KR20190143319A - Apparatus and method for learning language using muscle memory - Google Patents

Abstract

A language learning device according to one embodiment of the present invention comprises an input part where a user selects voice information including at least one a phoneme, a syllable, a word, and a suprasegment; a memory part which stores the voice information selected in the input part and information on positions and use methods of muscles strained to speak a voice; a display part which displays movements of the muscles according to the positions and the use methods of the muscles strained to speak the voice; and a speaker which makes the user listen to the voice spoken by straining the muscles. According to the present invention, a language learning effect can be improved by accurately dividing, speaking, and recognizing a phoneme, a syllable, a word, and a suprasegment of vowels and consonants.

Description

Language learning device and language learning method using muscle memory {APPARATUS AND METHOD FOR LEARNING LANGUAGE USING MUSCLE MEMORY}

The present invention relates to a learning apparatus and a method for clearly distinguishing and recognizing different speech sounds using muscle memory. More specifically, the electronic learning using the speech recognizer makes it possible to memorize the movements of muscles according to the location of the muscles and the way of using them to pronounce the sounds, so that each phoneme and syllable of vowels and consonants, words, and segmental sounds The present invention relates to a learning apparatus and method for enabling pronunciation and recognition.

So far, phonology says that the vocal cords, such as the vocal cords, make basic noises, and then the articulators, such as the lips and tongue, produce a variety of speech sounds. Learning methods used to learn foreign languages are also based on the characteristics of vowels and consonants described in phonetics. In the case of vowels, the articulatory organs describe the sounds of each vowel based on the shape of the lips and the position of the tongue. In the case of consonants, voiced sounds, unvoiced sounds, and nasal sounds are distinguished by using the movement of articulation organs.

However, when you actually pronounce a vowel, it is difficult for a phonetician to tell exactly where his tongue is. In addition, it is almost impossible to consciously adjust the shape of the lips or the position of the tongue to match the speed of the horse. The consonants are also described as voiced sounds that the vocal cords vibrate, but there is no explanation on how the vocal cords vibrate, and the position of articulation is slightly different depending on the person speaking.

In the speech recognition field, various attempts have been made to recognize speech based on the characteristics of vowels and consonants according to phonetics, but the results have not been successful. Recently, in-depth learning analyzes the sound waves of people who use the language as their mother tongue based on probability and statistics to recognize each phoneme and joint, and combines them to distinguish each word.

However, such a speech recognizer cannot be recognized properly when it is out of the speech patterns of people who use the language as its native language, so it is not a problem for foreigners who have many differences in the speech and pronunciation patterns of the language to be used in learning the speech of the language. There is this.

The movement of the vocal cords, the representative vocal organs, depends on the movement of the muscles that can control the vocal cords and the muscles that can control the vocal cords. Representative articulation organs, including the movement of the lips and tongue, depend not only on the muscles around the lips and the internal muscles of the lips, but also on the muscles connected to the tongue and the muscles connected to the cervical vertebrae.

If you follow the movements of the vocal or articulation organs belonging to the pronunciation organs, you can follow the movements of the muscles while showing the movements of the muscles that cause the movements of the pronunciation organs. . In addition to telling a certain speech sound, by giving the power to pronounce the sound to show the movement of the muscles causing the movement of the pronunciation organs to follow along, you can pronounce the speech by moving the same muscle in the same way.

When you learn a movement, such as walking, swimming, cycling, or playing a musical instrument, and then become familiar with the movement through repetitive exercises, the movements of the muscles associated with the movement are stored in the brain in the form of procedural memory, which is called "muscle memory". It is called. When muscle memory is formed, it can be easily done later without conscious effort. If the muscle movements that give strength to pronounce words are memorized through repetitive exercises, the words can be pronounced without conscious effort.

If you become accustomed to the movement of muscles that give power to pronounce new speech, you can pronounce the new speech by distinguishing it from the existing speech. When you recognize the speech, you can see that the new speech is distinguished from the existing speech.

This fact suggests that a person's listening to someone's words is not a recognition of the sound patterns of the words, but rather a way of knowing how the speaker has moved the pronunciation organ (motor theory of speech). perception). For example, the frequency at which [p] starts to sound in front of [i] and [u] is similar to the frequency at which [k] starts to sound in front of [a]. Listen differently with and [k]. The frequency of [d] varies from [di] and [du] to [d] until it starts to sound [i] or [u], but people hear the same with [d]. In addition, there are several phenomena that support the movement of the pronunciation organs rather than the sound patterns.

Meanwhile, since the Italian neuroscientist Giacomo Rizzolatti and his colleagues discovered the mirror nerve in monkeys and published it in 1992, numerous studies on mirror nerves in monkeys and humans have been published. Among those achievements, it was confirmed that the brain areas that people use to speak are also activated when they listen. This finding in relation to the mirror nerve is also linked to the above view that the object of speech is the movement of the pronunciation organ. In other words, when a person can pronounce certain speech sounds using certain muscles, when he hears sound waves in a pattern similar to the speech sounds, he can know what muscles are used to pronounce the sound waves through the mirror nerve. It can be seen that the speech of a person can be recognized.

However, the problem is that up to now, there is no research that summarizes how muscles can be pronounced and which sounds can be pronounced. Meanwhile, the study of the muscles associated with the pronunciation of speech sounds at the level of listing the muscles that are expected to contract when speech is pronounced. It is not possible to move the muscles listed in the previous study and follow the voice. In order to solve this problem, it is necessary to find a way to follow the movements of muscles that actually give strength when pronounced and to connect the pronunciation and recognition of speech with muscle memory.

In addition, if the speech sound learning device may include a speech recognizer capable of informing a correctly pronounced part and a wrongly pronounced part of a speech that the learner pronounces, it will be a great help in learning. In order to perform such a function, there must be a voice recognizer capable of recognizing speech based on the movement of muscles that give power when the speech is pronounced. However, such a speech recognizer has not been found yet.

For this reason, the present invention provides a solution to the above problems that must be solved in order to be able to follow while showing the movement of the muscles that give power when pronounced, and by using the muscle memory A language learning method and apparatus for enabling pronunciation and recognition are provided.

Language learning apparatus according to an embodiment of the present invention by using the muscle memory to distinguish and pronounce each segment of the vowels and consonants, syllables, words and pronunciation of the second segment sounds such as stress, tone, pitch, etc. It aims to provide improved language learning effects. In addition, according to the language learning apparatus according to an embodiment of the present invention, even the person who can not hear the language can not directly hear the language of the muscles that cause the movement of the pronunciation organ and the movement of the muscles according to the usage method directly to the eye By watching and learning, you can provide the opportunity to learn a language.

Language learning apparatus according to an embodiment of the present invention is an input unit for the user to select the information of the speech including at least one of a phoneme, syllables, words and seconds segment sounds, pronunciation of the speech information and the speech sound of the speech selected from the input unit Memory unit for storing information on the position and use of the muscle to give power to the display, a display unit for displaying the movement of the muscle according to the position and use of the muscle to give power to pronounce the speech and the muscle It may include a speaker for giving the user the sound of the pronunciation sound pronounced.

Language learning apparatus according to an embodiment of the present invention is an input unit for the user to select the information of the speech including at least one of a phoneme, syllables, words and seconds segment sounds, pronounced information of the speech sound selected from the input unit and the speech sound Memory unit for storing information about the position of the muscle to give a force and the manner of use, using the sound wave information by the user pronounced the speech, the position of the muscle that the user applied to pronounce the speech And a voice recognition unit for recognizing the use method and the display unit for displaying the movement of the muscles according to the position and the use of the muscles recognized by the voice recognition unit to the user.

Language learning apparatus according to an embodiment of the present invention is an input unit for the user to select the information of the speech including at least one of a phoneme, syllables, words and seconds segment sounds, pronunciation of the speech information and the speech sound of the speech selected from the input unit Memory unit for storing information on the position and use of the muscle to give power to the display, a display unit for displaying the movement of the muscle according to the position and use of the muscle to give power to pronounce the speech and the muscle A speaker for giving the user the sound of the speech to pronounce, and using the sound wave information caused by the user to pronounce the speech, the position and manner of use of the muscle that the user has applied to pronounce the speech A voice recognition unit for recognizing the display unit; The position of the muscle according to the pronunciation of the user recognized by the voice recognition unit, and the position and use of the muscle stored in the memory unit. The evaluator for determining whether or not within a predetermined range with respect to the position and use of the muscle according to the pronunciation of the user in the evaluation unit is within a predetermined range for the position and use of the muscle stored in the memory unit If determined, it may include a learning unit for strengthening muscle memory through repetitive learning.

The language learning method according to an embodiment of the present invention includes voice information of a speech sound including at least one of a phoneme, a syllable, a word, and a segmental sound, and information about a location and a usage method of muscles that give power to pronounce the speech. A language learning method using a device including a memory unit for storing, comprising the steps of a user selecting the information of the speech sound and the movement of the muscle according to the position of the muscle that gives force to pronounce the speech sound selected by the user and the usage method It may include the step of displaying, by the force to the muscle to say the sound of the pronunciation.

The language learning method according to an embodiment of the present invention stores information on speech sounds including at least one of a phoneme, syllables, words, and segmental sounds, and information on the location and usage of muscles that give power to pronounce the speeches. A language learning method using a device comprising a memory unit, comprising: selecting information of the speech by a user, and using sound wave information by the user to pronounce the speech, a force for the user to pronounce the speech Recognizing the position of the muscle and the manner of use, and displaying the movement of the muscle according to the recognized position of the muscle and the manner of use to the user.

The language learning method according to an embodiment of the present invention includes voice information of a speech sound including at least one of a phoneme, a syllable, a word, and a segmental sound, and information about a location and a usage method of muscles that give power to pronounce the speech. A language learning method using a device including a memory unit for storing, comprising the steps of: a user selecting information of the speech sound, displaying the movement of the muscle according to the position of the muscle that gives force to pronounce the speech and the usage method, and The step of giving a sound to pronounce the sound to the muscle, using the sound wave information by the user to pronounce the speech, to recognize the position of the muscle and the manner of use of the muscle to the user to pronounce the speech Step, the location and use of the recognized muscle location and use of the muscle stored in the memory unit Determining whether the method is within a predetermined range with respect to the method and when the location and use of the muscle according to the pronunciation of the user are determined to be within a predetermined range with respect to the location and use of the muscle stored in the memory unit; Repeated learning may include strengthening muscle memory.

Voice recognizer according to an embodiment of the present invention is a memory unit for storing the information of the sound and the position of the muscles and the way to use the force to pronounce the sound, the sound wave information by the user pronounces the sound By using the voice recognition unit for recognizing the position of the muscles and the manner of use of the force to pronounce the speech by using the user based on the movement of the muscles according to the position and use of the muscles recognized by the speech recognition unit It may include a display unit for displaying to the user what the sound of the user pronounced.

According to the language learning apparatus according to an embodiment of the present invention, by using the muscle memory, the phoneme and the syllables of the vowels and consonants, the words and the accents, the tonality, the pitch of the segmental sounds such as the tone and the pitch are distinguished and pronounced and recognized, Improve your language learning. In addition, even if a person cannot learn the language because he / she cannot hear the sound of speech, the effect of providing the opportunity to learn the language by directly learning the position of the muscles that causes the movement of the pronunciation organs and the movement according to the usage method is achieved. can do.

1 is a view showing the position of the larynx and the internal muscles of the larynx.
Figure 2 is a view showing the shield pharyngeal part and the ring shield muscle of the lower pharyngeal myocardium.
3 is a diagram illustrating the palatal pharynx and the palate muscles.
4 is a diagram showing a muscle used as a vocal muscle when a consonant is pronounced.
Figure 5 is a view showing the anterior teeth of the shield pyramidal muscles.
6 illustrates a language learning apparatus according to an embodiment of the present invention.
FIG. 7 is a diagram illustrating a plurality of speech sounds displayed on a screen of a display unit of a language learning apparatus according to an embodiment of the present invention.
FIG. 8 is a diagram illustrating a display unit of a language learning apparatus according to an embodiment of the present invention displaying a position and a usage method of muscles that give a force to pronounce a selected speech (vowel).
9 illustrates a language learning apparatus according to another embodiment of the present invention.
10 is a diagram illustrating a speech recognition unit according to an embodiment of the present invention.
11 is a diagram illustrating a language learning apparatus according to another embodiment of the present invention.
12 is a diagram illustrating a language learning method according to an embodiment of the present invention.
13 illustrates a language learning method according to another embodiment of the present invention.
14 is a diagram illustrating a language learning method according to another embodiment of the present invention.
15 is a diagram illustrating a user terminal including a language learning server and a language learning application according to an embodiment of the present invention connected through a network.
16 is a diagram illustrating a hardware configuration of a user terminal including a language learning application according to an embodiment of the present invention.
17 is a diagram illustrating an operation of performing language learning by communicating between a language learning server and a user terminal including a language learning application according to an embodiment of the present invention.
18 is a diagram illustrating an operation of performing language learning by communicating with a user terminal including a language learning server and a language learning application according to another embodiment of the present invention.
19 is a diagram illustrating an operation of performing language learning by communicating with a user terminal including a language learning server and a language learning application according to another embodiment of the present invention.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the present document, the same reference numerals are used for the same components in the drawings, and duplicate descriptions of the same components are omitted.

For the various embodiments of the present invention disclosed in this document, specific structural to functional descriptions are merely illustrated for the purpose of describing the embodiments of the present invention, and various embodiments of the present invention may be implemented in various forms. It should not be construed as limited to the embodiments described herein.

Expressions such as “first,” “second,” “first,” or “second,” used in various embodiments may modify various components in any order and / or importance, and may modify the components. It is not limited. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may be referred to as the first component.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise.

All terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by one of ordinary skill in the art. Generally defined terms used in the context of the related art may be interpreted as having the same or similar meaning as the meaning in the context of the related art and shall not be interpreted as ideal or excessively formal meanings unless clearly defined in this document. . In some cases, even if terms are terms defined in the specification, they may not be interpreted to exclude embodiments of the present disclosure.

As described above, in order to show the movement of muscles that give strength when a person pronounces speech, many difficulties must be overcome. During the pronounciation, the muscles of the lips, tongue, cervical bones, the larynx, the tongue muscles, and the muscles of the larynx are constantly moving. Some of these muscles move by force, but many move together because of the movement of other muscles. Among the many muscles that move together when you pronounce words, you need to find out which muscles you can pronounce when you move with strength.

If you can move a muscle in many ways, the sound of the words changes depending on how you move. Therefore, you need to find out how to move the muscles that give you the power to pronounce words.

The present invention has been devised to solve the above problems, and shows the movement of the muscles according to the position and use of the muscles that give power when the person pronounces the sound of speech, and the pronunciation of the pronunciation of the pronunciation of the learner through the voice recognition It is intended to provide a language learning apparatus and a language learning method capable of judging wrong and pronounced parts. Description of these is described in detail below.

Agonistic muscles are those muscles when they can move parts of the body as desired by empowering them. The muscles that act oppositely to allow the main muscles to work stably are called antagonistic muscles, and the muscles that help the main muscles move or stabilize other parts of the muscles are called synergistic muscles. And cooperative muscles move together according to the movement of the main root muscles without additional force. Among the many muscles that move together when pronounced, you can pronounce the intended speech by emphasizing the psoas muscles that cause the movement of the pronunciation organs, such as the vocal cords, lips, tongue, and soft palate.

The following is a description of the muscles used to pronounce each segment of vowels or consonants, and the muscles used to pronounce hypersegmental sounds such as stress, tone, and pitch. As you show the movement of each muscle, you can tell which muscles should be moved by showing or pointing to where they are located. Instead of showing or pointing to the location of the muscles, you can tell them the name of the muscle, or tell them where the muscle is connected and tell them which muscle to move.

1 is a view showing the position of the larynx and the internal muscles of the larynx.

Referring to FIG. 1, the thyroarytenoid muscle of the muscles of the larynx may be divided into three parts, thyrovocalis belly, thyromuscularis belly, and thyroarytenoid ventricular belly. have. Shield vocal cords are also called vocalis muscles (“vocal cord muscles”), which are the forces connected from the thyroid cartilage to the vocal process of the arytenoid cartilage. The length of the muscles varies according to how they are applied, and the length of the vocal cords changes accordingly.

The shield horn ventricular tendon of the shield rhizome is the strength of the shield cartilage that connects to the laryngeal ventricle of the shield horn, but is not considered to be directly related to the pronunciation of the vowels. On the other hand, the shield muscle muscles (hereinafter referred to as “shield shield muscles”) of the shield horn muscles are the muscles connected from the shield cartilage to the muscle processes of the chondrocartilage. As the projections turn inward a little, the front gap of the vocal cords becomes narrower. The lateral cricoarytenoid muscles are muscles connected to the muscle cartilage of the chondrocartilage on both sides of the cricoid cartilage. Make it close As a result, the middle portion of the vocal cords becomes narrower.

The transverse arytenoid muscle is the muscle that connects the lateral cartilage from the lateral cartilage to the lateral edge of the other cartilage. As a result, the rear gap of the vocal cords becomes narrower. An oblique arytenoid muscle is a muscle that connects from the base of the muscle cartilage of the cartilage to the back of the top of the other cartilage, and when the muscle is shortened, the tops of the two cartilage close together. This narrows the spacing of the posterior part of the vocal cords.

The posterior cricoarytenoid muscle is the muscle from the back of the ring cartilage that connects to the muscle cartilage of the chondrocartilage, and when the muscle is shortened, the gap between the vocal cords increases.

Figure 2 is a view showing the shield pharyngeal part and the ring shield muscle of the lower pharyngeal myocardium.

Referring to FIG. 2, an inferior pharyngeal constrictor muscle may be divided into a thyropharyngeal part and a cricopharyngeal part. The shield pharyngeal part of the lower pharyngeal contractor muscle (hereinafter referred to as the "shielding pharyngeal muscle") is a muscle that begins at both sides of the shield cartilage and connects to each other in the pharyngeal raphe, which forces the muscle to shorten. In this case, the gap between the shield cartilage and the back wall of the lower pharynx decreases, and the gap between the shield cartilage and the ring cartilage decreases. This reduces the length of the vocal cords. The cricothyroid muscle is a muscle that starts from the front side of the cartilage and connects to the lower horn of the cartilage of the shield and connects to the plate. When the muscle is shortened, the vocal cord increases and the pitch increases.

The muscles inside the larynx, the shield pharynx and the ring shield muscle are the main muscles that move the vocal cords. Shield pyramid, lateral ring pyramid, transverse pyramid, and comb pyramid function to narrow the spacing of vocal cords, and vocal cord and shield pharynx to adjust the length of vocal cords. When vowels are pronounced, muscles that narrow the vocal cords and muscles that control the vocal cords are used as articulation muscles (described later) and vocal muscles (described later).

3 is a diagram illustrating the palatal pharynx and the palate muscles.

Referring to FIG. 3, the palatine pharyngeal muscle (palatopharyngeus muscle) starts from the soft palate, partly connected to the pharyngeal constrictor muscle, and partly connected to the upper edge of the shield cartilage, When the muscles are shortened, the palate will go down. This opens the passage to the nasal tract. Except in the case of making a sound through the nasal cavity, the levator veli palatinimuscle is used to shorten the sound and block the passage to the nasal cavity.

4 is a diagram showing a muscle used as a vocal muscle when a consonant is pronounced.

Referring to FIG. 4, when the consonants are pronounced, muscles around the lips, muscles inside the tongue, muscles connected to the tongue, and muscles connected to the cervical bone are used as vocal muscles (to be described later). Specific muscle types and operations will be described below.

The transverse muscle of the tongue is one of the tongue's eigen muscles that make up the body of the tongue, starting from the median fibrous septum of the tongue and into the submucous fibrous tissue on both sides of the tongue. As a connecting muscle, when the muscle is shortened, the tongue is narrowed and pushed forward. This causes the tip of the tongue to touch the alveolar.

The vertical muscle of the tongue is one of the endotracheal muscles that make up the trunk of the tongue and is located in front of the tongue. It connects from the lower part of the tongue to the upper part, and when this muscle is shortened, the front middle part of the tongue goes down. This causes friction of air near the boundary between the hard palate and the alveolar when pronounced.

When the vertical muscles of the tongue and the transverse muscles of the tongue are shortened together, the front center of the tongue is lowered and the torso of the tongue is narrowed and pushed forward. This causes friction of air just behind the alveolar during pronunciation.

Geniohyoid muscles are muscles that begin at the inferior mental spine of the mandible and connect to the hyoid bone. It is pulled forward and raised up. This places the tongue between the upper and lower teeth. The hyoglossus muscle is a muscle that starts at the vertebra and connects to the sides of the tongue. When the muscle is shortened, the tongue is pulled toward the vertebra. If you apply force to the muscles to pronounce the vowels, and the neck is shortened, the tongue is pulled toward the neck and the tip of the tongue touches the back of the alveolar. Mylohyoid muscle is a muscle that starts from the mylohyoid line of the lower jaw and connects to the body of the hyoid bone and median ridge. The horns and tongue are up. This causes the central portion of the tongue to rise toward the palate. When you contract the muscles, such as the shield pharyngeal muscles, the jawbone shortens the force, causing the central tip of the tongue to rise toward the palate, with the tip of the tongue facing up.

The menalis muscle is the muscle that starts from the anterior lower jawbone and connects to the skin at the tip of the jaw. When this muscle is shortened, the jaw's skin is moved upward and inward, so that the middle part of the lower lip moves up. . This causes the lower lip to approach the upper teeth. The styloglossus muscle is a muscle that starts from the styloid process of the temporal bone and connects to the tip and sides of the tongue. Both sides are pulled up. As a result, the posterior tongue area reaches the soft palate.

The inferior orbicularis oris muscle wraps around the lips starting at the end of the buccinator. The circumference of the mouth, starting at the center of the root, crosses up and down at both ends of the lips, enclosing the lip, and the circumference of the mouth, starting at the top of the root, connects past the top of the mouth, crossing the top, bottom, Starting from the part, the circumference of the mouth is connected past the bottom of the circumference of the mouth, crossing the top and bottom. Applying strength to shorten the deep muscles of the mouth closes the lips. On the outside of the deep mouth muscles are the mouth muscles of the surface area, and when the muscles are shortened, the lips are strongly closed.

The superior longitudinal muscle of the tongue is a muscle that starts around the epiglottis and runs down the mucosa of the tongue to the tip of the tongue, which causes the tongue to become shorter and thicker when the muscle is shortened. .

The genioglossus muscle is a muscle that starts from the superior mental spine of the lower jaw and connects to the underside of the tongue and the cervical vertebrae, the lower part of the muscle acting as the tongue sticking out, and the middle part pressing the tongue The upper part causes the tip of the tongue to descend back and forth.

Figure 5 is a view showing the anterior teeth of the shield pyramidal muscles.

Referring to FIG. 5, the thyrohyoid muscle is a muscle connected from the oblique line of the shield cartilage to the lower boundary of the greater horn, and when the force is applied to shorten the muscle, If the shield cartilage is narrowed, if the shield cartilage is fixed, the cervical vertebrae are pulled down, if the cervical bone is fixed, the shield cartilage is raised, the vocal cords are increased, and the pitch is increased.

The anterior belly of the digastric muscle begins at the medial lower boundary of the mandible and crosses the midline of the biceps tendon near the apical horn to the posterior belly of the biceps. As a result, the muscles are pulled short and pulled forward, pulling upwards. This, along with the tongue up front, pulls the larynx forward, increasing the vocal cords and raising the pitch. When the cervical vertebrae are fixed, the lower jaw is pulled down along with the lateral pterygoid muscles of the jaw lateral pyramidal muscle, the jaw pyramidal muscle and the lateral pterygoid muscle.

When the sound of the sound is pronounced while the neck is fixed, the shield is shortened and the front of the biceps muscle is shortened while the neck is not fixed. There is a sound.

According to the present invention, the method of using the main muscles is i) a method used as an artificial muscle, (ii) a method used as a phonatory muscle, iii) a method used as a standby muscle, iv) as an intervenient muscle, v) as a stressing muscle, vi) as a tonal muscle, vii) as a tuning muscle Divide in such a way.

Articulatory muscle refers to a muscle that causes the characteristic of contraction of the muscle to appear in pronounced speech while the muscle is in a contracted state, and vocal muscles create direct sounds such as vocal cords or articulators. Refers to the muscles that cause the vocal cords or articulators to make sounds. Depending on which muscle is used as a vocal muscle, it is distinguished by different speech sounds. For example, the sound of pronunciation using the lateral rhomboid muscle as the vocal muscles and the sound of pronunciation using the lateral rhizomus as the vocal muscles are divided into different speech sounds.

In the case of articulated muscles, even if the same muscles are used as vocal muscles, the sounds are different depending on which muscles are used as articulated muscles. For example, even if you use the lateral rhomboid muscles as vocal muscles, the sound produced by using only the vocal cord muscles as articulation muscles and the sound using the vocal cords and transverse muscles as articulation muscles are distinguished from each other.

In the case of pronounced consonants, even when the same muscle is used as a vocal muscle, the sound is pronounced when the sphincter muscle is shortened as an articulation muscle, and the voice is sounded while the back muscle is shortened as the articulation muscle. When the sound is unvoiced, the articulation muscle is shortened as the articulation muscle. Instead of pronouncing the arterial muscles in a state in which the rhizome is shortened, the voiced sounds are also produced when the atmospheric muscles (described later) to pronounce the vowels are contracted.

The same muscles are used, but depending on which of the muscles are used as vocal muscles and the rest of the muscles are articulated muscles, the pronunciation sounds different. For example, the use of the shield pharynx as an articulation muscle and the use of the transverse muscles as vocal muscles and the use of the shield pharynx as vocal muscles, use the transverse muscles as articulation muscles.

In addition, the sound of using the comb muscles and the lateral roots as vocal muscles and the sound of using the lateral muscles as the vocal muscles while using the comb muscles as articulation muscles are also different.

Words that use different muscles as vocal muscles are mostly treated as different phonemes. If you use the same vocal muscles but different articulation muscles, they are sometimes treated as different phonemes or as different joints of the same phoneme.

와 /e/의 음소 차이로 의미가 달라지고, "bat"와"bad"는 /t/와 /d/의 음소 차이로 의미가 달라진다. 이와 같이, 의미의 차이를 가져오는 /b/, /k/,

, /e/, /t/, /d/ 등을 음소라고 한다. 반면, "pit"와 "spit"에서 각각의 [p] 소리는 조금 다르게 발음되지만 동일한 /p/ 음소이다. 이 때, 각각의 소리를 [p^h], [p]로 구분하여 표시하기도 한다. 동일한 음소에 속하면서 조금씩 다르게 발음되는 소리를 이음이라 한다.Here, the phoneme is the unit of the smallest sound that makes the meaning of words different. For example, "bat" and "cat" have different meanings due to phoneme differences between / b / and / k /, and "bat" and "bet"

The meaning is changed by the phoneme difference between / e / and "bat" and "bad" are changed by the phoneme difference between / t / and / d /. In this way, / b /, / k /,

, / e /, / t / and / d / are called phonemes. On the other hand, in "pit" and "spit", each [p] sound is pronounced a little differently, but in the same / p / phoneme. At this time, each sound may be divided into [p ^h ] and [p]. Sounds belonging to the same phoneme and pronounced slightly differently are called joints.

Even if you use the same articulation muscles and vocal muscles, the sound you pronounce depends on how you use them. For example, using the vocal cord muscles as the articulation muscle and the shield horn muscle as the vocal muscles, but using the vocal cord muscles as a force to lengthen and using the vocal cord muscles as the articulation muscle, Using the vocal cords as articulation muscles produces different sounds when pronounced.

In the present invention, it is said that one muscle is used as an articulatory muscle by giving strength to a long muscle, and one muscle is used as an articulator muscle by giving a force to shorten a muscle.

The vocal muscles are divided into a method of using isotonic vocal muscles, a method of using elongated vocal muscles, and a method of using unilateral vocal muscles.

In the present invention, the use of the isotonic vocal muscles is to force the vocal muscles so that the vocal cords or articulators are in a position where they can make a sound, and then the vocal cords vibrate while the vocal muscles are isotropically contracted while the vocal cords vibrate or the articulators are rubbed. In other words, the use of elongated vocal muscles means that the vocal muscles are shortened and the articulators are brought into contact with each other. This shortening contraction means that the vocal cords are vibrated or the articulator is rubbed.

와

는 혀의 가로근을 신장성 발성 근육으로 사용하면서 동시에 혀의 수직근을 단축성 발성 근육으로 사용하여 발음할 수 있다.To pronounce one phoneme, use one or two vocal muscles. In some cases, two vocal muscles may be used simultaneously or sequentially in different ways. For example, English

Wow

Can be pronounced using the transverse muscles of the tongue as elongated vocal muscles while the vertical muscles of the tongue as unilateral vocal muscles.

The use of articulated muscles and vocal muscles can be divided into muscle uses and contraction types. For example, using isometric vocal muscles can be used to describe the muscles as being used for vocal muscles and when they are pronounced, they are isometric contractions.

On the other hand, the use of atmospheric muscles means that the two phonemes are followed by sequential pronunciation, and the articulation muscles and the vocal muscles for pronunciation of the back phoneme are contracted before the front phoneme is pronounced and contracted while the front phoneme is pronounced. To maintain, but using the articulation muscles and vocal muscles to pronounce the front phoneme means contraction in a range that does not interfere with the pronunciation of the front phoneme.

When used as an interstitial muscle, when two phonemes are followed by overlapping pronunciation, it means that the articulation muscle and the vocal muscle to pronounce the back phoneme are contracted while the front phone is pronounced. In some languages, only the vocal muscles to pronounce the back phoneme contract while the front phone is being pronounced.

Using stressed muscles means that the pronounced speech in the contracted state of the muscle sounds more pronounced than the pronounced speech in the non-constricted state.

Using it as an adult muscle means that i) the vocal cord muscles are in a state of contractile contraction during the pronunciation of a syllable, or ii) they are forced to stretch when the vocal cord muscles are relaxed, or iii) Force the contraction to retract as soon as it is forced to contract shortening in the relaxed state, or iv) force shortening contraction with the vocal cord muscle contracting, or v) relax the vocal cord muscles. Vi) means to maintain the pitch of the sound or to vary the pitch by maintaining the state that the vocal cord muscles have contracted shortening.

It is used as a pitch-controlling muscle, with the ring shield muscle and the shield pharynx muscle relaxed, i) the vocal cord muscles being shortened, ii) the vocal cord muscles relaxed, iii) the vocal cord muscles being lengthened. In the semi-circle, the ring shield and the shield pharynx are all shortened iv) the vocal cord muscles are shortened and the ring shield muscles are shortened and the shield pharynx is relaxed v) the vocal cords This means adjusting the pitch so that the muscle becomes shorter in force, vi) the vocal cord muscles are relaxed, and vii) the vocal cord muscles are increased.

Here, in the use method of the main muscles, the stress muscle, the tone muscle and the pitch control muscle are divided into separate muscles, but not limited thereto. Articulation muscles, stress muscles, tone muscles, You can also divide it into pitch-controlled muscles. This is because all of these subtle muscles correspond to the 'muscles of the contraction of the muscles that appear in the pronounced speech in the contracted state of the muscles'.

In addition, in addition to the muscles described above, muscles used for regional accents, muscles used for expressing emotions, and the like may be classified in various ways depending on the purpose.

In the sequential or superimposition pronunciation according to the present invention, when the pronunciation of the consonants and vowels, vowels and consonants, consonants and consonants, vowels and vowels are pronounced in succession, the front phoneme is to be pronounced. With preparation, prepare to pronounce the back phoneme, and then pronounce the front phone and the back phone in order. In the case of “nested pronunciation”, the phoneme is being pronounced while the phoneme is being pronounced. It is to pronounce the phoneme immediately after the pronunciation.

In the case of sequential pronunciation, i) contracting the articulation muscles and vocal muscles to pronounce the front phoneme along with i) using the articulation muscles and vocal muscles to pronounce the back phoneme, and ii) to pronounce the back phoneme. Pronouncing the front phoneme using vocal muscles for pronouncing the front phoneme while maintaining the contraction of the articulation muscles for pronouncing the atmospheric muscles and the front phoneme; Relaxing the vocal muscles and contracting the atmospheric muscles that have been contracted to pronounce the back phonemes into the articulation muscles and vocal muscles, iv) pronounce the back phonemes using the vocal muscles while contracting the articulation muscles to pronounce the back phonemes It is pronounced through steps.

/ 부분은 다음에 모음으로 이어질 경우 /r/을 발음하고, 그렇지 않은 겨우 schwa 음으로 발음하는 대신에, /

/와 /r/을 이어서 중첩 발음으로 발음하되 다음에 모음으로 이어질 경우 ii-1)과 같이 /r/을 발음하고, 그렇지 않은 경우 ii-2)와 같이 /r/을 발음하지 않고 종료하여 발음할 수 있다. In the case of overlapping pronunciation, i) contracting the articulation muscles and vocal muscles for the pronunciation of the back phoneme during the pronunciation of the front phoneme and using them as intervening muscles, ii) depending on whether to pronounce the back phoneme. Among the intervening muscles that relax and relax the articulation muscles and vocal muscles for the sake of the artery, use the vocal muscles to pronounce the back phoneme while maintaining the contraction of the articulation muscles, or ii-2) The pronunciation of the phoneme is terminated through the step of ending the pronunciation. / of words ending in '-er', such as better, water

The / part pronounces / r / the next time it leads to a vowel, and instead of just the schwa sound, /

Pronounce / and / r / followed by nested pronunciation, but if it is followed by vowels, pronounce / r / as in ii-1), otherwise end without pronunciation / r / as in ii-2) can do.

6 illustrates a language learning apparatus according to an embodiment of the present invention.

Referring to FIG. 6, the language learning apparatus 100 may include an input unit 110, a memory unit 120, a speaker 130, and a display unit 140. For example, the language learning apparatus 100 may be published in the form of an e-book as well as a portable terminal such as a smartphone or a tablet PC.

The input unit 110 may allow the user to select information of speech sounds including at least one of a phoneme, a syllable, a word, and a segmental sound. The input unit 110 may be, for example, a device such as a touch panel, or may be a device such as a mouse or a keyboard. Alternatively, the input unit 110 may be a concept including not only a device for generating a signal indicating a selection from a user, but also a configuration corresponding to an interface for receiving a signal indicating a selection from the user. The user may start learning by selecting one of speech sounds, that is, desired phonemes, syllables, words, and second segment sounds through the input unit 110.

The memory unit 120 may store voice information of the voice sound selected by the input unit 110 and information about the location of the muscle that gives power to pronounce the voice and how to use the voice. That is, the memory unit 120 stores information about which muscles are to be used in what manner and when the user pronounces the selected voice. Here, muscles that give power to pronounce words mean muscles that cause movements of pronunciation organs such as vocal cords, lips, tongue, soft palate, etc. Since these muscles have been described in detail with reference to FIGS. 1 to 5, detailed descriptions thereof will be omitted.

The speaker 130 may function as a voice output means, and the speaker 130 may speak a spoken sound by using muscles that give power to pronounce the selected voice. That is, the speaker 130 directly listens to the speech selected by the user, so that the user can repeatedly practice the pronunciation.

The display unit 140 serves as an image output means including a still image and a moving image. The display unit 140 transmits a muscle movement according to a position and a usage method of a muscle to give a force to pronounce the selected speech sound from the input unit 110. I can display it. In other words, by visually showing the user the position of the muscles and the movement of the muscles according to the way of using the force to pronounce the speech selected by the user, it is easy to determine which muscle is used in which way and when the user pronounces the specific speech. Make it understandable. In particular, when the user pronounces the phoneme continuously, the display unit 140 may display one of the sequential pronunciation and the superimposed pronunciation, and display the movement according to the position of the muscle that gives power to the phoneme and the pronunciation. .

In addition, the display unit 140 may display the position and the use method of the muscles that give power to pronounce the words, in at least one of the shape, color, shape change, or hand gesture expression of the muscles. That is, the movement of muscles that give power to pronounce words may be represented by changes in the shape, color, or shape of specific muscles so that the user can clearly see the movement of muscles that give power to pronounce words that they want to learn. Can be represented by hand gestures.

For example, muscles that give strength to pronounce words are represented by the shape, color, or shape of a particular muscle, and when the words are pronounced, the muscle changes are defined by the shape or size of the muscle, or by the shape or size of the shape. By expressing with a back so that the user can easily determine which muscle to use to pronounce the selected voice. Alternatively, the movements of muscles that give power to pronounce words may be expressed in the form of hand gestures, and thus the changes of muscles may be easily expressed as changes in hand gestures when the words are pronounced. However, this representation is only one example, and the present invention is not limited thereto.

The display unit 140 may display a location or use method of muscles that give power to pronounce words as a moving image or a still image for each step. That is, the display 140 displays the movement of the muscles that give power to pronounce the words that the user wants to learn in a video, so that the user can check the continuous movement of the muscles that give the force to pronounce the words. . In addition, the muscles that give power to pronounce the speech is shown in each step of the still image, so that the user can learn step by step the movement of the muscles that you did not see in the video.

In addition, muscles that give strength to pronounce speech move the vocal cords or articulators. In this case, the display 140 may display the movement of the vocal cords or articulators and the movement of the main root muscle.

In particular, muscles that give strength to pronounce speech can be used as at least one of vocal muscles, articulation muscles, atmospheric muscles, interstitial muscles, stress muscles, tone muscles, or pitch control muscles. The vocal muscles use one or two vocal muscles in one of isotropic, elongated, or short unilateral, or two or more vocal muscles simultaneously or sequentially. Articulation muscles can be used as renal articulation muscles or shortening articulation muscles.

FIG. 7 is a diagram illustrating a plurality of speech sounds displayed on a screen of a display unit of a language learning apparatus according to an embodiment of the present invention.

Referring to the example illustrated in FIG. 7, the user selects a speech sound to be learned by the mouse, which is the input unit 110, on the screen of the display 140. Specifically, the user first selects one of the desired languages (eg, Korean, English, Japanese, Chinese, etc.). Next, the user selects a desired unit of speech in the language (for example, a phoneme such as a consonant or a vowel, a syllable, a word, an accent, a tone, a pitch control, and the like). In this case, as shown in FIG. 7, when the user selects a speech unit, the shape of the muscle related to uttering the speech may be displayed together on the screen of the display 140.

However, the display and selection method of the screen of the display unit 140 shown in FIG. 7 is merely exemplary, and the present invention is not limited thereto. For example, the information on the speech sounds desired by the user on the display 140 may be displayed only in letters, or may be displayed together with a video regarding the movement of the muscles when the speech is pronounced, instead of the mouse as the input unit 110. A device such as a keyboard or a touch panel may be used. In addition, in addition to the unit of speech sounds, it may also be possible to select the use of muscles and learning according to the type of contraction, such as the use of vocal muscles and the classification of speech sounds according to the contraction type of the articulated muscles. It may be configured as a learning device.

FIG. 8 is a diagram illustrating a display unit of a language learning apparatus according to an embodiment of the present invention displaying a user's movement of a muscle according to a position and a usage method of a muscle to give a force to pronounce a selected speech (vowel).

Referring to (a) to (e) of FIG. 8, as an example of speech information, the position of muscles when pronounced [a], [e], [yi], [o], [right], which is a basic vowel in Korean. And usage. In the example of FIG. 8, the muscles into which power is applied to pronounce each phoneme are shaded.

In a) of FIG. 8, when the vowel [a] is pronounced, the transverse rhizome is given a force to shorten the interval between the vocal cords and the back of the vocal cord. In addition, referring to b) of FIG. 8, when the vowel [e] is pronounced, the vocal cords are narrowed and are pronounced while giving a force to shorten the pectoral muscles.

As shown in c) of FIG. 8, when the vowel [i] is pronounced, the front edge of the vocal cord is narrowed by giving force to the shield rhizome. In d) of FIG. 8, when the vowel [o] is pronounced, the transverse and comb rhomboids are forced to be shortened so that the interval between the rear part of the vocal cord and the rear upper part of the vocal cord are narrowed. In e) of FIG. 8, when the vowel [right] is pronounced, the comb horn is shortened to give a narrower upper interval of the vocal cord.

As such, the display unit 140 displays a position and a usage method of the muscles that give power to pronounce the speech selected by the user through the screen in the form of muscle movement, so that the user can identify which muscle to pronounce the speech. Make it easy to figure out how to use it.

Meanwhile, in FIG. 8, the movement of the muscles when the words are pronounced is shown in a step-by-step screen, but in practice, the process of moving the muscles may be provided as a video, but is not limited to the embodiment of FIG. 8.

9 illustrates a language learning apparatus according to another embodiment of the present invention.

Referring to FIG. 9, the language learning apparatus 200 may include an input unit 210, a memory unit 220, a display unit 240, and a voice recognition unit 250. Since the input unit 210 and the display unit 240 according to the present exemplary embodiment have the same function and operation as the input unit 110 and the display unit 140 of FIG. 6, a detailed description of the overlapping configuration of FIG. 6 will be omitted. .

The memory unit 220 may provide information on the combination of the information of the speech, the position of the muscle and the manner of use that gives power to pronounce the speech, and the information on the combination of the information of the speech and the position of the muscle and the manner of use. You can save the corresponding table.

The voice recognition unit 250 may recognize the location of the muscle and the manner in which the user has applied the force to pronounce the speech using the sound wave information by the user pronounce the speech. At this time, the speech recognition unit 250 may include a microphone (not shown), and the position and use of the muscles that the user has applied to pronounce the speech using a voice file in which the user's pronunciation is recorded. You can also recognize it. That is, when the user pronounces the speech selected by the input unit 210, the speech recognizer 250 may identify the location and the method of using the muscles that the user has given power to pronounce the speech through the recognized sound waves. have. At this time, the muscle that the user has given power to pronounce means the muscle causing the movement of the pronunciation organ.

The speech recognizer 250 includes a table that maps information of speech sounds and information about a combination of positions and usage methods of muscles that give power to pronounce the speech sounds. The speech recognizer 250 includes a recognized muscle. By using the location and the manner of use of the table, it is possible to determine the information of the user pronounced speech sounds. In addition, when the user pronounces the phoneme in succession, the voice recognition unit 250 may recognize one of the sequential pronunciation and the superimposed pronunciation.

The display unit 240 may display the position and use of the muscles according to the pronunciation of the user recognized by the voice recognition unit 250 in the form of muscle movement. In other words, by visually showing the position and use of the muscles applied to the user to pronounce the selected speech, the user can determine whether the user used the appropriate muscle in order to pronounce the speech. For example, the display unit 240 may show the wrongly pronounced part of the muscle movements that should be given strength in order to pronounce the selected speech sound in a separate color, or may properly pronounce the movement of the muscles and the actual pronunciation. The movement of the muscles can be compared and shown, and can be displayed to the user in various ways such as simply displaying the position of the wrongly used muscle.

In addition, as in FIG. 6, muscles that give strength to pronounce speech cause the vocal cords or articulators to move. In this case, the display unit 240 may display the movement of the vocal cords or articulators and the movement of the main root muscle.

In particular, muscles that give strength to pronounce speech can be used as at least one of vocal muscles, articulation muscles, atmospheric muscles, interstitial muscles, stress muscles, tonal muscles, or pitch control muscles, and vocal muscles are one or two vocal muscles. Is used in the manner of isometric, renal or shortening, or two or more different muscles are used simultaneously or in succession. Can be used as a shortening articulation muscle.

In addition, when the user pronounces the phoneme continuously, the display unit 240 may display one of the sequential pronunciation and the superimposed pronunciation to display the movement of the muscle according to the position of the muscle that gives power to the phoneme and the pronunciation. Can be.

10 is a diagram illustrating a speech recognition unit according to an embodiment of the present invention.

Referring to FIG. 10, the speech recognizer 250 may include a phoneme recognizer 251, a syllable recognizer 252, and a word recognizer 253.

The phoneme recognizer 251 may recognize the phoneme through the location and use of the muscles that the user has given power to pronounce words. In detail, the phoneme recognizer 251 may include a phoneme pronunciation pattern recognizer 251a, a phoneme change recognizer 251b, and a phoneme pronunciation change recognizer 251c.

The phoneme pronunciation pattern recognizer 251a may recognize a location and a usage method of muscles that give power when the user starts to pronounce the phoneme. In this case, the phoneme pronunciation pattern recognizer 251a may recognize the location of the articulation muscle and the manner of use of the muscle used as the vocal muscle and the vocal muscle and the muscle to give the user a pronounced consonant or vowel.

The change recognizer 251 b of phoneme pronunciation may recognize a location and a usage method of muscles used while a user is pronounced a phoneme. At this time, the change recognizer 251b of the phonetic pronunciation may recognize a location of a vowel and a consonant, or a muscle to pronounce another consonant or a vowel while the consonant is pronounced. have.

After the phonetic pronunciation change recognizer 251c may recognize the position and the method of use of the muscle used after the user pronounces the phoneme and before the next phoneme is pronounced. At this time, the phoneme pronunciation change recognizer 251c recognizes whether another consonant or vowel is pronounced or stopped following the pronunciation of the consonant, or whether another vowel or consonant is pronounced or stops following the pronunciation of the vowel. Recognizing the presence of a consonant or vowel followed by the movement of the muscle used to pronounce the consonant and vowel that were pronounced before the other consonants and vowels

The syllable recognizer 252 may recognize syllables by dividing consonants or vowels pronounced by a user into syllable heads, syllable nucleus, and syllable tails. Specifically, the syllable recognizer 252 pronounces consonants and vowels sequentially, or pronounces two consonants sequentially or overlaps before pronunciation of the vowels, or overlaps three consonants before pronunciation of the vowels and then pronounces them sequentially. If the consonant or consonants are recognized as syllable heads, one vowel followed by syllable heads or pronounced without syllable heads, or two sequential or overlapping vowels are recognized as syllable nuclei. Subsequently, the consonants that are pronounced and the consonants that are sequentially pronounced subsequent to the consonants may be recognized as syllable tails. In addition, the syllable recognizer 252 may further include a function of recognizing whether the stressed muscle, the tonal muscle, the pitch control muscle is used for the syllable, and if so, how the syllable is used.

The word recognizer 253 may recognize a word based on the connection state between the recognized syllables, the second segmental sound, and the grammatical elements. In detail, the word recognizer 253 recognizes the syllables continuously recognized through the syllable recognizer 252 and the connection state between the syllables and the syllables recognized through the phoneme pronunciation change recognizer 251c and the syllable recognizer 252. It is a composition that recognizes each word considering grammatical factors based on stress, tone, pitch, etc. In this case, the memory unit 220 may further include a database (not shown) including the existing words, so that the word recognizer 253 may recognize the word quickly and easily.

As an example, an operation for recognizing the word “teach” in English by the voice recognition unit 250 of the present embodiment will be described. When / t /, the syllable head of “teach”, is pronounced, the phonetic pronunciation pattern recognizer 251a starts to make sounds when the transverse of the tongue contracts shortly and starts to make sounds. During pronouncing, the posterior paraspinal muscles maintain shortened contractions, and the atmospheric muscles are also constricted. If it is recognized that the atmospheric muscles are intended to pronounce vowels, the phoneme pronunciation pattern recognizer 251a is transverse to the tongue. It is recognized that the muscle was used as the renal vocal muscle, the posterior ring muscle was used as the shortening articulation muscle, and the atmospheric muscle was used as the muscle to pronounce the vowel.

Based on the recognition result of the phoneme pattern recognizer 251a, the phoneme recognizer 251 recognizes that / t / is pronounced using the transverse muscle of the tongue as the elongated vocal muscle while using the posterior ring muscle as a shortening articulation muscle. The syllable recognizer 252 recognizes that / t / is pronounced as a syllable head preceding the vowel in sequential pronunciation based on the use of the atmospheric muscle for pronunciation of the vowel. After the phonetic pronunciation change recognizer 251c recognizes the relaxation of the posterior half root muscle before the pronunciation of the vowel after / t / pronunciation, the phoneme recognizer 251 may confirm that the previously recognized consonant is an unvoiced consonant. Although the phoneme pattern recognizer (251a) recognized that the transverse muscle of the tongue was used as the vocal muscle, it was difficult to determine which of the rump and comb muscles was used as the articulation muscle. ) Recognizes the relaxation of the hindlimb pyramidal muscle, the phoneme recognizer 251 may recognize that / t / is pronounced based on the recognition results.

Following the pronunciation of / t /, the phonetic pronunciation pattern recognizer (251a) recognizes the sound produced by the isotropic contraction of the shield pyramid, and the vocal cord muscle has contracted its contraction during pronunciation from the beginning of pronunciation. If it is recognized that the phoneme pronunciation pattern recognizer 251a recognizes that the shield rhizome is used as the isometric isotonic muscle and the vocal cord muscle is used as the renal articulation muscle. Based on the recognition result of the phoneme pattern recognizer 251a, the phoneme recognizer 251 recognizes that / i / using the vocal cord muscle as the isometric vocal muscle is pronounced while using the vocal cord muscle as the renal articulation muscle, and the syllable recognizer (252) recognizes that / i / is pronounced syllable nucleus based on the vowel pronunciation followed by syllable head / t / through sequential pronunciation.

If, during / i / is pronounced, the phoneme pronunciation change recognizer 251b recognizes that the transverse muscles of the tongue are shortening contractions and recognizes that the hindlimb is shortening contractions, the change recognizer during phoneme pronunciation (251b) recognizes that the posterior biceps and the transverse muscles of the tongue are used as interposition muscles, and the phoneme recognizer 251 indicates that the unvoiced consonants pronounced after the shortening of the transverse muscles of the tongue will be pronounced as the next phoneme. In response, the syllable recognizer 252 predicts that the syllable nucleus is pronounced as the syllable tail after the systolic nucleus undergoes a shortening contraction following the syllable nucleus through overlapping pronunciation.

가 발음되었다고 인식하고, 음절 인식기(252)는 중첩 발음을 통해 음절핵 /i/에 이어 자음이 발음되었음을 근거로

가 음절 꼬리로 발음되었다고 인식한다. After the phonetic pronunciation change recognizer 251c recognizes that the phoneme is pronounced following the pronunciation of / i /, and the phoneme pronunciation pattern recognizer 251a falls when the transverse of the tongue contracts shortly, resulting in a drop in the articulator. At the same time that you start to make a sound and recognize that the vertical muscles of the tongue are rubbing during shortening contractions, and you recognize that the hindlimb muscles have contracted shortening during pronunciation from the beginning of pronunciation, The phoneme pronunciation pattern recognizer 251a is pronounced as the transverse muscles of the tongue are used as elongated vocal muscles, while the vertical muscles of the tongue are used as unilateral vocal muscles. Recognize that it was used. Based on the recognition result of the phonetic pronunciation pattern recognizer 251a, the phoneme recognizer 251 shortens the vertical muscle of the tongue while using the transverse muscle of the tongue as the shortening articulation muscle and the transverse muscle of the tongue as the elongated vocal muscle. Used as a sexual vocal muscle

The syllable recognizer 252 is based on the syllable nucleus / i / followed by the consonant

Recognize that is pronounced as a syllable tail.

의 음소 발음 패턴을 인식할 때 조음 근육으로 뒤반지모뿔근과 빗모뿔근 중 어떤 근육이 사용되는지 인식하지 못한 경우 음소 인식기(251)는 앞선 음절핵 /i/의 음소 발음중 변화 인식기(251b)의 인식 결과 뒤반지모뿔근이 개재 근육으로 사용된 것을 근거로 무성 자음인

로 인식한다.The phonetic pronunciation pattern recognizer (251a) has a syllable tail

When recognizing the phonetic pronunciation pattern of the phonetic muscles, if it is not recognized which of the muscles of the posterior rhizome or comb muscle is used, the phoneme recognizer 251 changes the phoneme pronunciation of the preceding syllable nucleus / i /. Recognition results of a silent consonant based on the use of the posterior pyramidal muscle as an intervening muscle

To be recognized.

가 발음된 것을 종합하여,

라는 음절이 발음된 것을 인식한다.The syllable recognizer 252 is / t / is pronounced as a syllable head, / i / is pronounced as a syllable nucleus, and as a syllable tail

Synthesized by

Recognizes that the syllable is pronounced.

라는 음절에 해당하는 단어가 데이터베이스에 있는지 확인하여 해당하는 단어가 있으면 그 단어를 예비 인식 결과로 저장하면서 음절 인식기(252)의 다음 음절의 인식 결과를 기다려, 다음 인식 결과를 포함하는 단어가 없으면 예비 인식 결과를 인식 결과로 제공하고, 다음 인식 결과를 포함하는 단어가 있으면 그 단어를 예비 인식 결과로 저장하면서 그 다음 음절의 인식 결과를 기다린다. 예를 들면,

의 경우 단어 데이터베이스 상에 “teach”라는 단어가 있고, 그 다음 음절의 인식 결과를 포함하는 단어가 없다면, 단어 인식기(253)는 “teach”를 인식 결과로서 제공할 수 있다. 만약 "teach"를 예비 인식 결과로 인식한 후 다음 음절의 인식 결과가

이고 단어 데이터베이스 상에

에 해당하는 “teacher”라는 단어가 있는 경우, "teacher"를 예비 인식 결과로 인식한 후 그 다음 음절의 인식 결과를 기다리고, 그 다음 음절의 인식 결과를 포함하는 단어가 없다면 단어 인식기(253)는 "teacher"를 인식 결과로서 제공할 수 있다.The word recognizer 253 is recognized through the syllable recognizer 252.

Check whether the word corresponding to the syllable is in the database, and if there is a word, the word is stored as a preliminary recognition result, and the syllable recognizer 252 waits for the recognition result of the next syllable. The recognition result is provided as a recognition result, and if there is a word including the next recognition result, the word is stored as a preliminary recognition result and the recognition result of the next syllable is waited. For example,

In this case, if there is a word “teach” on the word database and there is no word including the result of the recognition of the next syllable, the word recognizer 253 may provide “teach” as the recognition result. If "teach" is recognized as a preliminary recognition result, the recognition result of the next syllable

On the word database

If the word "teacher" corresponds to the word "teacher", it recognizes "teacher" as a preliminary recognition result and waits for the recognition result of the next syllable. If there is no word including the recognition result of the next syllable, the word recognizer 253 "teacher" can be provided as a recognition result.

라는 음절이 발음될 때 강세 근육이 사용되었는지, 음높이 조절 근육이 사용되었는지, 음높이 조절 근육이 사용되었다면 어떻게 사용되었는지를 인식하고, 단어 인식기(253)는 단어 인식에 추가 정보가 필요할 경우 음절 인식기(252)의 인식 결과를 활용한다.The syllable recognizer 252

When a syllable is pronounced, the accented muscle is used, the pitch adjusting muscle is used, and if the pitch adjusting muscle is used, the word recognizer 253 recognizes how the word recognizer is used. ) To use the recognition result.

11 is a diagram illustrating a language learning apparatus according to another embodiment of the present invention.

Referring to FIG. 11, the language learning apparatus 300 includes an input unit 310, a memory unit 320, a speaker 330, a display unit 340, a voice recognition unit 350, an evaluation unit 360, and a learning unit. 370 may include. Similarly, the input unit 310, the memory unit 320, the speaker 330, and the voice recognition unit 350 according to the present exemplary embodiment may include the input unit 110, the memory unit 120, and the speaker 130 of FIGS. 6 and 7. ) And the voice recognition unit 250 have the same function and operation, and thus descriptions of the overlapping configuration of FIGS. 6 and 7 will be omitted.

The display unit 340, in addition to the movement of the muscles according to the position and use of the muscles to give a force to pronounce the speech selected by the user, the position of the muscles according to the pronunciation of the user recognized by the speech recognition unit 350 and The usage may be displayed to the user in the form of muscle movement.

In addition, as in FIG. 6, muscles that give strength to pronounce speech cause the vocal cords or articulators to move. In this case, the display unit 340 may also display the movement of the vocal cords or articulators and the movement of the main root muscle.

In particular, muscles that give strength to pronounce speech can be used as at least one of vocal muscles, articulation muscles, atmospheric muscles, interstitial muscles, stress muscles, tonal muscles, or pitch control muscles, and vocal muscles are one or two vocal muscles. Is used in the manner of isometric, renal or shortening, or two or more different muscles are used simultaneously or in succession. Can be used as a shortening articulation muscle.

The evaluation unit 360 may determine whether the location and use of the muscles according to the pronunciation of the user recognized by the voice recognition unit 350 are within a predetermined range of the location and use of the muscles stored in the memory unit 320. have. At this time, the predetermined range may be set in advance in the language learning apparatus 300, or may be set arbitrarily by the user. That is, the evaluator 360 determines whether the user correctly uses muscles related to the pronunciation of speech to be learned. At this time, the muscle associated with the pronunciation of speech may include muscles that cause movement of the pronunciation organs.

The learner 370 may provide repetitive learning or supplementary learning to the user according to the determination result of the evaluator 360. That is, when it is determined by the evaluator 360 that the position and use of the muscle according to the user's pronunciation are within a predetermined range with respect to the position and use of the muscle stored in the memory 320, the learning unit 370 Repeated learning can strengthen muscle memory.

In addition, when it is determined by the evaluator 360 that the position and use of the muscles according to the user's pronunciation are within a predetermined range with respect to the position and use of the muscles stored in the memory 320, the learning unit 370 may be used. Speech recognition recognition evaluation may be further performed to evaluate whether the user can distinguish between words that have different consonants or vowels but are similarly pronounced. At this time, the speech recognition evaluation can distinguish words that have different vowels or consonants but are actually pronounced similarly, for example, “and” and “end”, “pet” and “fat”, “day” and “they”. It is to evaluate whether there is.

On the other hand, when it is determined in the evaluation unit 360 that the position and use of the muscles according to the user's pronunciation is not within a predetermined range for the position and use of the muscles stored in the memory 320, the learning unit 370 The display unit 340 to provide a supplementary learning to the user by displaying the position and the use of the muscle to give a force to pronounce the speech sound at least one of the shape or color of the muscle, the shape change, or the expression of the hand gesture. Can be. At this time, supplementary learning through a change in the shape, color, or shape of a muscle or a hand gesture may be performed by the display unit 140 in the manner described with reference to FIG. 6.

12 is a diagram illustrating a language learning method according to an embodiment of the present invention.

The language learning method of FIG. 12 may use an apparatus including a memory unit configured to store voice information of speech sounds and information about a location of muscles and a method of using muscles to pronounce speech sounds. For example, the language learning method according to the present embodiment may use the language learning apparatus 100 according to FIG. 6, and hereinafter, it is assumed that the language learning apparatus 100 according to FIG. 6 is used. It demonstrates concretely.

First, information of speech sounds including at least one of a phoneme, a syllable, a word, and a second segment sound that can be selected by a user is displayed on the display 140 of the language learning apparatus 100. Thereafter, any speech information is selected by the user through the input unit 110 (S110).

Control means, not shown, such as the CPU of the language learning apparatus 100 according to the signal input through the input unit 110 by the user, according to the position and use of the muscle to give a force to pronounce the speech selected by the user The movement of the muscles may be displayed and the spoken words may be spoken by giving power to the muscles (S120). That is, the user can easily determine which muscle is used in which way by directly speaking the words that the user wants to learn by voice and visually displaying the movements of the muscles that give power to pronounce the words. To be able.

13 is a diagram illustrating a language learning method according to another embodiment of the present invention.

The language learning method of FIG. 13 stores information of speech sounds (for example, may include speech information of speech sounds, visual information, etc.) and information on the location and usage of muscles that give power to pronounce speech sounds. A device including a memory unit can be used. For example, the language learning method according to the present embodiment may use the language learning apparatus 200 according to FIG. 9, and hereinafter, assumes that the language learning apparatus 200 according to FIG. 9 is used. It demonstrates concretely.

First, information of speech sounds including at least one of a phoneme, a syllable, a word, and a second segment sound that can be selected by a user is displayed on the display 240 of the language learning apparatus 200. Thereafter, any speech information is selected by the user through the input unit 210 (S210).

If the user pronounces the selected sound, the language learning apparatus 200 may recognize the user's pronunciation. At this time, the recognition of the user's pronunciation may be performed by the voice recognition unit 250 described above. That is, when the user directly pronounces the selected speech, the user may recognize the location of the muscle applied by the user to pronounce the speech and the manner of use using the sound wave information by the user pronounce the speech (S220).

Next, according to a signal of a control unit (not shown) such as a CPU of the language learning apparatus 200, the position and usage of muscles according to the pronunciation of the user recognized by the voice recognition unit may be displayed to the user (S230). . That is, the position and usage of the muscles according to the pronunciation of the user recognized by the voice recognition unit 250 may be directly displayed to the user through the aforementioned display unit 240 in the form of muscle movement. This allows the user to visually show the location and use of the muscles that the user has applied to pronounce the speech selected by the user so that the user can determine whether he has used the appropriate muscle in order to pronounce the speech. Can be.

14 is a diagram illustrating a language learning method according to another embodiment of the present invention.

The language learning method of FIG. 14 may use an apparatus including a memory unit configured to store voice information of speech sounds and information regarding a location of muscles and a method of using muscles to pronounce speech sounds. For example, the language learning method according to the present embodiment may use the language learning apparatus 300 according to FIG. 11, and hereinafter, it is assumed that the language learning apparatus 300 according to FIG. 11 is used. It demonstrates concretely.

First, information of speech sounds including at least one of a phoneme, a syllable, a word, and a second segment sound that can be selected by a user is displayed on the display 340 of the language learning apparatus 300. Thereafter, any speech information is selected by the user through the input unit 310 (S310).

Control means (not shown) such as a CPU of the language learning apparatus 300 displays the movement of the muscles according to the position and use of the muscles associated with the pronunciation of the words according to a signal input by the user through the input unit 310. And, using the muscle can tell the sound of the pronunciation (S320). The detailed scheme is the same as that of step S120 of FIG.

If the user pronounces the selected sound, the language learning apparatus 300 may recognize the user's pronunciation. In this case, the recognition of the user's pronunciation may be performed by the voice recognition unit 350 described above. That is, when the user directly pronounces the selected speech, the user may recognize the location of the muscle applied by the user to pronounce the speech and the manner of use using the sound wave information by the user pronounce the speech (S330). The detailed manner is the same as step S220 of FIG.

The language learning apparatus 300 may determine whether the location and use of the muscles according to the recognized pronunciation of the user are within a predetermined range with respect to the location and use of the muscles stored in the memory unit (S340). Here, the predetermined range may be set in advance in the language learning apparatus or may be arbitrarily set by the user.

At this time, if it is determined that the position and use of the muscle according to the pronunciation of the user is within a predetermined range with respect to the position and use of the muscle stored in the memory unit (YES), the process proceeds to step S350 and the muscle through repeated learning. Can enhance memory. For example, repetitive learning may be performed by going back to step S320 or step S330 of FIG. 14. In addition, after the repetitive learning, as described above, the method may further include a step (not shown) of evaluating whether the user can distinguish between words having different consonants or vowels.

On the other hand, if it is determined that the position and use of the muscles according to the pronunciation of the user are not within a predetermined range with respect to the position and use of the muscles stored in the memory unit (NO), the process proceeds to step S360, for example, speech sounds. Supplementary learning may be provided to the user by displaying the position and the use of the muscles that give power to pronounce the muscles in the form or color of a muscle, a change in a figure, or a hand gesture.

In addition, as described above, muscles that give power to pronounce speech may include the apical muscles that move the vocal cords or articulators, and the apical muscles that move the vocal cords or articulators may include vocal muscles, articulation muscles, atmospheric muscles, interstitial muscles, It may be used as at least one of tonal muscle or pitch control muscle. On the other hand, the vocal muscles may be used by using one or two vocal muscles in the manner of isometric vocal muscles, elongated vocal muscles, or unilateral vocal muscles, or by using two vocal muscles simultaneously or sequentially in different ways. The articulation muscles can be used as renal articulation muscles or shortening articulation muscles.

15 is a diagram illustrating a user terminal including a language learning server and a language learning application according to an embodiment of the present invention connected through a network.

Here, the language learning server 300 may have at least some of the functions of the language learning apparatus according to an embodiment of the present invention, and the present disclosure is not limited thereto. The language of the user terminal 500 may be defined according to an embodiment of the present invention. It may also include at least some of the functions of the learning apparatus. In addition, the user terminal 500 may include, for example, a mobile terminal such as a smartphone or a tablet, but is not limited thereto and may include a device such as a PC. When the user selects the speech sounds (for example, phonemes, syllables, words, second segment sounds, etc.) to be learned through the user terminal 500, the selected speech information is transferred to the language learning server 300 through the network 400. Can be sent.

At this time, the language learning server 300 displays the movement of the muscles according to the position and use of the muscles to give power to pronounce the speech to the speech sound selected by the user, the voice of the speech sound pronounced using the muscle Information may be transmitted to the user terminal 500 through the network 400.

The language learning server 300 uses the sound wave information according to the pronunciation of the user recognized by the voice recognizer of the user terminal 500 to provide information about the location and usage of muscles that the user has given power to pronounce words. By transmitting to the user terminal 500 through the network 400 may be displayed on the display to the user. In this case, the sound wave information recognized by the user terminal 500 is transmitted to the language learning server 300 so as to recognize a location and a usage method of a muscle applied by the user to pronounce a speech sound, but the present invention is not limited thereto. Using the sound wave information in the terminal 500 to recognize the location and use of the muscles that the user has given power to pronounce the speech, and transmits the recognition result to the language learning server 300 through the network 400 It is possible.

In addition, the language learning server 300 uses the sound wave information by the user pronounced, the position and use of the muscles recognized after the user recognizes the position and use of the muscles that gave the force to pronounce words The location of the muscle stored in the memory unit and the manner of use may be determined within a predetermined range. At this time, if it is determined that it is within a predetermined range, it is possible to reinforce the muscle memory through repetitive learning, and if it is determined that it is not within the predetermined range, supplementary learning (for example, of the muscle used to pronounce a speech sound) is performed. Location and mode of use may be provided as a form of muscle, a change in color, shape, or a hand gesture.

16 is a diagram illustrating a hardware configuration of a user terminal including a language learning application according to an embodiment of the present invention.

Referring to FIG. 16, the user terminal 500 may include a CPU 510, a memory 520, a display unit 530, an I / F unit 540, and a communication module 550.

The CPU 510 executes a language learning application stored in the user terminal 500. The memory 520 includes a language learning application, sound wave information according to a user's pronunciation, and a muscle for a user's pronunciation received from a server. Information regarding the location and the manner of use may be stored.

The display unit 530 is information on the location and use of the muscles to give a force to pronounce the speech selected by the user received from the server, information on the location and use of the muscle according to the recognized user pronunciation, pronunciation of the speech In order to display the muscle shape, color, figure change, or hand movement, etc., about the location and use of muscles to give strength to the user as a movement of the muscle, or to change the shape, color, shape, or hand movement of the muscle. I can display it. To this end, the CPU 510 may display a GUI on the display unit 530 by executing a language learning application, and the user may input a desired instruction through the GUI.

The I / F unit 540 may perform an interface function between an input from a user and an output signal of the user terminal 500. For example, the I / F unit 540 may be an input device such as a touch panel. The I / F unit 540 may provide an instruction (for example, speech information to be learned) based on a GUI displayed on the display unit 530. An instruction to select) may be input through the I / F unit 540.

In addition, the communication module 550 is connected to the language learning server 300 through the network 400, the information on the location of the muscles and the manner of use to give power to pronounce the speech selected by the user, the recognized user's pronunciation To communicate various information such as the shape of the muscle, the change in the color, the shape, or the expression of the hand gesture for the position of the muscle and the way of using the voice, and the position of the muscle used for pronunciation Can be.

17 is a diagram illustrating an operation of performing language learning by communicating between a language learning server and a user terminal including a language learning application according to an embodiment of the present invention.

Referring to FIG. 17, an application for language learning according to an embodiment of the present invention may be provided to a user terminal that communicates with a server that stores voice information of speech sounds and information about a location and usage method of muscles that give power to pronounce speech sounds. It may be a stored language learning application.

First, a user selects information of a speech sound including at least one of a phoneme, a syllable, a word, and a second segment sound through the user terminal 500 (S11). Then, the user terminal 500 transmits the speech information selected by the user through the network 400 to the language learning server 300 (S12).

The language learning server 300 transmits the information on the position and the use method of the muscles that give power to pronounce the selected speech and the voice data pronounced through the muscles to the user terminal 500 (S13).

 The user terminal 500 displays the information on the position and the use of the muscles to give power to pronounce the speech received from the server in the form of muscle movement on the display unit, and the speech sounds to be pronounced using the corresponding muscle (voice information) ) To the user through the speaker (S14).

Through this, the user can directly see and determine which muscle should be moved in what way to pronounce the speech selected by the user.

18 is a diagram illustrating an operation of performing language learning by communicating with a user terminal including a language learning server and a language learning application according to another embodiment of the present invention.

Referring to FIG. 18, an application for language learning according to an embodiment of the present invention may be provided to a user terminal that communicates with a server that stores voice information of speech sounds and information about a location and usage method of muscles that give power to pronounce speech sounds. It may be a stored language learning application.

First, a user selects information of a speech sound including at least one of a phoneme, a syllable, a word, and a second segment sound through the user terminal 500 (S21).

Next, when the user pronounces the selected sound, the user terminal 500 recognizes the sound wave according to the user's pronunciation (S22). In this case, the user terminal 500 may further include a microphone (not shown) for recognizing a sound wave according to a user's pronunciation.

The user terminal 500 transmits the sound wave information on the recognized pronunciation of the user's speech to the language learning server 300 (S23).

The language learning server 300 recognizes the position of the muscle according to the pronunciation of the user and the method of use based on the sound wave information regarding the recognized pronunciation of the user (S24). That is, by using sound wave information by the user pronouncing the speech, it is determined which muscle the user pronounced and how.

The language learning server 300 transmits the information about the location and use of the muscles according to the determined pronunciation of the user to the user terminal 500 (S25). Next, the user terminal 500 displays the information on the position and use of the muscle received from the language learning server 300 on the display in the form of muscle movement (S26).

Through this, the user can directly determine which muscle is used and how to pronounce the speech selected by the user, and directly determine, and compare the position of the muscle to be used to pronounce the speech and the method of use. .

19 is a diagram illustrating an operation of performing language learning by communicating with a user terminal including a language learning server and a language learning application according to another embodiment of the present invention.

Referring to FIG. 19, an application for language learning according to an embodiment of the present invention may be provided to a user terminal that communicates with a server that stores voice information of a voice and information about a location and usage of muscles that give power to pronounce the voice. It may be a stored language learning application.

First, a user selects information of a speech sound including at least one of a phoneme, a syllable, a word, and a second segment sound through the user terminal 500 (S31). Then, the user terminal 500 transmits the speech information selected by the user through the network 400 to the language learning server 300 (S32).

The language learning server 300 transmits the information on the position and the use method of the muscles that give power to pronounce the selected speech and the voice data pronounced through the muscle to the user terminal 500 (S33).

In addition, the user terminal 500 is displayed on the display unit in the form of muscle movement information on the position and use of the muscle to give a force to pronounce the speech received from the server, the speech sound using the muscle To the user through the speaker (S34).

Next, when the user pronounces the selected sound, the user terminal 500 recognizes the sound wave according to the user's pronunciation (S35). In this case, the user terminal 500 may further include a microphone (not shown) for recognizing a sound wave according to a user's pronunciation. In operation S36, the user terminal 500 transmits sound wave information on the recognized pronunciation of the user's speech to the language learning server 300.

The language learning server 300 recognizes the location and use of muscles that the user has given power to pronounce the words by using sound wave information by the user pronounce the words, and recognizes the muscles according to the pronunciation of the user. It is determined whether the location and the usage method are within a predetermined range with respect to the location and the usage method of the muscle stored in the server 300 (S37). In this case, the predetermined range may be set in the server 300 itself, or may be configured to be set directly by the user through the language learning application on the user terminal 500.

In step S37, if it is determined that the position and use of the muscle according to the pronunciation of the user are within a predetermined range with respect to the position and use of the muscle stored in the server 300 (YES), repeat memory is provided to provide the muscle memory. Strengthen. In other words, the process may return to step S34 to allow the user to pronounce the speech repeatedly and to receive feedback from the language learning server 300 (S38).

In step S37, when it is determined that the position and use of the muscles according to the pronunciation of the user are not within a predetermined range with respect to the position and use of the muscles stored in the server (NO), the language learning server 300 moves to the user terminal. Supplementary learning may be provided (S39). For example, the supplementary learning may be to display the position and use of the muscle used to pronounce the speech in the form, color, figure of the muscle, or hand gesture representation (S40).

In FIGS. 17 to 19, when the user selects speech information desired by the plurality of user terminals 500, the related data is transmitted to the server 300 and the data is received from the server 300. The invention is not limited thereto. For example, in another embodiment, the plurality of user terminals 500 directly download a language learning application from the server 300, and store the same in a memory 520, and thereafter, without a separate communication with the server 300. Through the application stored in the terminal 500 may be configured to operate on the language learning itself. In this case, the language learning application may perform the operation by directly executing the steps illustrated in FIGS. 12 to 14 on the user terminal 500.

Thus, according to the language learning apparatus according to an embodiment of the present invention, by using the muscle memory, the pronunciation of each segment of vowels and consonants, syllables, words, and accents such as stress, tone, pitch control, etc. By recognizing and recognizing, the effect of language learning can be improved. In addition, it is an effect that provides an opportunity to learn a language by allowing the person who has not learned a language because he cannot hear the voice, and learns directly by looking at the position of the muscle that causes the movement of the pronunciation organ and the movement of the muscle according to the usage method. Can be achieved.

In the above description, it is described that all the components constituting the embodiments of the present invention are combined or operated in one, but the present invention is not necessarily limited to these embodiments. That is, within the scope of the present invention, all of the components may be selectively operated in combination with one or more.

In addition, the terms "comprise", "comprise" or "having" described above mean that the corresponding component may be inherent unless otherwise stated, and thus, other components are excluded. It should be construed that it may further include other components instead. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. Terms commonly used, such as terms defined in a dictionary, should be interpreted to coincide with the contextual meaning of the related art, and shall not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present invention.

The above description is merely illustrative of the technical idea of the present invention, and those skilled in the art to which the present invention pertains may make various modifications and changes without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention but to describe the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100, 200, 300: language learning device (server) 110, 210, 310: input unit
120, 220, 320: Memory unit 130, 330: Speaker
140, 240, 340: display unit 250, 350: speech recognition unit
251 phoneme recognizer 251a phoneme pronunciation pattern recognizer
251b: Phoneme change recognizer 251c: Phoneme change recognizer
252: syllable recognizer 253: word recognizer
360: evaluation unit 370: learning unit
400: network 500: user terminal
510: CPU 520: memory
530: display unit 540: I / F unit
550: communication module

Claims (30)

An input unit configured to select information of a speech sound including at least one of a phoneme, a syllable, a word, and a second segment sound;
A memory unit for storing voice information of the speech sound selected by the input unit and information on the location and usage of muscles that give power to pronounce the speech sound;
A display unit which displays the movement of the muscles according to the position and use of the muscles to give power to pronounce the speech; And
A language learning device comprising a speaker for telling the user the sound of the sound to pronounce the force by the muscle. The method according to claim 1,
The display unit is a language learning device for displaying the movement of the muscle according to the position and use of the muscle to give a force to pronounce the speech in at least one of the shape, color, shape of the muscle, or gesture expression. The method according to claim 1,
The display unit is a language learning device for displaying the movement of the muscle according to the position and use of the muscle to give a force to pronounce the speech by dividing the sequential pronunciation or superimposed pronunciation when the user pronounces the phoneme. An input unit configured to select information of a speech sound including at least one of a phoneme, a syllable, a word, and a second segment sound;
A memory unit for storing information about the speech sound selected by the input unit, and information about the position of the muscle that gives force to pronounce the speech and how to use the speech sound;
A speech recognition unit for recognizing the location and usage of muscles that the user exerts force to pronounce the speech using the sound wave information by the user pronouncing the speech; And
And a display unit which displays the movement of the muscles according to the position and use of the muscles recognized by the voice recognition unit to the user. The method according to claim 4,
The speech recognition unit includes a table in which the information of the speech sounds and the information on the combination of the position of the muscles and the manner of use that give power to pronounce the speech sounds are mapped.
The speech recognition unit is a language learning device for determining the information of the speech sound pronounced by the user using the recognized position and use of the muscle and the table. The method according to claim 4,
The speech recognizer recognizes the phoneme by dividing it into sequential pronunciation or superimposed pronunciation when the user subsequently pronounces the phoneme.
The display unit is a language learning apparatus for displaying the movement according to the position and use of the muscles applied to pronounce the speech by dividing the sequential pronunciation or superimposed pronunciation when the user pronounces the phoneme. The method according to claim 4,
The speech recognition unit,
A phoneme recognizer for recognizing a phoneme through the location and use of the muscle to give power to pronounce the speech used for the user's pronunciation;
A syllable recognizer that recognizes syllables by dividing the consonant or vowel pronounced by the user into syllable heads, syllable nucleus, and syllable tails; And
And a word recognizer that recognizes a word based on a connection state between the recognized syllables and a grammatical element. The method according to claim 4,
A speaker for sounding the speech sound by giving power to the muscle;
An evaluator configured to determine whether the position and use of the muscle according to the pronunciation of the user recognized by the voice recognition unit are within a predetermined range with respect to the position and use of the muscle stored in the memory unit; And
When the evaluation unit determines that the location and use of the muscles according to the pronunciation of the user is within a predetermined range for the location and use of the muscles stored in the memory unit, reinforcing muscle memory through repeated learning Further includes a learning unit,
The display unit is a language learning device for displaying the movement of the muscles in accordance with the position and use of the muscles to give power to pronounce the sound spoken through the speaker. The method according to claim 8,
If it is determined by the evaluator that the location and use of the muscle according to the pronunciation of the user are not within a predetermined range with respect to the location and use of the muscle stored in the memory unit, the learning unit is arranged on the display unit. Providing supplementary learning to the user by displaying the movement of the muscle according to the position and use of the muscle that gives power to pronounce the speech as at least one of the shape, color, shape change, or hand gesture expression of the muscle Language learning device. The method according to claim 8,
If it is determined by the evaluation unit that the location and use of the muscle according to the pronunciation of the user is within a predetermined range with respect to the location and use of the muscle stored in the memory unit, the learning unit is different from the consonant or vowel And a speech recognition evaluation for evaluating whether the user can distinguish similarly pronounced words. The method according to claim 1, 4 or 8,
The muscles that give strength to pronounce the speech include the psoas muscles that move the vocal cords or articulators,
The display unit is a language learning device for displaying the movement of the vocal cord or the articulator and the movement of the main root muscle. The method according to claim 11,
The main muscle for moving the vocal cord or the articulator to pronounce the speech is used as at least one of vocal muscles, articulation muscles, atmospheric muscles, interposition muscles, tonal muscles, stress muscles and pitch control muscles. The method according to claim 12,
If the speech is a vowel,
The memory unit is a muscle that gives power to pronounce the vowel, and stores information about the position and usage of the muscles for narrowing the vocal cords and the muscles for adjusting the length of the vocal cords,
The display unit, the language learning device for displaying the movement of the muscles according to the position and use of the muscles to narrow the interval between the vocal cords and the length of the vocal cords. The method according to claim 12,
If the speech is a consonant,
The memory unit is a muscle that gives strength to pronounce the consonant, and uses muscles around the lips, muscles inside the tongue, muscles connected to the tongue, and muscles connected to the cervical bone as the vocal muscles, and the comb muscles and the posterior ring horns. Store information about how the muscles and palatine pharynx are used as the articulation muscles,
The display unit uses the muscles around the lips, the internal muscles of the tongue, the muscles connected to the tongue, and the muscles connected to the cervical bone as the vocal muscles, and the comb pyramid, the posterior ring ruff, and the palatine pharyngeal muscle. The language learning apparatus for displaying the movement of the muscles according to the method used as the articulation muscle. The method according to claim 12,
When used as the adult muscle,
The memory unit is a method of using the tonal muscles, i) maintaining the stretch contraction of the vocal cords during the pronunciation of one syllable, or ii) exerting the stretching contractions in the relaxed state of the vocal cords; iii) exerting a contractile contraction as soon as the vocal cord muscles are relaxed to shorten contractions, or iv) vocal cords undergoing contractile contractions with elongated contractions, or v) storing at least some of the information on how to use the vocal cords to relax, or vi) to maintain the pitch of the sound or to vary the pitch by keeping the vocal cords contracting shortened. and,
The display unit, the language learning device for displaying the movement of the muscles according to the method of using the adult muscles. The method according to claim 12,
When used as the pitch control muscles,
The memory unit, as the use of the pitch control muscles, the ring shield muscles and the shield pharyngeal muscles are relaxed i) the vocal cord muscles shortened, ii) vocal cord muscles relaxed, iii) vocal cord muscles Iv) the vocal cord muscles were shortened, the ring shield muscles were shortened, and the shield pharynx was relaxed. Information on how to adjust the pitch so that the vocabulary muscles are shortened in force, vi) the vocal cords are relaxed, and vii) the vocal cords are gradually sounded in order. Save at least some of the
The display unit, the language learning device for displaying the movement of the muscles according to the use of the pitch-adjusted muscle. The method according to claim 12,
When used as the stress muscle,
The memory unit, in order to accentuate the sound of the speech, to give a force to shorten the shield cervical muscle in a state where the cervical vertebrae is fixed, or to force the anterior muscles of the jaw muscles in a state where the cervical vertebrae are not fixed. Store information about the use of the accent muscle to pronounce the speech
The display unit, the language learning device for displaying the movement of the muscles according to the use of the stressed muscles. The method according to claim 12,
When used as the vocal muscles,
The memory unit may use one or two vocal muscles as a method of isotropic vocal muscles, a method using eccentric vocal muscles, or a method of using unilateral vocal muscles or using two vocal muscles. Store information about how to use them simultaneously or sequentially in different ways,
The display unit, the language learning device for displaying the movement of the muscles according to the use method of the vocal muscles. The method according to claim 12,
When used as the articulation muscles,
The memory unit stores information about a method of using the renal articulation muscle or the shortening articulation muscle,
The display unit, the language learning device for displaying the movement of the muscles according to the use of the articulated muscle. The method according to claim 12,
When used as the atmospheric muscles,
When the two phonemes are sequentially pronounced, the memory unit contracts information before articulation of the front phoneme and maintains the contracted state during pronunciation of the front phoneme. Save it,
The display unit, the language learning device for displaying the movement of the muscles according to the use of the atmospheric muscle. The method according to claim 12,
When used as the interstitial muscle,
The memory unit stores information about articulation muscles and vocal muscles for pronunciation of the back phoneme, which are contracted during pronunciation of the front phoneme when the two phonemes are pronounced followed by overlapping pronunciation.
The display unit, the language learning apparatus for displaying the movement of the muscles according to the use of the interposition muscle. A memory unit for storing information of speech sounds and information on the location of muscles and the manner of use of the muscles that give power to pronounce the speech sounds;
A speech recognition unit for recognizing the location and usage of muscles that the user exerts force to pronounce the speech using the sound wave information by the user pronouncing the speech; And
And a display unit configured to display to the user what speech sounds the user pronounced based on the movement of the muscle according to the position and use of the muscle recognized by the speech recognition unit. Method for learning a language using a device including voice information of a speech sound including at least one of a phoneme, a syllable, a word, and a segmental sound, and a memory unit configured to store information about a location and a usage method of muscles that give power to pronounce the speech As
Selecting information of the speech by a user; And
And displaying the movements of the muscles according to the position and use of the muscles that give power to pronounce the speech selected by the user, and giving the muscles the sound of the words. What is claimed is: 1. A language learning method using a device including a memory unit for storing information on speech sounds including at least one of a phoneme, syllables, words, and segmental sounds, and information on the location and usage of muscles that give power to pronounce the speech. ,
Selecting information of the speech by a user;
Recognizing the location and usage of muscles that the user exerts force to pronounce the speech using the sound wave information by the user pronouncing the speech; And
And displaying the movement of the muscle according to the recognized position of the muscle and the usage manner to the user. Method for learning a language using a device including voice information of a speech sound including at least one of a phoneme, a syllable, a word, and a segmental sound, and a memory unit configured to store information about a location and a usage method of muscles that give power to pronounce the speech As
Selecting information of the speech by a user;
Displaying the movement of the muscles according to the position and use of the muscles that give power to pronounce the speech, and giving the muscles a sound to pronounce the speech;
Recognizing the location and usage of muscles that the user exerts force to pronounce the speech using the sound wave information by the user pronouncing the speech;
Determining whether the recognized position and use of the muscle are within a predetermined range with respect to the position and use of the muscle stored in the memory unit; And
If it is determined that the position and use of the muscle according to the pronunciation of the user are within a predetermined range with respect to the position and use of the muscle stored in the memory unit, reinforcing muscle memory through repetitive learning; How to learn a language. The method according to claim 25,
If it is determined that the position and use of the muscle according to the pronunciation of the user is not within a predetermined range with respect to the position and use of the muscle stored in the memory unit, the muscle of the muscle that gives a force to pronounce the speech And providing supplementary learning to the user by displaying the movement of the muscle according to the position and the usage manner by at least one of the shape, color, shape change, or hand gesture expression of the muscle. The method according to claim 25,
If it is determined that the location and use of the muscle according to the user's pronunciation are within a predetermined range with respect to the location and use of the muscle stored in the memory unit, the consonants or vowels are different but similarly pronounced words. Further comprising evaluating whether the user can distinguish. The method according to any one of claims 23 to 25,
The muscles that give strength to pronounce the speech include the psoas muscles that move the vocal cords or articulators,
The displaying of the muscle movement to the user may include displaying the movement of the vocal cord or the articulator and the movement of the main root muscle. The method according to claim 28,
The vocal cord, which causes the vocal cords or the articulator to move, is used as at least one of vocal muscles, articulation muscles, atmospheric muscles, interposition muscles, tonal muscles, stress muscles and pitch control muscles. The method of claim 29,
The vocal muscles may be used by using one or two vocal muscles in any one of isotropic, elongated vocal, or uniaxial vocal muscles, or by using two or more vocal muscles simultaneously or sequentially in different ways. Use,
The said articulation muscle is a language learning method used as an elongate articulation muscle or a shortening articulation muscle.

Images