KR20160115041A - Apparatus and method for pronunciation - Google Patents

Apparatus and method for pronunciation Download PDF

Info

Publication number
KR20160115041A
KR20160115041A KR1020150041698A KR20150041698A KR20160115041A KR 20160115041 A KR20160115041 A KR 20160115041A KR 1020150041698 A KR1020150041698 A KR 1020150041698A KR 20150041698 A KR20150041698 A KR 20150041698A KR 20160115041 A KR20160115041 A KR 20160115041A
Authority
KR
South Korea
Prior art keywords
pronunciation
learner
native
speech
learning
Prior art date
Application number
KR1020150041698A
Other languages
Korean (ko)
Inventor
오유리
정의석
전형배
박전규
이윤근
이윤경
강점자
정호영
이성주
최우용
강병옥
김현우
훈 정
송화전
Original Assignee
한국전자통신연구원
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 한국전자통신연구원 filed Critical 한국전자통신연구원
Priority to KR1020150041698A priority Critical patent/KR20160115041A/en
Publication of KR20160115041A publication Critical patent/KR20160115041A/en

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B19/00—Teaching not covered by other main groups of this subclass
    • G09B19/06—Foreign languages
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00—Electrically-operated educational appliances
    • G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied

Abstract

According to the present invention, a learning apparatus for pronunciation based on voice recognition comprises: a lecture content providing unit providing multimedia lecture contents to which a pronunciation error of a non-native learner is reflected, and providing a vocalization script for speech practice; a voice recognition unit receiving a learner voice signal of the non-native learner provided with the vocalization script, and generating voice information recognized through the received learner voice signal recognition; and a pronunciation evaluation unit generating pronunciation evaluation feedback information based on the vocalization script and the recognized voice information.

Description

[0001] APPARATUS AND METHOD FOR PRONUNCIATION [0002]

TECHNICAL FIELD The present invention relates to language learning, and more particularly, to pronunciation learning using speech recognition technology.

Due to the trend of internationalization of modern society, interest in foreign languages is getting bigger than in the past. In response to this trend, various language applications related to foreign language learning are being developed. Recently, as speech recognition technology has been developed, application programs for self-learning using speech recognition technology are being developed. As such, the language learning programs using the speech recognition technology recognize the user's speech input, compare the speech with the set speech, and provide a result, thereby providing a higher learning effect to the user. However, the learning technique using conventional speech recognition merely recognizes and compares the user's voice through speech recognition, but does not provide a learning method of correcting the pronunciation of the learner.

Korean Patent No. 10-0997255

A problem to be solved by the present invention is to provide a speech learning-based training service for pronunciation learning of a non-native speaker and a speech recognition based speech recognition device capable of self-correcting a pronunciation of a learner through speech recognition-based speaking practice .

The speech recognition-based pronunciation learning apparatus according to the present invention provides multimedia lecture contents reflecting a pronunciation error of a non-native learner and provides lecture contents providing utterance script for speech exercises and non-native learner A speech recognition unit for receiving the learner speech signal, generating the recognized speech information through recognition of the received learner speech signal, and a pronunciation evaluation unit for generating pronunciation evaluation feedback information based on the speech information and the recognized speech information.

The lecture contents providing department provides the non-native learner with a multimedia lecture including the learning contents for the pronunciation of the articulatory phenomenon which is non-native speaker's error. Then, the lecture contents providing section provides the non-native learner with a multimedia lecture including a description of the characteristics of the pronunciation error that the non-native learner learns due to the influence of the mother language, and a description of a method for pronunciation as the native speaker.

The pronunciation evaluation unit compares the utterance script with the recognized voice information using the non-native speaker utterance characteristic information, and can determine whether the learner's voice of the non-native learner is normal utterance based on the comparison result. The lecture contents providing section provides the pronunciation evaluation and the result to the non-native learner based on the feedback information of the pronunciation evaluation section. In this process, if the lecture content providing unit determines that the pronunciation is normal according to the feedback information, it can inform the non-native learner of the success of utterance and induce another word or sentence learning of the content. On the other hand, if it is determined that the lecture contents providing unit is not normal pronunciation in accordance with the feedback information, the lecture contents providing unit may present a method that can be improved based on the feedback information to the non-native learner, and induce the same word or sentence to be practiced again.

The speech recognition based pronunciation learning method according to the present invention first provides a multimedia lecture content in which a pronunciation to be learned from a non-native learner is selected and a pronunciation error of a non-native learner is reflected on the selected pronunciation. After providing the multimedia contents, a non-native learner is provided with a speech script for speech exercises. When the non-native speaker learns and reads the provided speech script, it generates the recognized speech information through recognition of the learner speech signal of the non-native learner, and generates the pronunciation evaluation feedback information based on the speech script and the recognized speech information. And. Provides pronunciation evaluation and results according to feedback information. Here, the step of providing the contents of the multimedia lecture provides a multimedia lecture to the non-native learner including a description of the characteristics of the pronunciation error which is caused by the influence of the native language of the non-native learner, do.

If the pronunciation evaluation and the result providing step are determined to be normal pronunciation according to the feedback information, the non-native speaker can be informed of the success of utterance and can induce learning of another word or sentence of the content. On the other hand, if it is determined that the pronunciation is not the normal pronunciation in accordance with the feedback information, the non-native learner can be suggested to improve the method based on the feedback information and induce the same word or sentence to be practiced again.

The pronunciation learning apparatus and learning method based on the speech recognition based on the present invention recognize the pronunciation errors of the learners by providing lectures and contents specialized for pronunciation characteristics of the non-native learner, self-pronounced by providing repeated speaking exercises and feedback And the like.

FIG. 1 is a configuration diagram showing an embodiment of a pronunciation learning apparatus 100 based on speech recognition according to the present invention.
2 is a flowchart illustrating a pronunciation learning process of the pronunciation learning apparatus 100 according to an embodiment of the present invention.
FIG. 3 is a configuration diagram showing pronunciation learning contents of the speech learning apparatus 100 based on speech recognition according to an embodiment of the present invention.
4 is a diagram illustrating a pronunciation evaluation and a result providing process of the pronunciation learning apparatus 100 based on the speech recognition according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The terms and words used in the present specification are selected in consideration of the functions in the embodiments, and the meaning of the terms may vary depending on the intention or custom of the invention. Therefore, the terms used in the following embodiments are defined according to their definitions when they are specifically defined in this specification, and unless otherwise specified, they should be construed in a sense generally recognized by those skilled in the art.

FIG. 1 is a configuration diagram showing an embodiment of a pronunciation learning apparatus 100 based on speech recognition according to the present invention.

Referring to FIG. 1, a speech recognition-based pronunciation learning apparatus 100 according to the present invention includes a lecture contents providing unit 110, a speech recognizing unit 120, and a pronunciation evaluating unit 130. The pronunciation learning apparatus 100 based on the speech recognition is a pronunciation learning method based on the pronunciation learning contents reflecting the characteristics of the non-native speaker 10.

The lecture content providing unit 110 provides pronunciation learning content capable of grasping the pronunciation error characteristic of the non-native learner 10. The pronunciation error characteristic of the non-native speaker (10) is a characteristic according to the difference between the target language of the learner and the language (native language) of the non-native speaker (10). For example, when a non-native speaker (10), a Korean, learns English (target language), there may be differences in pronunciation characteristics between the two languages. English pronunciation / b / can be wrong pronunciation in Korean / / / pronunciation. Since Korean pronunciation / b / is a voiced sound, Korean pronunciation / b / is unvoiced sound, Korean name 'Busan' may sound similar to 'Fushan' for English native speakers. Therefore, Korean pronouns / b / English native speakers may recognize English as unvoiced pronunciation / p /. The pronunciation error characteristic indicates a characteristic of a pronunciation error caused by such a language difference.

The pronunciation learning contents are composed of learning contents for pronunciation of phonemes constituting the language to be learned and pronunciations of the non-native language learners 10, Multimedia lecture materials including information, words including learning pronunciation, and native speakers voice, interpretation, and pronunciation data for the sentence.

The lecture contents providing unit 110 can provide the learner 10 with a multimedia lecture reflecting pronunciation errors of the non-native learner 10 using pronunciation learning contents. The pronunciation learning contents can provide the learner 10 with a description of the characteristics of the pronunciation error that the non-native learner 10 makes due to the influence of the mother tongue, and an explanation of the method of pronunciation as the native speaker.

Then, the lecture contents providing unit 110 provides the multimedia lecture based on the pronunciation learning contents to the learner 10, and then provides the learner 10 with the learner content through the lecture script for speaking practice. The speaking learning contents sequentially progresses the speaking practice about the learning pronunciation itself, the speaking practice for the word including the learning pronunciation, and the speaking practice for the sentence including the learning pronunciation, so that the learner 10 repeatedly Let practice. The utterance script constituting each sentence or word of the speech learning contents is transmitted to the pronunciation evaluation unit 130. [

The non-native language learners 10 are provided with multimedia lectures based on the pronunciation learning contents by the lecture contents providing unit 110, and explain the characteristics of the pronunciation errors which are caused by the influence of the native language, You can hear the explanation. After receiving the multimedia lectures, the non-native speaker 10 receives the speech learning contents based on the speech script from the lecture contents providing unit 110. The non-native speaker 10 reads the speech script (speech sentence) of the provided speech learning contents and voices the corresponding word. The voice of the learner 10 is recognized through the voice recognition unit 120. [

The speech recognition unit 120 recognizes the learner 10 speech signal input by the learner 10 speech script. The learner 10 reads the learner script in a sentence selected to provide the learner script to the learner 10 through the speech learning content, and pronounces the corresponding word or sentence. The speech recognition unit 120 performs speech recognition specialized for the non-native speech by using the learner 10 speech and utterance script. Speech recognition specialized for a non-native speaker voice represents speech recognition considering the pronunciation error characteristic of the non-native speaker 10 described above. The use of a speech script means that the speech recognition target is limited to sentences and words selected by the learner 10 in the process of performing speech recognition.

The speech recognition unit 120 extracts speech feature information from the learner 10 speech signal. The speech feature extraction can be extracted using various algorithms such as MFCC (Mel Frequency Cepstral Coefficient), LPC (Linear Predictive Coding) and PLP (Perceptual Linear Prediction). The speech recognition unit 120 may remove noise using a sound quality improvement technique, a feature compensation technique, and a model adaptation technique. The voice recognition unit 120 transmits the recognized voice information to the pronunciation evaluation unit 130. [

The pronunciation evaluating unit 130 compares the utterance script received from the lecture contents providing unit 110 and the recognized voice information received from the voice recognizing unit 120 to determine whether the recognized voice information correctly pronounces the utterance script . The non-native learner 10 reads the utterance script and transmits the voice by pronouncing it. The pronunciation evaluation unit 130 can compare the voice information recognized from the learner 10 with the utterance script using the non-native speech utterance characteristic information and confirm whether the word or sentence corresponding to the utterance script is pronounced similar to the actual native speaker . The non-native speaker utterance characteristic information is a utterance characteristic according to the pronunciation error characteristic of the non-native speaker 10, and indicates a characteristic occurring in a difference between the native language of the non-native speaker 10 and the language to be studied. The pronunciation evaluation unit 130 generates feedback information based on the result of comparison between the utterance script and the recognized voice information, and transmits the generated feedback information to the lecture contents providing unit 110.

The lecture content providing unit 110 provides the learner with a pronunciation evaluation and a result based on the feedback information received from the pronunciation evaluation unit 130. [ The lecture contents providing unit 110 may notify the learner 10 of the success of speech when the pronunciation is determined to be uttered according to the result of the comparison based on the feedback information, Learning can be induced. On the other hand, if the lecture contents providing unit 110 determines that the pronunciation is not properly pronounced according to the comparison result, the learner 10 presents the calculated pronunciation information and the possible improvement method to the learner 10, You can provide the content so that you can try out the exercises.

2 is a flowchart illustrating a pronunciation learning process of the pronunciation learning apparatus 100 according to an embodiment of the present invention.

Referring to FIG. 1 and FIG. 2, the pronunciation learning process of the speech recognition-based pronunciation learning apparatus 100 according to an embodiment of the present invention is based on pronunciation learning contents reflecting characteristics of non-native language learners. First, the pronunciation learning apparatus 100 based on the speech recognition selects a pronunciation to be learned from the learner (S201). The pronunciation learning apparatus 100 based on the speech recognition provides a multimedia lecture reflecting the pronunciation errors of the non-native learner based on the pronunciation learning contents according to the learner's choice (S202). The pronunciation learning contents are composed of learning contents about pronunciation of phonemes constituting the language to be learned and pronunciation of articulation phenomenon in which non-native learners are likely to make mistakes, and multimedia lectures including pronunciation error information of non-native learners Words and phrases that include material and learning pronunciation, and native speaker voice, interpretation, and pronunciation data for the sentence. The pronunciation learning apparatus 100 based on the speech recognition can provide the learner with multimedia lectures reflecting the pronunciation errors of the non-native learner using the pronunciation learning contents. The pronunciation learning contents can provide the learner with a description of the characteristics of the pronunciation error that the non-native learner makes due to the influence of the mother tongue, and a description of how to pronounce it like the native speaker.

Next, the pronunciation learning apparatus 100 based on the speech recognition proceeds with a process for speaking practice (pronunciation practice) (S203). The speech learning apparatus 100 based on speech recognition provides multimedia lectures based on pronunciation learning contents to a learner, and then provides speech learning contents to a learner through a speech script for speech exercises. The speech learning contents sequentially progresses the speaking practice about the learning pronunciation itself, the speaking practice for the word including the learning pronunciation, and the speaking practice for the sentence including the learning pronunciation, so that the learner is repeatedly practiced the learning pronunciation .

The speaking exercise process can be performed in the order of pronunciation self speaking practice to be learned (S203-1), word speaking practice including pronunciation to be learned (S203-2), and sentence speaking practice including pronunciation to be learned (S203-3). The speech learning apparatus 100 based on speech recognition provides contents for practicing a specific pronunciation (pronunciation symbol) itself to be learned first. You can then practice the words that contain the specific pronunciation you have practiced, and then practice the sentences that contain the pronunciation you have practiced next. As described above, in the present invention, the exercises can be started by extending from a specific pronunciation to a word and a sentence including the pronunciation. When the learner speaks through the speech exercises, the speech learning apparatus 100 based on the speech recognition receives the learner speech signal.

The speech recognition-based pronunciation learning apparatus 100 recognizes the received learner speech, compares the recognized speech information and the speech script to generate feedback information, and provides a pronunciation evaluation and a result (S204). The speech learning apparatus 100 based on the speech recognition compares the received speech script and the recognized speech information to determine whether the recognized speech information correctly pronounces the speech script. The speech learning apparatus 100 based on the speech recognition can compare the speech information recognized by the learner with the speech script and confirm whether the word or sentence corresponding to the speech script is pronounced like a real native speaker. The speech learning apparatus 100 based on speech recognition generates feedback information on the basis of the result of comparison between the utterance script and the recognized speech information. If the pronunciation learning apparatus 100 based on speech recognition recognizes that the pronunciation is appropriately uttered according to the comparison result, it can notify the learner of the success of utterance, and can induce the learning of another word or sentence of the pronunciation learning contents . On the other hand, if the pronunciation learning apparatus 100 based on speech recognition recognizes that the pronunciation is not properly pronounced according to the comparison result, after the learner is presented with the calculated pronunciation information and a possible improvement method, the learner performs the re- The content can be provided.

The pronunciation evaluation and the result providing step S204 may be performed in such a manner that a determination process is performed after performing the entire speaking process of the speaking exercise step S203. In addition, the pronunciation evaluation and the step of providing the result (S204) may be provided each time the steps (S203-1 to S203-3) of the speaking exercise step (S203) are performed. For example, the learner's voice according to the speech-to-speech speaking practice (S203-1) to be learned can be evaluated and provided only in a case where the learner's voice is judged as a normal pronunciation, so that the next step can be performed.

FIG. 3 is a configuration diagram showing pronunciation learning contents of the speech learning apparatus 100 based on speech recognition according to an embodiment of the present invention.

Referring to FIGS. 1 and 3, in order to improve the pronunciation error of a non-native learner, the pronunciation learning apparatus 100 based on speech recognition first calculates a pronunciation error of a non-native speaker based on the pronunciation learning contents reflecting characteristics of non- To provide multimedia lectures. Different languages have different pronunciation systems. Pronunciation errors of non-native learners represent pronunciation errors that occur due to different pronunciation systems that exist between the language (native language) used by non-native learners and the target language in which pronunciation is desired. Thus, non-native learners may have general pronunciation errors that occur due to differences in pronunciation between the language they are using and the target language in which pronunciation is desired to be corrected.

As described above, the pronunciation learning apparatus 100 based on the speech recognition can be constituted by phonemic pronunciation constituting the language to be learned, pronunciation of the articulation phenomenon in which non-native learners are likely to make errors, and the like. The speech recognition-based pronunciation learning apparatus 100 includes a multimedia lecture material 301 including pronunciation error information of a non-native learner for each pronunciation, a native speaker voice, interpretation, pronunciation data (302). The user can receive a multimedia lecture material 301 including pronunciation error information of a non-native learner through the pronunciation learning apparatus 100 based on the speech recognition, a native speaker voice, interpretation, pronunciation data 302) for each pronunciation.

4 is a diagram illustrating a pronunciation evaluation and a result providing process of the pronunciation learning apparatus 100 based on the speech recognition according to an embodiment of the present invention.

Referring to FIG. 4, the pronunciation learning apparatus 100 based on the speech recognition recognizes a model in which non-native speech characteristics are reflected on the basis of the speech script 41 provided on the basis of the pronunciation learning contents and the learner speech 20 received from the learner (S401). The learner makes a predetermined utterance in accordance with the utterance script 41 and delivers the learner's voice 42 to the utterance-learning-based pronunciation learning apparatus 100. The speech recognition-based pronunciation learning apparatus 100 performs speech recognition specialized for non-native speech using the speech script 41 and the learner's voice 42. [ The models used for speech recognition include acoustic models, language models, and pronunciation models. Non-native speech models can be generated by using rules such as phonetics and then reflected in each model, It can be generated automatically. Speech recognition using a model that reflects non-native speaker speech characteristics means performing speech recognition using the learned model as described above.

Next, the pronunciation learning apparatus 100 based on speech recognition compares the learner's voice 42 recognized based on the non-native-speaker utterance characteristic information 43 with the utterance script 41 to derive pronunciation evaluation feedback for the learner's voice (S402). The non-native speaker utterance characteristic information indicates characteristics arising from a linguistic difference between a language of a non-native speaker (learner) and a learning target language, as described in Fig. 1. Speech recognition-based pronunciation learning apparatus 100 recognizes It is possible to check whether the word or sentence corresponding to the utterance script is pronounced like a real native speaker by comparing the voice information with the utterance script. The speech recognition-based pronunciation learning apparatus 100 determines whether the learner's utterance is normal utterance based on the result of feedback derivation (S403).

If it is determined that the pronunciation has been properly uttered according to the comparison result, the speech recognition-based pronunciation learning apparatus 100 notifies the learner of the success of utterance (S404), and induces learning of another word or sentence of the pronunciation learning contents S405). On the other hand, if it is determined that the pronunciation is not properly pronounced according to the comparison result, the pronunciation learning apparatus 100 based on the speech recognition provides the learner with the pronunciation information and the improvement method (S406, S407) The contents are provided so as to try again speaking practice (S408).

The present invention including the above-described contents can be written in a computer program. And the code and code segment constituting the program can be easily deduced by a computer programmer of the field. In addition, the created program can be stored in a computer-readable recording medium or an information storage medium, and can be read and executed by a computer to implement the method of the present invention. And the recording medium includes all types of recording media readable by a computer.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It is possible.

100: Speech recognition based pronunciation learning device
110: Lecture contents offerer
120:
130:

Claims (11)

Providing multimedia lecture contents reflecting pronunciation errors of non - native learners and providing lecture contents script for speaking practice;
A voice recognition unit for recognizing a voice of a non-native learner provided with the voice generation script and generating recognized voice information; And
A pronunciation evaluation unit for generating pronunciation evaluation feedback information based on the speech script and the recognized speech information;
And a speech recognition unit for recognizing the pronunciation of the speech. The method according to claim 1,
Wherein the lecture contents providing unit provides the non-native learner with a multimedia lecture including learning contents for pronouncing articulation phenomenon in which the non-native learner is likely to make a mistake. The method according to claim 1,
The lecture contents providing unit provides the non-native learner with a multimedia lecture including a description of the characteristics of pronunciation errors that the non-native learner learns due to the influence of the mother tongue, and a description of a method for pronunciation as the native speaker Wherein the speech recognition device is a speech recognition device. The method according to claim 1,
Wherein the pronunciation evaluating unit compares the utterance script with the recognized voice information using non-native speech utterance characteristic information, and determines whether the learner's voice of the non-native learner is normal utterance according to a result of the comparison. Based pronunciation learning device. The method according to claim 1,
Wherein the lecture contents providing unit provides the pronunciation evaluation and the result to the non-native learner based on the feedback information of the pronunciation evaluation unit. 6. The method of claim 5,
Wherein the lecture contents providing unit notifies the non-native learner of the success of utterance and induces another word or sentence learning of the content if it is determined that the utterance is normal pronunciation according to the feedback information. 6. The method of claim 5,
Wherein the lecture contents providing unit instructs the non-native learner to present an improvement method based on the feedback information, and instructs the non-native learner to practice the same word or sentence again if it is determined that the pronunciation is not normal pronunciation in accordance with the feedback information A recognition - based pronunciation learning device. Providing a multimedia lecture content reflecting a pronunciation error of a non-native learner with respect to a pronunciation selected by a non-native learner;
Providing a speech script for speaking practice;
Generating recognized speech information through recognition of a learner speech signal of a non-native learner provided with the speech script;
Generating pronunciation evaluation feedback information based on the speech script and the recognized speech information; And
Providing a pronunciation evaluation and a result according to the feedback information;
Wherein the speech recognition method comprises: 9. The method of claim 8,
The step of providing the multimedia lecture contents may include providing a multimedia lecture to the non-native learner, the multimedia lecture including a description of a characteristic of a pronunciation error that the non-native learner is influenced by the native language, Wherein the speech recognition method comprises the steps of: 9. The method of claim 8,
Wherein the step of providing the pronunciation evaluation and the result includes notifying the non-native speaker of the success of the speech and inducing another word or sentence learning of the content if it is determined that the pronunciation is normal according to the feedback information. Learning method. 9. The method of claim 8,
Wherein the step of providing the pronunciation evaluation and the result provides an improvement method based on the feedback information to the non-native learner when it is determined that the pronunciation is not normal pronunciation in accordance with the feedback information, Wherein the speech recognition method comprises the steps of:
KR1020150041698A 2015-03-25 2015-03-25 Apparatus and method for pronunciation KR20160115041A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150041698A KR20160115041A (en) 2015-03-25 2015-03-25 Apparatus and method for pronunciation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150041698A KR20160115041A (en) 2015-03-25 2015-03-25 Apparatus and method for pronunciation

Publications (1)

Publication Number Publication Date
KR20160115041A true KR20160115041A (en) 2016-10-06

Family

ID=57165104

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150041698A KR20160115041A (en) 2015-03-25 2015-03-25 Apparatus and method for pronunciation

Country Status (1)

Country Link
KR (1) KR20160115041A (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101955818B1 (en) 2017-09-29 2019-03-08 숭실대학교산학협력단 Method for providing hologram-control training service and computer readable medium for performing the method
KR20210079512A (en) * 2019-12-20 2021-06-30 주식회사 에듀템 Foreign language learning evaluation device
WO2022035125A1 (en) * 2020-08-13 2022-02-17 (주)인포마크 Foreign language learning system and method using ai speech recognition learning device
KR20220036717A (en) * 2020-09-16 2022-03-23 한양대학교 산학협력단 Method for providing vocal learning information, server and program using the same
KR20220038852A (en) 2020-09-21 2022-03-29 주식회사 케이엠에듀 English teaching method and apparatus using teaching media
KR20220078862A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Medium of record that records English education program
KR20220078876A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching program to improve the hearing ability of English sentences
KR20220078867A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Medium of record that records English education programs
KR20220078873A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for providing english teaching using teaching media
KR20220078872A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching apparatus using teaching media
KR20220078861A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Recording Medium
KR20220078868A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching method using teaching media
KR20220078870A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching method to improve the hearing ability of English sentences based on phonetic phenomena
KR20220078865A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Record medium recording an English education program that improves the hearing ability of English sentences based on pronunciation
KR20220078874A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for providing english education
KR20220078875A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for english teaching

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100997255B1 (en) 2010-03-11 2010-11-29 (주)말문이터지는영어 Language learning system of simultaneous interpretation type using voice recognition

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100997255B1 (en) 2010-03-11 2010-11-29 (주)말문이터지는영어 Language learning system of simultaneous interpretation type using voice recognition

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101955818B1 (en) 2017-09-29 2019-03-08 숭실대학교산학협력단 Method for providing hologram-control training service and computer readable medium for performing the method
KR20210079512A (en) * 2019-12-20 2021-06-30 주식회사 에듀템 Foreign language learning evaluation device
WO2022035125A1 (en) * 2020-08-13 2022-02-17 (주)인포마크 Foreign language learning system and method using ai speech recognition learning device
KR20220036717A (en) * 2020-09-16 2022-03-23 한양대학교 산학협력단 Method for providing vocal learning information, server and program using the same
KR20220038852A (en) 2020-09-21 2022-03-29 주식회사 케이엠에듀 English teaching method and apparatus using teaching media
KR20220078862A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Medium of record that records English education program
KR20220078876A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching program to improve the hearing ability of English sentences
KR20220078867A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Medium of record that records English education programs
KR20220078873A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for providing english teaching using teaching media
KR20220078872A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching apparatus using teaching media
KR20220078861A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Recording Medium
KR20220078868A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching method using teaching media
KR20220078870A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 English teaching method to improve the hearing ability of English sentences based on phonetic phenomena
KR20220078865A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Record medium recording an English education program that improves the hearing ability of English sentences based on pronunciation
KR20220078874A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for providing english education
KR20220078875A (en) 2020-12-04 2022-06-13 주식회사 케이엠에듀 Program for english teaching

Similar Documents

Publication Publication Date Title
KR20160115041A (en) Apparatus and method for pronunciation
KR102246943B1 (en) Method of multilingual text-to-speech synthesis
US8175882B2 (en) Method and system for accent correction
US7529678B2 (en) Using a spoken utterance for disambiguation of spelling inputs into a speech recognition system
US8024179B2 (en) System and method for improving interaction with a user through a dynamically alterable spoken dialog system
US11043213B2 (en) System and method for detection and correction of incorrectly pronounced words
US7624013B2 (en) Word competition models in voice recognition
DE69425564D1 (en) METHOD AND DEVICE FOR VOICE TEACHING BY MEANS OF INTERACTIVE VOICE CONTROL
Van Doremalen et al. Optimizing automatic speech recognition for low-proficient non-native speakers
KR101037247B1 (en) Foreign language conversation training method and apparatus and trainee simulation method and apparatus for qucikly developing and verifying the same
WO2021074721A2 (en) System for automatic assessment of fluency in spoken language and a method thereof
KR102062524B1 (en) Voice recognition and translation method and, apparatus and server therefor
Tabbaa et al. Computer-aided training for Quranic recitation
Srikanth et al. Automatic pronunciation scoring and mispronunciation detection using CMUSphinx
Liao et al. A prototype of an adaptive Chinese pronunciation training system
Cámara Arenas et al. Automatic pronunciation assessment vs. automatic speech recognition: A study of conflicting conditions for L2-English
Yilmaz et al. Automatic assessment of children's reading with the FLaVoR decoding using a phone confusion model
Kibishi et al. A statistical method of evaluating the pronunciation proficiency/intelligibility of English presentations by Japanese speakers
KR101283271B1 (en) Apparatus for language learning and method thereof
Kitaoka et al. Effect of acoustic and linguistic contexts on human and machine speech recognition
Krasnova et al. The use of speech technology in computer assisted language learning systems
van Doremalen et al. Utterance verification in language learning applications
KR20090109501A (en) System and Method for Rhythm Training in Language Learning
Wang et al. Second language speech recognition using multiple-pass decoding with lexicon represented by multiple reduced phoneme sets
van Doremalen Developing automatic speech recognition-enabled language learning applications: from theory to practice

Legal Events

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