KR20140004541A - Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine - Google Patents

Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine Download PDF

Info

Publication number
KR20140004541A
KR20140004541A KR1020120072544A KR20120072544A KR20140004541A KR 20140004541 A KR20140004541 A KR 20140004541A KR 1020120072544 A KR1020120072544 A KR 1020120072544A KR 20120072544 A KR20120072544 A KR 20120072544A KR 20140004541 A KR20140004541 A KR 20140004541A
Authority
KR
South Korea
Prior art keywords
phoneme
phonemes
user terminal
providing
words
Prior art date
Application number
KR1020120072544A
Other languages
Korean (ko)
Inventor
전은경
김종기
문미정
원철희
윤성희
김경숙
이진영
권요성
윤산정
Original Assignee
(주)아이티씨교육
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by (주)아이티씨교육 filed Critical (주)아이티씨교육
Priority to KR1020120072544A priority Critical patent/KR20140004541A/en
Publication of KR20140004541A publication Critical patent/KR20140004541A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G06Q50/2053—Education institution selection, admissions, or financial aid
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G06Q50/2057—Career enhancement or continuing education service
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The present invention relates to a method for providing a foreign language phonics learning service, and according to the method for providing a foreign language phonics learning service through phoneme feedback using a speech recognition engine proposed by the present invention, the phonemes used by the service providing server in the target language are By presenting and providing phonics learning services for a plurality of words containing the phonemes for each phoneme, and adopting a configuration that transmits the shape of the mouth that pronounces the words as a video and provides detailed phonemic feedback, It is possible to precisely correct the pronunciation of a foreign language corresponding to each phoneme, and become familiar with the sounds of foreign languages and the oral structure of pronunciation, thereby increasing the sensitivity to foreign language sounds that were hard to be heard due to the effects of the native language sounds, and each phoneme of ambiguous foreign languages. Listening to foreign languages with clear perception of differences Improve, and can cause the user's interests and strengthen the motivation of pronunciation exercises.
In addition, according to the present invention, the service providing server stores the score for each phoneme set in each step to provide a cumulative score for each phoneme to the user terminal, according to the information and learning date for the phonemes and vulnerable phonemes excellent user utterance By providing information on cumulative score changes for each phoneme, you can precisely correct pronunciation while practicing vulnerable phonemes more intensively, and intuitively show the effect of pronunciation practice.
In addition, according to the present invention, by further comprising a phonics learning step for the group of words that combine two or more words to generate a sound, it is possible to improve the pronunciation and sound listening ability of the foreign language made by the sound.

Description

How to provide foreign language phonics learning service through phoneme feedback using speech recognition engine {METHOD FOR PROVIDING FOREIGN LANGUAGE PHONICS TRAINING SERVICE BASED ON FEEDBACK FOR EACH PHONEME USING SPEECH RECOGNITION ENGINE}

The present invention relates to a method for providing a foreign language phonics learning service, and more particularly, to a method for providing a foreign language phonics learning service through feedback of phonemes using a speech recognition engine.

As the need for global talent for active international exchange and diplomacy expands, so does the expectation for fluent pronunciation in foreign language use. In foreign language learning, phonics learning to learn the correct pronunciation of phoneme, which is a basic unit of foreign language sounds, can greatly improve foreign language pronunciation as well as listening to foreign languages and understanding sentences. Phonics (learning) was originally designed as a method for acquiring English characters for natives in the high illiteracy state of the United States. . These phonics learning methods are now being applied to many learners who are learning foreign languages, can read foreign language words with correct pronunciation, and read each word quickly by combining basic phonemes, thus preventing them from understanding the meaning of foreign language sentences. You can expect the learning effect to minimize the

Infants who acquire their mother tongue naturally learn their native pronunciation through the crucial acquisition of language in their growing environment, but after their native language is formed, their ability to hear or speak sounds that do not exist in their native language is deteriorated. In addition, foreign language learners need to consciously recognize and practice foreign language pronunciation. For example, the phonemes of English [f], [v], [r], [z], etc., do not exist at all in the Korean language. If used, the brain considers the sound unused and makes it difficult to hear or pronounce and cannot handle it delicately, so neither [p] nor [f] is a sound that can be recognized by oneself. You are likely to hear and speak with your pronunciation. Therefore, in phonics learning, by checking the location of the native oral organs (mouth, tongue, teeth, palate, etc.), listening to the exact foreign language and practicing the pronunciation accordingly, along with self-correction through elaborate and discriminating feedback on pronunciation If this is done, a very large learning effect can be achieved.

In Korea, phonics learning is mainly an introductory study of English for infants, and various services are provided from learning through specialized textbooks to songs and games, and phonics learning devices related to alphabets have been developed (Patent Application No. 10). -2009-0050753). However, the existing phonics learning method is not only character-oriented learning, but merely a method of following the voice of native speakers, and development of a systematic and original method that has a remarkable effect in the method of providing foreign language learning services is insufficient. . Accordingly, the present inventors, by first listening to the pronunciation associated with the letters of the foreign language correctly recognized, by providing detailed feedback of the phoneme unit in the process of repeating the direct sound practice, effective learning service that can improve foreign language pronunciation and listening skills An attempt was made to develop a provisioning method.

The present invention has been proposed to solve the above problems of the conventionally proposed methods, phonics for a plurality of words containing the phonemes for each phoneme presented first to the phonemes used by the service providing server learning language By providing a learning service, a configuration that transmits the shape of the mouth that pronounces the word as a video, and a configuration that provides detailed phonemic feedback, the foreign language pronunciation of each phoneme can be corrected precisely. As you become familiar with the oral structure of sound and pronunciation, you can improve the sensitivity of foreign language sounds that were hard to hear due to the influence of your native language, and improve the ability to listen to foreign languages by clearly recognizing the differences of each phoneme in the ambiguous foreign language. Voice recognition can induce interest and strengthen motivation of pronunciation practice To provide a language learning phonics service delivery through each phoneme feedback using the binary for that purpose.

In addition, the present invention, the service providing server stores the score for each phoneme set at each step to provide a cumulative score for each phoneme to the user terminal, the phoneme according to the information and learning date for phonemes and vulnerable phonemes excellent user utterance By providing information on the cumulative score change of each star, the phonetic feedback using the speech recognition engine enables you to precisely correct pronunciation while practicing vulnerable phonemes more intensively, and to show the effect of pronunciation practice intuitively. Another object is to provide a method for providing foreign language phonics learning services.

In addition, the present invention further includes a phonics learning step for word groups in which two or more words are combined to generate a consonant, thereby improving speech fluency and ability to listen to a foreign language made by the consonant. Another object of the present invention is to provide a foreign language phonics learning service providing method through phoneme feedback using an engine.

A method for providing a foreign language listening ability through the listening and speaking using the voice recognition engine according to the characteristics of the present invention for achieving the above object includes a service providing server for providing a foreign language phonics learning service,

(1) transmitting phonemes used in the target language to a user terminal and receiving a selection of one phoneme from the user terminal;

(2) transmitting a plurality of words including the phonemes selected and selected in step (1) to the user terminal, and transmitting a mouth shape for pronouncing one word among the plurality of words as a video to the user terminal; ;

(3) recording and transmitting a user's voice uttering a word transmitted from the user terminal as a video in step (2) using a voice recognition engine;

(4) providing the user terminal with a total score obtained by summing scores by phonemes for the user voices received in step (3);

(5) Steps (1) to (4) of the phonemes of step (1) and other phonemes or words that have not been performed in steps (1) to (4) among the phonemes of step (1) and words of step (2). Performing the same process as; And

And (6) providing the user terminal with a cumulative score for each phoneme accumulated in the phoneme scores set in steps (4) and (5) to the user terminal.

Preferably, the step (2)

After transmitting the plurality of words including the phonemes selected and selected in step (1) to the user terminal, one word among the plurality of words is selected and input from the user terminal, and the selected input word is pronounced. It may be a step of transmitting the shape of the mouth to the video.

Preferably, in step (4) or step (5),

The total score and the detailed score set for each phoneme may be displayed on the user terminal by displaying one or more selected from the group including numbers, alphabets, and graphs.

Preferably, in step (6),

The cumulative score for each phoneme may provide information on phonemes with excellent phonetics and vulnerable phonemes.

Preferably, in step (6),

Information about cumulative score change for each phoneme according to a learning date may be provided for each phoneme.

Preferably, after step (5) or step (6),

(a) transmitting a group of words that combine a plurality of words to cause a noise, to the user terminal, and transmitting a shape of a mouth that pronounces one word group among the word groups as a moving picture;

(b) receiving and recording a user voice using the voice recognition engine from the user terminal, the user voice uttering the word group transmitted as a video in the step (a); And

(c) The method may further include providing the user terminal with a score set for the user voice received in step (b).

Preferably, after step (5) or step (6),

The method may further include performing the same process as that of the steps (1) to (5) for the phonemes or words whose scores set in the step (4) or the step (5) are less than the predetermined score, respectively.

According to the method for providing a foreign language phonics learning service through a phoneme feedback using a speech recognition engine proposed by the present invention, a plurality of phonemes that are provided by the service providing server for the target language are first presented and include the corresponding phonemes for each phoneme. By providing a phonics learning service for words, a configuration that transmits the shape of the mouth that pronounces the words in a video, and a configuration that provides detailed phonemic feedback, the foreign language pronunciation of each phoneme can be corrected precisely. As you become familiar with the sounds of foreign languages and the oral structure of pronunciation, you can improve the sensitivity of foreign language sounds that are hard to hear due to the effects of native language sounds, and clearly recognize the differences of each phoneme in foreign languages that are ambiguous. Can inspire the user's interest and practice the pronunciation To be strengthened.

In addition, according to the present invention, the service providing server stores the score for each phoneme set in each step to provide a cumulative score for each phoneme to the user terminal, according to the information and learning date for the phonemes and vulnerable phonemes excellent user utterance By providing information on cumulative score changes for each phoneme, you can precisely correct pronunciation while practicing vulnerable phonemes more intensively, and intuitively show the effect of pronunciation practice.

In addition, according to the present invention, by further comprising a phonics learning step for the group of words that combine two or more words to generate a sound, it is possible to improve the pronunciation and sound listening ability of the foreign language made by the sound.

1 is a diagram showing the configuration of a system for implementing a method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention.
2 is a diagram illustrating a flow of a method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating a screen of a learning page for transmitting phonemes used in a target language to a user terminal in a method for providing a foreign language phonics learning service through phoneme feedback using a speech recognition engine according to an embodiment of the present invention.
4 illustrates a screen of a learning page to which a plurality of words and a mouth shape of a word are transmitted in a method of providing a foreign language phonics learning service through phoneme feedback using a speech recognition engine according to an embodiment of the present invention. drawing.
FIG. 5 is a diagram illustrating a screen of a learning page for providing a score for a user voice to a user terminal in a method for providing a foreign language phonics learning service through feedback of each phoneme using a speech recognition engine according to an embodiment of the present invention.
6 is a screen of a learning page that provides a score for each user's voice by word or phoneme in a method of providing a foreign language phonics learning service through phoneme feedback using a voice recognition engine according to an embodiment of the present invention. Figure.
FIG. 7 is a diagram illustrating a screen of a learning page for providing a cumulative score for each phoneme to a user terminal in a method for providing a foreign language phonics learning service through feedback by phoneme using a speech recognition engine according to an embodiment of the present invention.
8 illustrates a screen of a learning page that provides information on cumulative score change for each phoneme according to a learning date in a method for providing a foreign language phonics learning service through phoneme feedback using a voice recognition engine according to an embodiment of the present invention. drawing.
9 shows the results of experiments with learning effects on the diversity of feedback.
10 is a flowchart illustrating a method of providing a foreign language phonics learning service through feedback of each phoneme using a speech recognition engine according to an embodiment of the present invention.
FIG. 11 is a diagram illustrating a screen of a learning page providing a phonics learning service for a group of words causing a phonics in a method of providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention. .

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. In the following detailed description of the preferred embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The same or similar reference numerals are used throughout the drawings for portions having similar functions and functions.

In addition, in the entire specification, when a part is referred to as being 'connected' to another part, it may be referred to as 'indirectly connected' not only with 'directly connected' . Also, to "include" an element means that it may include other elements, rather than excluding other elements, unless specifically stated otherwise.

1 is a diagram illustrating a configuration of a system for implementing a method for providing a foreign language phonics learning service through feedback of phonemes using a speech recognition engine according to an embodiment of the present invention. As shown in FIG. 1, a system for implementing a method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention includes a service providing server 100 and a user terminal 200. It may be configured to include).

The service providing server 100 may store or generate the learning content of the foreign language phonics learning service provided according to the present invention, and use the phoneme video to pronounce phonemes, words, and words used in the target language. The foreign language phonics learning service through the phoneme feedback using the speech recognition engine provided in accordance with the present invention, such as transmitted to the terminal 200, receiving the user's voice, and scoring the score for the user terminal 200 to provide to the user terminal 200; A series of procedures can be performed. In the present invention, the learning content may include phonemes used in the target language, words including the phonemes, and a mouth-shaped video to pronounce the words. The learning target language may be English, but it is not limited to this, and may be a variety of foreign languages such as Japanese and Chinese. Hereinafter, a case in which the learning target language is English will be described as an embodiment.

The user terminal 200 is a terminal of a user who wants to learn a foreign language using a foreign language phonics learning service through feedback by phonemes using a speech recognition engine provided by the service providing server 100. After the user downloads and installs a program provided by the service providing server 100 in the user terminal 200, the user records and transmits a user voice through the user terminal 200, and learns content from the service providing server 100. Alternatively, the foreign language phonics learning service to be provided by the present invention may be provided through a process of receiving a score or the like. The service providing server 100 and the user terminal 200 can transmit and receive information through a network including the Internet, an intranet, a wired / wireless communication network, and a mobile communication network. In the present invention, the user terminal 200 may be a personal computer (PC), but it can be used regardless of the form of a specific terminal if it is an electronic device capable of networking with the service providing server 100 and capable of recording and image execution . However, since the speech recognition test engine must be used for the speech test, a microphone and a speaker (including a headphone) must be provided like the headset shown in FIG.

2 is a diagram illustrating a flow of a method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention. As shown in FIG. 2, in the method for providing a foreign language phonics learning service through phoneme-specific feedback using a speech recognition engine according to an embodiment of the present invention, the service providing server 100 providing a foreign language phonics learning service is learned. Transmitting the phonemes used in the target language to the user terminal 200, and receiving a selection of a phoneme from the user terminal 200 (S100), a plurality of words including the phoneme selected in step S100 Transmitting to the terminal 200, the shape of the mouth pronounced one word among a plurality of words to the user terminal 200 as a video (S200), the word transmitted as a video from the user terminal 200 in step S200 Receiving the user's voice is recorded and transmitted using a voice recognition engine (S300), the score by the phonemes for the user voice received in step S300 Providing the total scores calculated and added to the user terminal 200 (S400), among the phonemes of step S100 and the words of step S200, other steps of phonemes and words that are not performed in steps S100 to S400 are performed. Implementing the same process as the step S400 (S500), and accumulating the scores for each phoneme set in the step S400 and step S500 on the user terminal 200, and providing to the user terminal 200 (S600) Can be. In the present invention, by learning the words that are stored or generated by dividing each phoneme in this way, it is possible to clearly recognize the difference between each phoneme of the foreign language ambiguous division.

In operation S100, the service providing server 100 may transmit phonemes used in the target language to the user terminal 200, and receive a selection of one phoneme from the user terminal 200. FIG. 3 is a diagram illustrating a screen of a learning page for transmitting phonemes used in a target language to a user terminal in a method for providing a foreign language phonics learning service through phoneme feedback using a speech recognition engine according to an embodiment of the present invention. . As shown in FIG. 3, the phonemes (eg, A, B, C, ai, ou, etc.) used in the target language (eg, English) are provided as texts through the learning page, and the user provides a mouse or the like. The phoneme to be learned can be selected and inputted.

In step S200, the service providing server 100 transmits a plurality of words including the phonemes selected and selected in step S100 to the user terminal 200, and pronounces a word shape of a word among the plurality of words. The video may be transmitted to the 200. 4 illustrates a screen of a learning page to which a plurality of words and a mouth shape of a word are transmitted in a method of providing a foreign language phonics learning service through phoneme feedback using a speech recognition engine according to an embodiment of the present invention. Drawing. As shown in FIG. 4, when the phoneme selected and input in step S100 is “F”, the words “Fan, Father, Favorite”, etc. including “F” may be transmitted to the user terminal 200 in text. have. At this time, the phonetic symbols and the native meanings of each word may be transmitted together. A mouth shape for pronouncing one word (eg, a fan) to perform phonics learning among the plurality of words may be transmitted to the user terminal 200 as a video. In other words, by providing a close-up video of the mouth where the native speaker pronounces the words to be learned, the user can go beyond simply learning the pronunciation through hearing and follow the correct mouth shape and oral structure during pronunciation through the eyes. Make sure

Meanwhile, according to the exemplary embodiment, after the plurality of words including the phonemes selected and selected in step S100 are transmitted to the user terminal 200, one word among the plurality of words is selectively received from the user terminal 200. In addition, it may be implemented to transmit the shape of the mouth to pronounce the selected input word as a video (S200 '). In detail, each of the plurality of words is transmitted with a video and a user's voice is transmitted correspondingly. In this case, the order of performing each word may be based on a predetermined word order and may be stored according to the stored user learning progress. Therefore, it may be automatically assigned but may also be selected by a user. The user may repeatedly select and receive the mouth-shaped video several times until the same word is satisfied.

In step S300, the service providing server 100 can be recorded and transmitted to the user voice from the user terminal 200 by using the voice recognition engine, the user's voice uttered the words transmitted in the video in step S200, in step S400, By providing a total score summed up by phonemes for each user's voice received by the phone, the user terminal 200 may provide precise feedback. 5 is a diagram illustrating a screen of a learning page for providing a score for a user's voice to a user terminal in a method for providing a foreign language phonics learning service through feedback of phonemes using a speech recognition engine according to an embodiment of the present invention. As shown in FIG. 5, according to an embodiment, steps S300 and S400 may be provided in one learning page. In step S200, the user's voice that utters a word (eg, Father) transmitted as a video is recorded and transmitted using a voice recognition engine, and the total scores are determined by adding the scores to phonemes (f / aa / dh / er). For example, A may be provided to the user terminal 200, and a score or a sound wave for each phone may be transmitted along with the overall score, thereby providing more precise feedback for each phone.

6 is a screen of a learning page that provides a score for each user's voice by word or phoneme in a method of providing a foreign language phonics learning service through phoneme feedback using a voice recognition engine according to an embodiment of the present invention. Figure is a diagram. As shown in FIG. 6, the score may be set for each word or phoneme for the performed item (word or word group) and displayed as an alphabet (eg, B +) and a graph. That is, the total score (sum total score) for the performance item and the score set for each word or phoneme constituting the corresponding item may be displayed in alphabets and graphs. In addition, it can be applied as a number, or as a graph according to various systems.

On the other hand, recording and transmission of the user's voice is performed through a voice recognition engine, it may be implemented to start automatically at a predetermined time, as shown in Figure 5, from the user terminal 200, the start button (for example, "START Button), the voice recognition engine can be started to record and transmit the user's voice.

In step S500, the service providing server 100 may perform the same process as that of the steps S100 to S400 for the other phonemes and words that have not performed the steps S100 to S400 among the phonemes of the step S100 and the words of the step S200. have. Steps S100 to S400 described above illustrate a process of selecting one phoneme and performing phonics learning on one word including the phoneme. When the learning for one word is completed, the learning may be performed in the same way with respect to other words. When the learning for one phoneme is completed, the learning may be performed in the same way with the other phonemes. This can be done in this step S500. Preferably, since learning of one phoneme is completed after learning about one phoneme is effective, when one phoneme is selected, a mouth shape that pronounces the word sequentially with respect to words including the phoneme To the user terminal 200, and after receiving the user's voice that has been spoken and setting and transmitting the score (corresponding to steps S200 to S400), the next learning phoneme is selected (corresponding to step S100), Steps S200 to S400 may be performed again.

According to an embodiment, only if the score set in S400 is greater than or equal to a predetermined score by performing S100 to S400 on one word, steps S100 to S400 are performed on the next word, and if the score is less than a predetermined score, the sentence For S100 to S400 may be implemented again. That is, by adopting a configuration that allows the step for the next word to proceed only if the score set for a single word performed is a certain score or more, the user can feel the tension by allowing the user to proceed to the next process only after passing through an immediate test. It can raise the efficiency of learning by invoking to keep the concentration immersed in the immersion state, and to repeatedly learn about the lacking part of the user. In addition, it does not set the number of iterations unilaterally, but it induces an appropriate amount of the iterative learning according to the difference of the learner's ability and concentration, and provides multi-level feedback of discriminative ability to the learner's voice, It can be done without the tedious process of progressing.

In step S600, the cumulative score for each phoneme is provided to the user terminal 200 while the service providing server 100 performs steps S100 to S500, thereby providing cumulative feedback. The cumulative score for each phoneme refers to a score obtained by classifying the scores of each phoneme (eg, A, B, C, etc.) among the scores set for the plurality of words. Cumulative feedback will be described in detail with reference to FIGS. 7 and 8.

FIG. 7 is a diagram illustrating a screen of a learning page for providing a cumulative score for each phoneme to a user terminal in a method of providing a foreign language phonics learning service through phoneme feedback using a voice recognition engine according to an embodiment of the present invention. As illustrated in FIG. 7, scores of phonemes that are determined while providing a learning service for a plurality of phonemes and words may be accumulated and summed for each phoneme and displayed as a score graph for each phoneme. Such comparison graphs can identify information on phonemes with excellent user voice and vulnerable phonemes. According to an embodiment, the phoneme may classify information about phonemes having excellent phonation and information about vulnerable phonemes through cumulative scores for each phoneme, and provide the information to be separately identified by the user.

8 illustrates a screen of a learning page that provides information on cumulative score change for each phoneme according to a learning date in a method for providing a foreign language phonics learning service through phoneme feedback using a voice recognition engine according to an embodiment of the present invention. Drawing. As illustrated in FIG. 8, information about cumulative score change for each phoneme according to a learning date may be provided for each phoneme (eg, F), and according to an embodiment, the phoneme may be displayed as a line graph. By adopting such a configuration, the service providing server 100 can intuitively show the effect of pronunciation practice to the user through the phoneme improvement degree graph.

9 is a diagram showing the results of experiments on the learning effect on the diversity of feedback. As shown in FIG. 9, the present inventors can confirm that the spontaneous execution time is significantly increased when there are seven types of feedback, compared to the case where there is no feedback or only two types of feedback such as success / failure. there was. Therefore, the present invention provides a variety of precise expressions such as step-by-step feedback (scoring and transmitting scores), the accuracy of pronunciation and expression for each word or phoneme, comparison of cumulative scores for each phoneme, changes in cumulative scores for each phoneme, etc. The feedback is sequentially provided to increase the learning effect.

In the foreign language phonics learning service providing method through phoneme feedback using a voice recognition engine according to an embodiment of the present invention, a plurality of words are combined to transmit a group of words causing a soft sound to the user terminal 200 and the word groups. Transmitting the shape of the mouth to pronounce one word group among the video (step (a)), the user's voice from the user terminal 200, the user's voice uttered the word group transmitted to the video in step (a) to the voice recognition engine It further comprises the step of recording and transmitting using (step (b)), and providing the user terminal 200 with the score set for the user voice received in step (b) (step (c)) Can be. When two or more words are combined, a symptom of a change in pronunciation may occur. Therefore, learning about the law of consonants is also required for fluent foreign language pronunciation. The consonant law can be learned using a word group that combines a plurality of words to generate a consonant.

10 is a flowchart illustrating a method for providing a foreign language phonics learning service through feedback of phonemes using a speech recognition engine according to an embodiment of the present invention. As shown in FIG. 10, according to the method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention, after the above-described steps S100 to S600 are performed, a plurality of words are provided. Is combined to transmit the word group causing the noise to the user terminal 200, and receives a selection of one word group from the word group from the user terminal 200 (S700), the user terminal 200 in step S700 Step of transmitting the shape of the mouth to pronounce the group of selected input words as a video (S800), recording and transmitting the user voice from the user terminal 200 using the voice recognition engine to utter the selected word in step S800 (S900) and providing the user terminal 200 with the total scores that are determined by phonemes for the user voices received in step S900 and added together. For (S1000) it may be further included.

FIG. 11 is a diagram illustrating a screen of a learning page providing a phonics learning service for a group of words causing a phonics in a method of providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine according to an embodiment of the present invention. to be. As illustrated in FIG. 11, phonics learning may be performed on a group of words (eg, I'v got a, Put it on, must have been) that combine a plurality of words to cause a consonant. Each step is similar to steps S100 to S400 except that the word is changed to a word group where a plurality of words combine to cause a noise, and thus other detailed descriptions will be omitted.

In addition, according to the embodiment, after step S500 or S600, further comprising the step of performing the same process as in steps S100 to S500 for the phonemes or words whose scores set in step S400 or S500 are less than a predetermined score, respectively. You may. By adopting such a configuration, it is possible to re-execute only the deficient portion, except for the portion that has already been learned, thereby improving the learning efficiency and reducing the boredom due to repetition.

Meanwhile, by further including a step of receiving member information from the user before the step S100 and receiving membership, the user can perform learning by level, and progress management, score management, and the like can be facilitated.

The present invention may be embodied in many other specific forms without departing from the spirit or essential characteristics of the invention.

100: service providing server 200: user terminal
S100: transmitting phonemes used in the learning target language to the user terminal and receiving a selection input of one phoneme from the user terminal
S200: transmitting a plurality of words including the phonemes selected and selected in step S100 to the user terminal, and transmitting a mouth shape to pronounce one word among the plurality of words as a video.
S200 ': After transmitting a plurality of words including phonemes selected and selected in step S100 to the user terminal, one word among the plurality of words is selected and input from the user terminal, and the selected input word is received. Steps to send a pronounced mouth shape as a video
S300: recording and transmitting a user's voice uttering a word transmitted from the user terminal as a video in step S200 using a voice recognition engine
S400: providing the user terminal with the total scores that are calculated by adding scores by phonemes to the user voices received in step S300.
S500: performing the same process as that of the steps S100 to S400 among the phonemes of the step S100 and the words of the step S200 that do not perform the steps S100 to S400
S600: accumulating scores for each phoneme set in steps S400 and S500 on the user terminal and providing them to the user terminal
S700: a step of transmitting a word group generating a noise by combining a plurality of words to the user terminal, and receiving one word group selected from the word groups from the user terminal;
S800: step of transmitting, as a video, a shape of a mouth to pronounce a word group selected and input in step S700 to the user terminal;
S900: recording and transmitting a user's voice uttering the word selected and input in step S800 by using the voice recognition engine from the user terminal
S1000: providing the user terminal with a total score obtained by summing scores by phonemes for the user voices received in step S900;

Claims (7)

A service providing server that provides foreign language phonics learning services,
(1) transmitting phonemes used in the target language to a user terminal and receiving a selection of one phoneme from the user terminal;
(2) transmitting a plurality of words including the phonemes selected and selected in step (1) to the user terminal, and transmitting a mouth shape for pronouncing one word among the plurality of words as a video to the user terminal; ;
(3) recording and transmitting a user's voice uttering a word transmitted from the user terminal as a video in step (2) using a voice recognition engine;
(4) providing the user terminal with a total score obtained by summing scores by phonemes for the user voices received in step (3);
(5) Steps (1) to (4) of the phonemes of step (1) and other phonemes or words that have not been performed in steps (1) to (4) among the phonemes of step (1) and words of step (2). Performing the same process as; And
(6) providing the user terminal with a cumulative score for each phoneme accumulated in the phoneme scores set in the steps (4) and (5) to the user terminal. How to provide foreign language phonics learning service through feedback by phoneme.
2. The method of claim 1, wherein step (2)
After transmitting the plurality of words including the phonemes selected and selected in step (1) to the user terminal, one word among the plurality of words is selected and input from the user terminal, and the selected input word is pronounced. Method for providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine, characterized in that the step of transmitting the shape of the mouth to a video.
The method of claim 1, wherein in step (4) or step (5),
The phoneme by using the speech recognition engine, characterized in that to display the total score and the detailed scores set by the phone to any one or more selected from the group comprising a number, alphabet, and graph, to the user terminal How to Provide Foreign Language Phonics Learning Services through Feedback.
The method of claim 1, wherein in step (6),
Method for providing a foreign language phonics learning service through the phoneme feedback using a speech recognition engine, characterized in that for providing information about the phoneme excellent and vulnerable phoneme of the user through the cumulative score for each phoneme.
The method of claim 1, wherein in step (6),
Method for providing a foreign language phonics learning service through the phoneme feedback using a speech recognition engine, characterized in that for each phoneme providing information on the cumulative score change for each phoneme according to the learning date.
The method of claim 1, wherein after step (5) or step (6),
(a) transmitting a group of words that combine a plurality of words to cause a noise, to the user terminal, and transmitting a shape of a mouth that pronounces one word group among the word groups as a moving picture;
(b) receiving and recording a user voice using the voice recognition engine from the user terminal, the user voice uttering the word group transmitted as a video in the step (a); And
(c) providing a foreign language phonics learning service through feedback by phonemes using a speech recognition engine, further comprising providing the user terminal with a score set for the user voice received in step (b). Way.
The method of claim 1, wherein after step (5) or step (6),
And re-performing the same process as that of the steps (1) to (5) for the phonemes or words whose scores set in the step (4) or step (5) are less than the predetermined score, respectively. , Foreign language phonics learning service through phoneme feedback using speech recognition engine.
KR1020120072544A 2012-07-03 2012-07-03 Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine KR20140004541A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020120072544A KR20140004541A (en) 2012-07-03 2012-07-03 Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020120072544A KR20140004541A (en) 2012-07-03 2012-07-03 Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine

Publications (1)

Publication Number Publication Date
KR20140004541A true KR20140004541A (en) 2014-01-13

Family

ID=50140514

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020120072544A KR20140004541A (en) 2012-07-03 2012-07-03 Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine

Country Status (1)

Country Link
KR (1) KR20140004541A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537591A (en) * 2014-12-31 2015-04-22 上海理工大学 Family education management system
US9697201B2 (en) 2014-11-24 2017-07-04 Microsoft Technology Licensing, Llc Adapting machine translation data using damaging channel model
KR20180095314A (en) * 2017-02-17 2018-08-27 국민대학교산학협력단 Education system for reading korean based on phoneme image and phoneme analysis algorithm
WO2019139248A1 (en) * 2018-01-15 2019-07-18 김민철 Method for managing language speaking lesson on network and management server used therefor
CN110264790A (en) * 2019-05-05 2019-09-20 昫爸教育科技(北京)有限公司 It is a kind of by decoding phoneme to decoding word English Teaching Method and system

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9697201B2 (en) 2014-11-24 2017-07-04 Microsoft Technology Licensing, Llc Adapting machine translation data using damaging channel model
CN104537591A (en) * 2014-12-31 2015-04-22 上海理工大学 Family education management system
KR20180095314A (en) * 2017-02-17 2018-08-27 국민대학교산학협력단 Education system for reading korean based on phoneme image and phoneme analysis algorithm
WO2019139248A1 (en) * 2018-01-15 2019-07-18 김민철 Method for managing language speaking lesson on network and management server used therefor
GB2585520A (en) * 2018-01-15 2021-01-13 Chul Kim Min Method for managing language speaking lesson on network and management server used therefor
US11322046B2 (en) 2018-01-15 2022-05-03 Min Chul Kim Method for managing language speaking lesson on network and management server used therefor
CN110264790A (en) * 2019-05-05 2019-09-20 昫爸教育科技(北京)有限公司 It is a kind of by decoding phoneme to decoding word English Teaching Method and system

Similar Documents

Publication Publication Date Title
Rogerson-Revell Computer-assisted pronunciation training (CAPT): Current issues and future directions
US20190385480A1 (en) System to evaluate dimensions of pronunciation quality
Pennington et al. Using technology for pronunciation teaching, learning, and assessment
US11145222B2 (en) Language learning system, language learning support server, and computer program product
US20080027731A1 (en) Comprehensive Spoken Language Learning System
US20200320898A1 (en) Systems and Methods for Providing Reading Assistance Using Speech Recognition and Error Tracking Mechanisms
KR101438087B1 (en) Method for providing language training service based on consecutive and simultaneous interpretation test using speech recognition engine
KR20140004541A (en) Method for providing foreign language phonics training service based on feedback for each phoneme using speech recognition engine
Ai Automatic pronunciation error detection and feedback generation for call applications
JP7376071B2 (en) Computer program, pronunciation learning support method, and pronunciation learning support device
JP6656529B2 (en) Foreign language conversation training system
Mutqiyyah et al. Developing mobile app of english pronunciation test using android studio
JP2018097250A (en) Language learning device
KR20140087956A (en) Apparatus and method for learning phonics by using native speaker's pronunciation data and word and sentence and image data
Meisarah Mobile-assisted pronunciation training: the *** play pronunciation and phonetics application
KR101854379B1 (en) English learning method for enhancing memory of unconscious process
KR101681673B1 (en) English trainning method and system based on sound classification in internet
Jo et al. Effective computer‐assisted pronunciation training based on phone‐sensitive word recommendation
Ross et al. Speaking with your computer: A new way to practice and analyze conversation
Shukla Development of a Human-AI Teaming Based Mobile Language Learning Solution for Dual Language Learners in Early and Special Educations
Filighera et al. Towards A Vocalization Feedback Pipeline for Language Learners
Shukla et al. iLeap: A Human-Ai Teaming Based Mobile Language Learning Solution for Dual Language Learners in Early and Special Educations.
US20080145824A1 (en) Computerized speech and communication training
KR20140004540A (en) Method for providing foreign language listening training service based on listening and speaking using speech recognition engine
KR20140004539A (en) Method for providing learning language service based on interactive dialogue using speech recognition engine

Legal Events

Date Code Title Description
A201 Request for examination
A302 Request for accelerated examination
E902 Notification of reason for refusal
E601 Decision to refuse application