use a well-known various thing, if the trainee can measure the strength of the breath which breathed in the detector 12. FIG. For example, there may be mentioned a device that measures the strength of the breath from the pressure of the breath that has been blown in and the rotational speed of the impeller, and a device that measures the strength of the breath from the inclination angle of the plate that is inclined by blowing the breath.
In this embodiment, the detector 12, the measurement unit 13, and the chart creation unit 14 constitute detection means.

FIG. 3 is an example of a model stored in the model storage unit 17.
The model is created by a trainer using this apparatus and stored in the model storage unit 17. In this embodiment, the model is a timing chart represented by breath blowing strength (vertical axis) and time (horizontal axis).
In the example shown in the figure, the difficulty of training increases as the process proceeds from (i) → (ii) → (iii) → (iv). Each time a trainee clears one model, the trainee can proceed to the next model and perform more advanced training.
The model selection unit 18 selects one model corresponding to the trainee from the models stored in the model storage unit 17 and causes the display unit 15 to display the model.

FIG. 4 shows a display example of the display unit 15. In the example of FIG. 4, the display unit 15 displays the model used in the current training, the date and time of training, the name of the trainee and the model number used in the current training, Additional information such as evaluation results and past training history is displayed.
The training starts when the trainee operates the start button and ends when the end button is pressed. When the start button is operated, the arrow at the bottom left of the screen moves to the right at a constant speed. The trainee breathes into the detector 12 when the arrow reaches the left end of the white square. The strength of the breath to be blown is represented by the height of the white square. In this embodiment, there are three levels of strong, medium, and weak. However, it is possible to have two levels of strength and four levels or more.

The comparison / evaluation unit of the CPU 19 compares the timing chart created by the chart creation unit 14 with the model timing chart used for the training after the training is completed, and evaluates the coincidence.
FIG. 5 is a comparison between a model used by a trainee in this training (upper) and a timing chart which is the current training result of the trainee (lower).
The chart creation unit 14 divides the detected trainee's breath strength into three levels of strong, medium, and weak just like the model, and the timing chart as shown in the lower part of FIG. Create Since the actual trainee's operation is somewhat delayed with respect to the movement of the arrow moving the display unit 15 from left to right, the chart creation unit 14 performs delay correction as necessary when creating the timing chart.

In the example shown in FIG. 5, it is understood that the trainee is able to adjust the breath strength well, but is slightly poor at timing adjustment.
The comparison / evaluation unit of the CPU 19 evaluates the training result based on, for example, the similarity of the shapes of both timing charts, and permits progress to the next step for those exceeding a certain evaluation value. As the shape similarity evaluation means, for example, those known in Japanese Patent Application Laid-Open No. 11-316846 and Japanese Patent Application Laid-Open No. 8-249426 can be used.

When the comparison / evaluation unit of the CPU 19 permits the model selection unit 18 to proceed to the next step, the model selection unit 18 is easier than the previously used model among the models stored in the model storage unit 17. A model with a high degree of degree is selected, and if it is not permitted, a model with the same difficulty level as the model used previously is selected.
In this embodiment, the history storage unit 20 includes past training history (training date and time, model used, training result and evaluation) for each trainee, together with identification information such as the trainee's name and date of birth. Results). The CPU 19 determines whether the trainee is a registered trainee at the start of training by referring to the history storage unit 20, and the model selection unit 18 stores the past history of the trainee stored in the history storage unit 20. From this, the model to be selected is determined.

Although the configuration of the generation training support apparatus 1 of the present invention has been described, the generation training support apparatus 1 of the present invention can use a commercially available personal computer (PC) except for the detector 12 and the measurement unit 13. And the use as the generation | occurrence | production training assistance apparatus 1 is attained by installing the utterance training assistance program demonstrated below in this PC.
Hereinafter, an embodiment of the utterance training support program of the present invention will be described together with the operation of the utterance training support apparatus 1 having the above configuration.
FIG. 6 is a flowchart for explaining the configuration of an utterance training support program according to an embodiment of the present invention.
At the start of training, the apparatus 1 is activated and information (name, ID number, password, etc.) regarding the trainee is input from the input unit 16 (step S1).

The CPU 19 determines whether the trainee is a registered trainee by inquiring the history storage unit 20 from the input information (step S2).
If it is determined in step S2 that the history information does not exist, the CPU 19 causes the display unit 15 to display a display prompting the trainee to input again or prompting a new registration procedure.
If the history information exists in step S2, the CPU 19 permits the start of training. And the model selection part 18 selects the model used for this training from the models memorize | stored in the model memory | storage part 17 from the past history of the said training student memorize | stored in the log | history memory | storage part 20 (step S3). . The selected model is displayed on the display unit 15 and prompts the trainee to start training (step S4).
Although not shown, a plurality of types of models are created in advance by a trainer using a device similar to the generation training support device 1 shown in FIG. 1 and stored in the model storage unit 17.

The chart creation unit 14 creates a training result of the trainee as a timing chart (step S5).
When the trainee presses the end button to end the training (step S6), the comparison / evaluation unit of the CPU 19 evaluates the training result (step S7).
As a result, if it is recognized that a certain standard is cleared (step S8), the CPU 19 permits the progress to the next step (step S10), and displays whether to proceed to the next step and continue the training. The trainee is inquired through 15 (step S11).

If it is determined that it has not been cleared (step S8), the CPU 10 inquires of the trainee whether or not to retrain with the same model through the display unit 15 (step S9).
If the trainee does not wish to retrain or continue training in step S9 or step S11, the training is terminated.
If the trainee wishes to retrain in step S9, the process returns to step S4 to resume the training with the same model as the previous time. If the trainee wishes to continue training in step S11, the process returns to step S3, selects the model of the next step, and reunites training with the model.
The program of this embodiment that executes each of the above steps is installed in a terminal device such as a personal computer through download via the FD, CD, DVD, MO, MD, flash memory, SD or other storage medium or the Internet. It becomes possible to execute.

Although a preferred embodiment of the present invention has been described, the present invention is not limited to the above-described embodiment.
For example, although the chart creation unit 14 and the model selection unit 18 have been described as being provided separately from the CPU 19 in the above embodiment, these may be provided in the CPU 19.
In the above example, the model selection unit 18 has been described as selecting one model from the plurality of models stored in the model storage unit 17 according to the achievement level of the trainee and displaying the selected model on the display unit 15. However, the model selection unit 18 may display part or all of the models stored in the model storage unit 17 on the display unit 15 so that the trainee can select one model.
Furthermore, in the above description, the model stored in the model storage unit 17 has been described as a timing chart, but the breath blowing strength, length, and timing may be represented by signal sound or light. In the above description, a rectangular model has been described as an example, but a triangle or waveform model may be used.
Further, by using the apparatus and program of the present invention, it is possible to train not only the balloon but also the suction and its timing.

  The present invention can be widely applied to utterance training support for a person with a disability in the utterance function.

DESCRIPTION OF SYMBOLS 1 Speech training assistance apparatus 12 Detector 13 Measurement part 14 Chart preparation part 15 Display part 16 Input part 17 Model storage part 18 Model selection part 19 CPU
20 History storage unit

Claims (7)

When a trainee with speech dysfunction performs speech training, it is a speech training support device that supports training of breath blowing strength and timing,
Model storage means for storing a model of breath blowing strength and timing created in advance;
A display unit that displays a predetermined model read from the model storage unit and prompts the trainee to start training; and
Detecting means for detecting the breath blown by the trainee according to the displayed model and measuring the strength and timing of the blown breath;
A comparison means for comparing the displayed model with the breath blowing strength and timing detected by the detection means;
An evaluation means for evaluating the achievement level of the training from the comparison result ,
History storage means for storing a history of training for each trainee including an evaluation result by the evaluation means;
In accordance with the training history of each trainee stored in the history storage means, model selection means for selecting a model that the trainee should use for the next training from the model storage unit;
An utterance training support apparatus characterized by comprising: The utterance training support apparatus according to claim 1, wherein the display unit displays the model and a detection result of the detection unit. The model is more prepared from difficulty is low level to a high level, the model selecting means, according to the history of training for each trainee stored in the history storage unit, the trainee to the next training utterance training support apparatus according to claim 1 or 2, characterized in that selecting a model to be used from the model storage unit. It said detecting means is formed in the shape of the voice of the mouth to be uttered, according to any one of claims 1 to 3, trainee, characterized in that it comprises a mouthpiece for performing balloon of breath example mouth to mouth Voice training support device. A speech training support program that supports training of breath blowing strength and timing by trainees with speech dysfunction,
Creating a model of breath blowing strength and timing and storing it in a model storage unit;
Reading out the model used for training from the model storage unit;
Displaying on the display means a display for displaying the read model and prompting a trainee to start training;
Comparing the trainee's breath blowing strength and timing with the displayed model;
And evaluating the degree of achievement of the trainee training the comparison result,
Storing a history of training for each trainee including the result of the evaluation in history storage means;
Selecting a model that the trainee should use for the next training from the model storage unit according to the training history of each trainee read from the history storage means;
A vocal training support program characterized by The utterance training support program according to claim 5 , further comprising: displaying the model and the breathing strength and timing of the trainee on the display unit. The model created, the steps of classifying a lower difficulty level to a high level is stored in the model storage unit, depending on the history of training for each trainee stored in the history storage unit, the training The utterance training support program according to claim 5 , further comprising: selecting from the model storage unit a model to be used by the student for the next training .

Images