KR20220115409A - Speech Training System For Hearing Impaired Person - Google Patents

Abstract

A disclosed vocal language training system for the hearing impaired includes a storage unit for storing learning target information including learning characters, learning pronunciation organ shapes, learning waveforms, and learning frequencies of a learning target; a recognition unit for generating practice information comparable to the learning target information from the language practice of a learner according to the learning target; a correction unit for generating correction information for minimizing a difference between the learning target information and the practice information; and a display unit for displaying the learning target information and the correction information. According to the present invention, language practice and learning efficiency can be maximized.

Description

Speech Training System For Hearing Impaired Person

The present invention (Disclosure) relates to a speech language training system for the deaf, and specifically, by analyzing the voice of the deaf who is engaged in language training in the form of sound waves and also in the form of a language composed of letters, It relates to a speech language training system for the hearing impaired that can maximize learning or training efficiency.

Herein, background information related to the present invention is provided, which does not necessarily imply prior art (This section provides background information related to the present disclosure which is not necessarily prior art).

Methods for deaf people to communicate with the general public include lip reading or speech reading, and sign language or sign language.

However, most of these are for the deaf to communicate to the general public or to learn the communication contents of the general public from the perspective of the hearing impaired.

In other words, there is a limit to the general public's ability to understand the communication of the hearing impaired.

Accordingly, it may be difficult for the general public to communicate with the deaf and hard to have close interpersonal relationships.

Hearing impaired people basically have a physical handicap with significantly lower or no hearing function compared to the general public.

However, in many deaf people, the function of the vocal organs including the vocal cords or the speech organs including the tongue is often normal.

Deaf people with normal functions of speech and pronunciation organs often use sign language or sign language to express their intentions, but at the same time use spoken language on their own, although inaccurately.

However, since the user cannot hear the voice generated by his/her own voice, it is impossible to determine the accuracy of the spoken language as well as the pitch of the voice.

Therefore, since the vocalization and pronunciation cannot be corrected by themselves, the general public may hear an incorrect word or a series of syllables.

Also, for this reason, it is often difficult to easily learn how to skillfully use the vocal organs or the pronunciation organs for accurate pronunciation thinking in the head.

As such, many techniques have been introduced for a method for hearing impaired people who can speak spoken language using a vocal organ or a pronunciation organ to learn and practice an accurate language speaking method.

However, these prior art techniques are based only on a lot of research on a method for analyzing the language of the deaf people, and lack of consideration on a method for increasing practical practice or learning efficiency.

1. Korean Patent Publication No. 10-2011-0065276

The present invention (Disclosure) aims to provide a speech language training system for the hearing impaired that can maximize the efficiency of language training and practice for the hearing impaired.

Herein, a general summary of the present invention is provided, which should not be construed as limiting the scope of the present invention (This section provides a general summary of the disclosure and is not a comprehensive disclosure of its full scope or all of its features).

In order to solve the above problems, the speech language training system for the hearing impaired according to any one aspect of the various aspects describing the present invention is a learning character, a learning pronunciation organ shape, a learning waveform, and a learning frequency of a learning target. a storage unit for storing learning target information including; a recognition unit for generating practice information comparable to the learning target information from the learner's language practice according to the learning target; a correction unit generating correction information for minimizing a difference between the learning target information and the practice information; and a display unit for displaying the learning target information and the calibration information.

In the voice language training system for the hearing impaired according to an aspect of the present invention, the correction unit derives a practice waveform and a practice frequency from the learner's voice, and compares the learning waveform and the learning frequency with each other for voice matching and a voice analysis unit that calculates the suitability as quantitative information, and the calibration information may include the voice matching suitability.

The correction information in the speech language training system for the hearing impaired according to an aspect of the present invention may further include a comparison graph for comparing the learning waveform and the learning frequency with the practice waveform and the practice frequency, respectively. .

In the voice language training system for the hearing impaired according to an aspect of the present invention, the correction unit analyzes the plurality of voice matching suitability generated from the repeated language practice of the learner, and as the voice matching suitability increases or decreases, It may further include a correction evaluation unit that generates voice matching trend information indicating whether the learner's language practice is improving or worsening.

The correction unit of the speech language training system for the hearing impaired according to an aspect of the present invention further comprises; , The calibration information may include the letter matching suitability.

In the voice language training system for the hearing impaired according to an aspect of the present invention, the correction unit generates a practice pronunciation organ shape including a mouth shape in which the learner pronounces the learner's hat, and the correction information is the learning pronunciation It may include a comparison image comparing the organ shape and the practice pronunciation organ shape.

The correction unit of the speech language training system for the hearing impaired according to an aspect of the present invention analyzes the plurality of letters matching suitability generated from the repeated language practice of the learner, and as the letter matching suitability increases or decreases, the It may further include; a correction evaluation unit for generating the letter matching trend information indicating whether the learner's language practice is improved or deteriorated.

According to the present invention, it is possible to maximize the efficiency of language practice and learning by providing various types of correction information in the verbal ability including vocalization and pronunciation so that the hearing impaired can practice accurate pronunciation and vocalization.

1 is a view showing a first embodiment of the speech language training system for the hearing impaired according to the present invention.
2 is a view showing a second embodiment of the speech language training system for the hearing impaired according to the present invention.
3 is a view showing a third embodiment of the speech language training system for the hearing impaired according to the present invention.

Hereinafter, an embodiment in which the speech language training system for the hearing impaired according to the present invention is implemented will be described in detail with reference to the drawings.

However, the intrinsic technical idea of the present invention cannot be said to be limited by the embodiments described below, and the It is disclosed that the range that can be easily suggested as a method of substitution or change of the embodiment described in is included.

In addition, since the terms used below are selected for convenience of description, in grasping the intrinsic technical idea of the present invention, they are not limited to the dictionary meaning and are appropriately interpreted as meanings consistent with the technical spirit of the present invention. it should be

1 is a view showing a first embodiment of the speech language training system for the hearing impaired according to the present invention.

Referring to FIG. 1 , the voice language training system for the hearing impaired according to the present embodiment includes a storage unit 100 , a display unit 200 , a recognition unit 300 , and a correction unit 400 .

The storage unit 100 stores the learning target information including the learning character of the learning object, the learning pronunciation organ shape, the learning waveform, and the learning frequency.

The learning object is an object in which the learner 1, who is deaf, trains a language by making a sound with a voice.

The learning target may be a word composed of specific objects or titles such as 'school', 'teacher', 'sky', 'ah', 'ya', 'uh', 'fe', 'ga', 'ga' It may be a single syllable, such as , 'geo' or 'cheap'. Also, it may be a sentence in which syllables and words are continuous.

The learning characters are the learning objects written in Korean, and the learner 1 can read the learning characters and recognize the learning objects.

The shape of the learning pronunciation organ is an image showing the shape of the pronunciation organ when the above-described learning characters are uttered by voice. The shape and position of the tongue, the shape of the lips or mouth, the shape of the inside of the oral cavity, etc. may be included.

The learner 1 can learn how to use the pronunciation organ required to pronounce the learning characters normally by following the shape of the pronunciation organ expressed as an image through the shape of the learning pronunciation organ and phoning.

In addition to this, the shape of the learning pronunciation organ may further include image information about the speech organ.

Language is composed of consonants and vowels combined, and each consonant and vowel is propagated as a voice through the vibration of air through the organic operation of the vocal organs and the pronunciation organs.

Therefore, for accurate language learning, the learner (1) must learn how to move his/her own body by practicing not only the pronunciation organ but also how to use the vocal organ.

The learning waveform is a vibration waveform of voice propagated in the air when the above-described learning character is read aloud. It has an amplitude that varies along the time axis.

The learning frequency is obtained by extracting the frequency component of the above-described learning waveform, and is generally obtained through Fourier transform.

The shape of the learning pronunciation organ, the learning waveform, and the learning frequency can be secured when a normal person with normal auditory and verbal ability reads the learning characters aloud.

A normal person with normal hearing and language ability is preferably a person who has completed education related to speech or pronunciation, or a worker in a related industry.

For example, such as announcers and voice actors, experts who have excellent Korean reading skills and can speak standard language are suitable.

The recognition unit 300 generates training information comparable to the learning object information from the audiovisual expression 301 generated when the learner's language practice according to the learning object is performed.

The recognition unit 300 generates practice information from the voice of the learner 1 or the shape of the lips of the learner when the learner reads the learning character aloud.

Therefore, the recognition unit 300 may have an input means 320 including a voice recording device capable of recording the learner 1's voice and an image recording device recording the learner 1's face shape or lip shape. .

The correction unit 400 generates correction information for minimizing the difference between the learning target information and the practice information, and displays the correction information through the display unit 200 .

The display unit 200 displays the learning target information and the correction information to the learner 1 ( 201 ).

At this time, it is preferable that the display unit 200 clearly recognizes the learning object to the learner by indicating the learning object using the learning character.

Accordingly, the learner 1 may receive quantitative and qualitative information on whether the sound he/she reads aloud the learning text is similar to the learning target information, that is, the sound that a normal person reads aloud the learning text.

This allows the learner to approach one learning object, that is, one learning character speaking aloud by a normal person, and maximize the practice effect.

2 is a view showing a second embodiment of the speech language training system for the hearing impaired according to the present invention.

Referring to FIG. 2 , in the speech language training system for the hearing impaired according to this embodiment, the correction unit 400 derives a practice waveform and a practice frequency from the learner's voice and compares them with the learning waveform and the learning frequency to match each other's voice and a voice analysis unit 410 for calculating the fitness as quantitative information, and the calibration information includes the voice matching suitability.

In this case, the calibration information may further include a comparison graph for comparing the learning waveform and the learning frequency with the practice waveform and the practice frequency, respectively.

Comparing the learning waveform and the practice waveform, the learner 1 can confirm which point in time is wrong during the entire time he makes a sound.

Comparing the learning frequency and the practice frequency, the learner 1 can know which part of the frequency height, that is, the high tone and the low tone is wrong.

In particular, high and low notes are not displayed as Hangul consonants and vowels.

However, when a normal person communicates with a deaf person through spoken language, if the high and low tones cannot be controlled, the unnaturalness of the consonants and vowels can be felt more clearly than when the pronunciation of consonants and vowels is uncertain.

Above all, by notifying the learner of the voice matching suitability, the learner 1 can confirm with quantitative information whether it is a situation that is gradually improved or a situation that worsens in the repeated practice process.

Speech matching fitness is a statistical voice matching ratio (SVMR) for speech and basic words. It is calculated by comparing the envelopes of the learning and practice waveforms, or the frequency of the learning frequency and the practice frequency. You may.

Alternatively, by comparing the movement of the shape of the learning pronunciation organ and the shape of the practice pronunciation organ extracted from the shape of the lips of the learner 1, the degree of suitability for voice matching may be calculated using the degree of agreement of the change in the shape of the speech.

2, in the speech language training system for the hearing impaired according to this embodiment, the correction unit 400 derives the learner's hat from the learner's voice, compares it with the learner's hat, and calculates the matching suitability of the letter analysis unit ( 420) is further included, and in this case, the correction information includes a letter matching suitability.

The above-mentioned voice matching suitability is quantitative information, and it is clear that the information is high and low. The learner 1 can clearly know whether the voice he makes is close to the learning waveform, the learning frequency, or the learning pronunciation organ shape.

However, the above-described voice matching suitability is not an analysis as a language, but an analysis method as a voice, that is, a sound wave, and a result.

Therefore, the learner 1 receives data that analyzes only the sound waves of his/her own voice even while training himself/herself, so it is difficult to accurately determine the accuracy of pronunciation required for actual communication.

That is, if the learning object is "ah", it is difficult for the learner 1 to distinguish whether the voice he or she made is "ah", "uh", or "wa".

If this is calculated as the voice matching suitability calculated through simple sound wave analysis, a variety of quantitative information can be provided, but the problem is that it is not clearly known what kind of sound the learner (1) sounds to others, that is, what kind of letters. There is this.

In the voice language training system for the hearing impaired according to the present embodiment, the learner 1 recognizes the voice matching suitability by analyzing the voice uttered by the learner as a sound wave itself, and recognizes the voice uttered by the learner as a language, that is, the correct language, that is, the alphabet. At the same time, you can receive feedback on the degree of suitability of matching letters, which indicates whether or not it was pronounced as .

At this time, the correction unit 400 generates the shape of the practice pronunciation organ including the shape of the mouth in which the learner 1 pronounces the learner's hat, and the correction information includes a comparison image comparing the shape of the learning pronunciation organ and the shape of the practice pronunciation organ. .

That is, the effect of language training can be maximized by providing the learner 1 with the shape and location of the pronunciation organ by dividing it into consonants and vowels, comparing the movement of the person's pronunciation organ with the movement of the pronunciation organ of a normal person.

3 is a view showing a third embodiment of the speech language training system for the hearing impaired according to the present invention.

In the speech language training system for the hearing impaired according to the present embodiment, the correction unit 400 may further include a correction evaluation unit that generates at least one of voice matching trend information and alphabet matching trend information.

The voice matching trend information is quantitative or qualitative information on whether the learner's language practice improves or deteriorates as the voice matching suitability rises or falls by analyzing a plurality of voice matching suitability generated as the learner's language practice is repeated. indicate

The alphabet matching trend information is quantitative or qualitative information on whether the learner's language practice improves or deteriorates as the alphabet matching suitability rises or falls by analyzing a plurality of letters matching suitability generated as the learner's language practice is repeated. indicate

Accordingly, the disabled_ can learn how to control their own voice and pronunciation organs so that they can find the correct pronunciation and vocalization method on their own.

Claims (7)

a storage unit for storing learning object information including the learning character of the learning object, the learning pronunciation organ shape, the learning waveform, and the learning frequency;
a recognition unit for generating practice information comparable to the learning object information from the learner's language practice according to the learning object;
a correction unit generating correction information for minimizing a difference between the learning target information and the practice information; and
A voice language training system for the hearing impaired including; a display unit for displaying the learning target information and the correction information. The method according to claim 1,
The correction unit,
A voice analysis unit for deriving a practice waveform and a practice frequency from the learner's voice, and comparing the learning waveform and the learning frequency, respectively, to calculate a mutual voice matching suitability as quantitative information; and
The correction information is
A voice language training system for the hearing impaired including the voice matching suitability. 3. The method according to claim 2,
The correction information is
and a comparison graph for comparing the learning waveform and the learning frequency with the practice waveform and the practice frequency, respectively. 3. The method according to claim 2,
The correction unit,
By analyzing a plurality of the voice matching suitability generated from the repeated language practice of the learner, as the voice matching suitability increases or decreases, voice matching trend information indicating whether the learner's language practice improves or deteriorates is generated. Orthodontic evaluation unit; speech language training system for the hearing impaired further comprising. The method according to claim 1,
The correction unit,
It further comprises; a character analysis unit for deriving the learner's hat from the learner's voice and comparing it with the learner's hat to calculate the matching suitability of the child's character;
The correction information is
A voice language training system for the hearing impaired, including the matching suitability of the letters. 6. The method of claim 5,
The correction unit,
generating a practice pronunciation organ shape including a mouth shape in which the learner pronounces the learner's hat;
The correction information is
A voice language training system for the hearing impaired including a comparison image comparing the shape of the learning pronunciation organ and the shape of the practice pronunciation organ. 6. The method of claim 5,
The correction unit,
By analyzing a plurality of the letters matching suitability generated from the repeated language practice of the learner, as the letter matching suitability rises or falls, the letter matching trend information indicating whether the learner's language practice improves or deteriorates to generate Orthodontic evaluation unit; speech language training system for the hearing impaired further comprising.

Images