KR101637975B1 - Speaking test system, device and method thereof - Google Patents

Abstract

According to an embodiment of the present invention, when speech automatic evaluation is performed according to a request from a terminal device, error information having a high frequency of occurrence is collected and stored in an error DB, content containing error information stored in the error DB is selected and stored, Wherein the automatic evaluation method comprises the steps of: calculating a level of pre-stored content based on a frequency or number of occurrences of the speech data, and providing the calculated level of the content to the terminal device; A service device for transmitting an evaluation result to the terminal device; Requesting the service device to perform automatic speaking evaluation, receiving the contents including the level information, transmitting the recorded voice to the service device as a result of speech automatic evaluation, receiving the evaluation result, and providing the result to the user It is possible to accurately diagnose the error inducing factor while improving the performance of the automatic English evaluation by storing errors such as pronunciations, grammars, intensities and intonations easily learned by foreign language learners including terminals, The content suitable for speech evaluation can be selected and used for evaluation and training by using the speech recognition method. Speaking which performs speech evaluation by predicting the place where the error occurs by using the database error information, An automatic evaluation system, method and apparatus thereof are provided.

Description

[0001] Speaking test system, device and method [0002]

The present invention relates to a speech automatic evaluation system, a method and an apparatus thereof, and more particularly, to an automatic speech evaluation system which can easily and accurately find contents suitable for speech automatic evaluation among a plurality of contents And to a speech automatic rating system, method and apparatus that can be used for evaluation.

Since most existing foreign language education focuses on grammar and reading-oriented education, there is a problem that the ability to communicate in a foreign language, which is the most necessary skill in the era of globalization, does not improve despite investing a lot of time and effort in foreign language education. Due to these problems, not only the university but also the corporation, it is a tendency to confirm foreign language communication ability by practicing the foreign language speaking test separately from the conventional grammar and reading test. It is known that foreign language communication ability can be improved most effectively only through actual conversation training. In recent years, many language institutes and telephone foreign language learning services have provided conversation classes with native speakers in order to provide actual language conversation training. However, there are some problems in the education through these native English teachers.

First, learning through native English teachers is limited in time and space. Therefore, at any time, the learner can not practice conversation with a native speaker at the desired time, and education is possible only according to the circumstances of the native speaker. On the other hand, artificial intelligence agents for painting education are available at any time.

Second, since the number of native teachers is always smaller than the number of students, it is common that one native speaker instructs several learners. Therefore, the learner individual receives only a partial attention, and the efficiency of the education is lowered. On the other hand, an artificial intelligence agent can realize one-on-one education because it can manufacture as much as demand.

Third, it is difficult for native English teachers to provide educational opportunities to many learners because they are generally very expensive. However, artificial intelligence agents can be supplied in large quantities at low cost, which can provide opportunities for underprivileged learners.

Fourth, passive learners are usually ashamed to speak in front of teachers or other students, so even if there are native speakers, it may not be effective because they can not actually communicate. But in an environment where there is no one else, conversations with artificial intelligence agents help to avoid these emotional difficulties.

Fifth, because there are many differences in the professionalism among the native teachers, the achievement of the learner can be greatly changed according to the competence of the teachers, and the quality of education can be changed according to the condition of the teachers. On the other hand, artificial intelligence agents dedicated to painting education can offer the best known teaching methods in a lump sum and can always provide the same quality of education.

However, there are many limitations in using the conventional speech evaluation system. Unlike native speakers, foreign language learners have many grammatical, intense, intonation, and pronunciation errors in their utterances, so that the existing speech evaluation system does not work well.

The present invention has been proposed in order to solve the problems in conventional speech evaluation, and the object of the present invention is to provide contents which can accurately evaluate error inducing factors such as pronunciation, grammar, And a speech automatic evaluation system that can more accurately perform speech evaluation based on the speech evaluation.

As a means for solving the above problems, the present invention includes an error collection module for collecting and storing one or more pieces of error information in an error DB, and a content selection module for collecting and storing contents containing error information stored in the error DB A service providing unit for providing content collected and stored by the content selection module to the terminal when performing speech automatic evaluation according to a request from the terminal device; A communication unit for transmitting and receiving data to and from a terminal device via a network; And an error DB in which error data is stored in a database, and a storage unit for storing the selected contents.

In the service apparatus according to the present invention, the content selection module selects and stores contents capable of automatic speech recognition and speech evaluation from the collected contents.

In the service apparatus according to the present invention, the service providing unit may further include a level calculating module for calculating a level of pre-stored content based on the occurrence frequency or the number of errors, and the level of content calculated by the level calculating module is considered The content to be provided to the terminal device is selected.

In the service apparatus according to the present invention, the at least one error information includes at least one of a pronunciation error, an accent error, a grammar error, and an accent error.

In the service device according to the present invention, the service providing unit transmits at least one of the stored contents to the terminal device, and when receiving the user's voice from the terminal device, the service providing unit uses the error information stored in the error DB to generate an error And transmitting the evaluation result to the terminal device.

In the service apparatus according to the present invention, the error collecting module can count the number of occurrences generated as an evaluation result of the evaluation module and store the count in the error DB.

According to another aspect of the present invention, there is provided an information processing system including an error collecting module for collecting at least one error information and storing the error information in an error DB, a content selection module for collecting and storing contents including error information stored in the error DB, A controller for outputting the stored contents to the user when the speech automatic evaluation is performed according to a user request, evaluating the user's voice when the user's voice is input, and outputting the evaluation result; An input unit for receiving a request of a user for providing a speech automatic evaluation service; An output unit for outputting a user interface screen related to the speech automatic evaluation service; An audio control unit for processing a voice of a user; A communication unit for transmitting and receiving data through a network; And a storage unit for storing an error DB including at least one error information and contents including error information.

In the terminal device according to the present invention, the content selection module selects and stores contents capable of automatic speech recognition and speech evaluation from the collected contents.

In the terminal device according to the present invention, the control unit may further include a level calculation module for calculating a level of previously stored content based on the occurrence frequency or the number of errors, .

In the terminal device according to the present invention, the at least one error information may include at least one of a pronunciation error, an accent error, a grammar error, and an accent error.

In the terminal device according to the present invention, the controller outputs at least one of the stored contents, and when the user's voice is input, evaluates the presence or absence of an error with respect to the user's voice using the error information stored in the error DB, And an evaluation module for outputting the evaluation result.

In the terminal device according to the present invention, the error collecting module counts the number of occurrences generated as a result of the evaluation of the evaluation module and stores the count in the error DB.

According to another aspect of the present invention, there is provided a speech automatic evaluation service, comprising: storing at least one error information including an error occurrence frequency in an error DB; Collecting content including an error stored in the error DB among a plurality of contents and storing the collected contents in a storage unit; Providing at least one content of the stored content to a user when performing automatic speech evaluation; And evaluating the presence or absence of an error with respect to the user's voice by using the previously stored error data and providing the evaluation result to the user when the user's voice obtained during the automatic speech evaluation process is received, To provide a speech automatic rating service.

In the automatic speech evaluation service providing method according to the present invention, before providing at least one content to the terminal device, the level of the content is calculated by considering the occurrence frequency or the number of errors included in the content by referring to the error DB, And selecting at least one content in consideration of the level of the content.

The present invention selects contents suitable for automatic speech evaluation from existing contents, thereby enhancing the accuracy of automatic evaluation and increasing the utilization of contents, and enables prediction of scores that can be received when the subject is solved by the subject This can be used as a tool to determine the level of the overall problem.

In addition, according to the present invention, evaluation can be accurately and quickly performed by predicting and predicting a place where an error occurs, using database-based error information in speech evaluation.

1 is a block diagram showing a speech automatic evaluation system according to the present invention.
2 is a block diagram illustrating a service apparatus for providing a speech automatic evaluation service according to the present invention.
3 is a flowchart illustrating a content selection method in a speech automatic evaluation service providing method according to the present invention.
FIG. 4 is a flowchart illustrating a speech automatic evaluation method in a speech automatic evaluation service providing method according to the present invention.
5 is a block diagram illustrating a terminal device for providing a speech automatic evaluation service according to another embodiment of the present invention.
FIG. 6 is a flowchart illustrating a speech automatic evaluation method in a speech automatic evaluation service providing method according to another embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed in an ordinary or dictionary sense, and the inventor shall properly define the terms of his invention in the best way possible It should be construed as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

FIG. 1 is a block diagram of a speech automatic evaluation system according to the present invention. Referring to FIG. 1, a speech automatic evaluation system according to the present invention includes a terminal device 100, a service device 200, and a network 300 .

The automatic speech evaluation service according to the present invention can be provided by a server-based computing method. Here, the service-based computing method refers to a method in which a speech automatic evaluation service providing method according to the present invention is performed in an arbitrary apparatus connected via a network, and only input and output are performed in a terminal apparatus. Hereinafter, for convenience of explanation, an apparatus for providing a speech automatic evaluation service according to the present invention will be described as a service apparatus 200.

The service apparatus 200 is a server apparatus that provides speech automatic evaluation service according to the present invention to a plurality of terminal apparatuses 100 through a network 300. [ More specifically, the service device 200 collects error information having a high frequency of occurrence and stores the error information in an error DB when performing automatic speech evaluation in response to a request from the terminal device, The level of the stored content is determined based on the occurrence frequency or the number of errors, and the content including the level information is provided to the terminal device. In the course of performing the automatic evaluation of speech from the terminal device, When the recorded voice is received, it is evaluated using previously stored error data, and the evaluation result is transmitted to the terminal device.

The service device 200 may operate in a server-client computing manner or may operate in a cloud computing basis. That is, one or more of the computer resources required to carry out the automatic speech evaluation service, for example, hardware and software, may be provided to the service apparatus 200.

The terminal device 100 may be any of various types of devices used by a user and may be a personal computer (PC), a notebook computer, a mobile phone, a tablet PC, a navigation terminal, a smart phone, A PDA (Personal Digital Assistants), a Smart TV, a PMP (Portable Multimedia Player), and a digital broadcast receiver. Of course, this is merely an example, and it should be construed as a concept including a device that is currently developed, commercialized, or capable of all communication to be developed in the future, in addition to the above-described examples.

Such a terminal device 100 can be used by a user requesting a speech automatic evaluation service. In the automatic speech evaluation system according to the present invention, the terminal apparatus 100 requests the service apparatus to perform automatic speaking evaluation, receives content including level information, performs speaking automatic evaluation, To the device, and receives the evaluation result and provides it to the user.

The network 300 provides a path for transmitting and receiving data between the service device 200 and a plurality of terminal devices 100. [ The network 300 is an i-bimetry that provides a large capacity data transmission / reception service and a data service without a disruption phenomenon through an internet protocol (IP). The i-bimet network 300 is an i-bimet network IP network. Also, the network 300 includes a 3G mobile network including a wired network, a Wibro (Wireless Broadband) network, a WCDMA, a 3.5G mobile network including an HSDPA (High Speed Downlink Packet Access) , A fourth generation mobile network, a satellite network, and a wireless LAN including a Wi-Fi network.

In the present invention, since the terminal device 100 performs only an output function for providing a speech automatic evaluation service, the service device 200 will be mainly described below.

2 is a block diagram showing a service apparatus 200 for providing a speech automatic evaluation service according to the present invention. In FIG. 2, the configuration of the service apparatus 200 is expressed as a functional unit. However, in actual implementation, the service apparatus 200 may be distributed to a plurality of server apparatuses, or may be implemented in one server apparatus.

Referring to FIG. 2, in the automatic speech evaluation system of the present invention, a service apparatus may include a communication unit 210, a storage unit 220, and a service providing unit 230.

The communication unit 210 exchanges data with a plurality of terminal devices 100 via the network 300. [

The storage unit 220 stores data and programs for operation of the service apparatus 200. In particular, in order to provide automatic speech evaluation service according to the present invention, an error DB 221 including one or more error information, And the content 222 selected using the error DB 221. [ The error DB 221 may include at least one of a grammar error, a pronunciation error, an accent error, and an accent error, and may further include frequency incidence information of each error. The difficulty level included in the content can be determined using the error occurrence frequency information.

The service provider 230 collects error information having a high frequency of occurrence and stores the error information in the error DB 221. The service provider 230 collects and stores contents 222 including error information stored in the error DB 221, When the speech automatic evaluation is performed at the request of the apparatus, the content 222 is transmitted to the terminal. When the speech is received from the terminal apparatus 100, the error information stored in the error DB 221 is used And transmits the evaluation result to the terminal device 100. [ An error collecting module 231 for collecting error information having a high occurrence frequency and storing the error information in the error DB 221 and a content selection module 232 for collecting and storing contents including error information stored in the error DB 221 A level calculation module 233 for calculating a level of previously stored contents on the basis of the occurrence frequency or number of errors, and a level calculation module 233 for transmitting at least one of the stored contents to the terminal device, The evaluation module 234 evaluates the error information stored in the error DB 221 using the error information and transmits the evaluation result to the terminal device 100. [ The service providing unit 230 includes at least one of an error collecting module 231 and a contents discriminating module 232 and a level calculating module 233 and an evaluating module 234 for speech automatic evaluation service according to the present invention .

The error collecting module 231 collects error information having a high frequency of occurrence and stores the collected error information in the error DB 221. When automatic speech evaluation is performed at the request of the terminal, And stores it in the error DB 221.

The content selection module 232 collects contents including error information stored in the error DB 221, and selects contents 222 suitable for speech automatic evaluation using speech recognition among them.

The level calculation module 233 calculates the level of the previously stored contents based on the frequency or the number of errors. Considering the error information stored in the error DB 221, the higher the error occurrence frequency is, the higher the level of the corresponding content is calculated. On the other hand, when there are fewer errors and fewer errors, the level of the content is calculated to be lower. When the error collecting module 231 provides the automatic speech evaluation service according to the present invention, the error occurrence frequency is low and high, the error occurrence count is counted for the error generated as the evaluation result, or the error level of the error is set The frequency of occurrence of the error can be set.

The evaluation module 234 transmits at least one of the contents for providing the automatic speech evaluation service according to the present invention to the terminal device 100 in consideration of the content level and receives the user's speech from the terminal device 100 And transmits the evaluation result to the terminal device 100. The evaluation result is transmitted to the terminal device 100 using the error information stored in the error DB 221. [

The error collection module 231, the content selection module 232, the level calculation module 233 and the evaluation module 234 may be implemented by software or hardware or a combination of software and hardware. Or may be implemented by being stored in the storage unit 220 in the form of a program and executed by the service providing unit 230.

3 is a flowchart illustrating a content selection method in a speech automatic evaluation service providing method according to the present invention.

Hereinafter, a content selection process in the automatic speech evaluation system according to the present invention will be described with reference to FIG.

Referring to FIG. 3, at least one error information including a frequency of error occurrence is stored in advance in the error DB 221 in order to provide automatic speech evaluation service (S105). In step S115, contents including an error stored in the error DB are collected from among a plurality of contents, and contents suitable for speech recognition and automatic speech evaluation are selected and stored (S115).

The level of the stored content 222 is calculated based on the occurrence frequency or the number of errors (S120) and stored in the storage unit 220 (S125). In this case, considering the error information stored in the error DB 221, the higher the error occurrence frequency is, the higher the level of the corresponding content is calculated. On the other hand, when there are fewer errors and fewer errors, the level of the content is calculated to be lower. In the case of providing automatic speaking evaluation service according to the present invention, the occurrence frequency of errors is low or high, the number of occurrences is counted, or the occurrence frequency of errors is considered in consideration of the fact that the difficulty level of the errors is set Can be set.

FIG. 4 is a flowchart illustrating a speech automatic evaluation method in a speech automatic evaluation service providing method according to the present invention.

Referring to FIG. 4, the terminal device 100 requests the service device 200 to provide contents for providing the automatic speech evaluation service according to the present invention, according to a user's input signal (S305).

In response to the request of the terminal device 100, the service device 200 provides the content to the terminal device 100 in consideration of the level of the content 152 (S310). That is, when the level information of the user of the terminal device 100 is stored in the service device 200, the level information can be selected and provided to the terminal device 100 using the selected level of content. Or may provide the terminal device 100 with a content including a desired level or a desired type of error according to a user request of the terminal device 100. [

The terminal device 100 receiving the contents performs automatic speaking evaluation according to the present invention to the user at step S315 and transmits the user's voice to the service device 200 at step S320.

The service device 200 can evaluate whether or not the user's voice contains an error using the error DB 221 (S325). Since the error information can be predicted in advance using the error DB 221, It can be done quickly.

For example, in pronunciation errors, fork should be pronounced with / f /, but an error pronounced with / p / can occur. Especially in Korean, pronouncing / p / The frequency of errors is generally high. If the fork word is included in the contents used in the speech automatic evaluation, it is checked whether there is an error to be pronounced by / p / Evaluation is possible.

The number of occurrences is counted and stored in the error DB 221 (S330) to provide the automatic speech evaluation service according to the present invention to the user of the terminal device 100 according to the level.

In another embodiment of the present invention, provision of a speech automatic evaluation service may be based on the terminal device 100. [ Here, the service apparatus 200 performs a plurality of contents provision only to the terminal apparatus 100, and thus can be configured as shown in FIG.

5 is a block diagram illustrating a configuration of a terminal device 100 for providing a speech automatic evaluation service according to another embodiment of the present invention.

5, a terminal device 100 according to the present invention includes a communication unit 110, an input unit 120, an audio processing unit 130, an output unit 140, a storage unit 150, (Not shown).

The communication unit 110 exchanges data with the service device 200 via the network 300.

The input unit 120 is a means for generating a user input signal for controlling or operating the terminal device 100 according to a user's operation, and may be implemented by input means of various types. For example, the input unit 120 may include at least one of a key input unit, a touch input unit, a gesture input unit, and a voice input unit. The key input means generates a signal corresponding to the key according to the key operation, and corresponds to a keypad and a keyboard. The touch input means is a touch pad, a touch screen, and a touch sensor, which recognize an input operation by sensing a user's operation of touching a specific portion. The gesture input means recognizes a specific operation, such as a shaking or moving operation of the terminal device, an approach to the terminal device, a blinking operation, etc., as a specific input signal, such as a geomagnetic sensor, A sensor, a camera, an altimeter, a gyro sensor, and a proximity sensor.

The audio processing unit 130 performs speech recognition by inputting a speech for automatic speaking evaluation of the present invention by a user of the terminal device 100 and performs speech recognition by using a wired / wireless earphone, a wire / wireless speaker, Output through one. The audio processing unit 130 may include a microphone for inputting a voice and a speaker for outputting the voice.

The output unit 140 may be an LCD (Liquid Crystal Display), a TFT-LCD (Thin Film Transistor-Liquid Crystal Display), an LED Emitting Diodes), OLED (Organic Light Emitting Diodes), AMOLED (Active Matrix Organic Light Emitting Diodes), flexible displays, and three-dimensional displays.

The storage unit 150 is a means for storing data or programs necessary for the operation of the terminal apparatus 100 and can basically store an operating program (OS) of the terminal apparatus 100 and one or more application programs. In addition, in the present invention, the storage unit 150 stores the error DB 151 for providing a speech automatic evaluation service and the selected content 152. The storage unit 150 may be any type of storage such as a RAM (Read Only Memory), a ROM (Read Only Memory), a hard disk (HDD), a flash memory, a CD- Media.

The control unit 160 controls the entire operation of the terminal device 100 and basically operates based on the operating program stored in the storage unit 150 to establish a basic platform environment of the terminal device 100, And provides an arbitrary function by executing the application program. In another embodiment of the present invention, the control unit 160 collects error information having a high frequency of occurrence, stores the error information in the error DB 151, and collects the content including the error information stored in the error DB 151 When speech automatic evaluation is performed according to a user's request, when a voice of a user is input, evaluation is performed using the error information stored in the error DB 151, and the evaluation result is output. The control unit 160 may include at least one of an error collection module 161, a content selection module 162, a level calculation module 163, and an evaluation module 164.

The error collecting module 161 collects error information having a high frequency of occurrence and stores the collected error information in the error DB 151. When automatic speech evaluation is performed at the request of the terminal, And stores it in the error DB 151. The content selection module 162 collects contents containing error information stored in the error DB 151, and selects contents 152 suitable for automatic speech evaluation using speech recognition. The level calculation module 163 calculates the level of the previously stored content based on the frequency or the number of errors. The evaluation module 164 transmits at least one of the contents for providing the automatic speech evaluation service according to the present invention to the terminal device 100 in consideration of the content level and receives the user's speech from the terminal device 100 And transmits the result of the evaluation to the terminal device 100. The evaluation result is transmitted to the terminal device 100 using the error information stored in the error DB 151. [

The error collection module 161, the content selection module 162, the level calculation module 163 and the evaluation module 164 may be implemented by software or hardware or a combination of software and hardware. For example, And may be implemented by being stored in the storage unit 150 and executed by the controller 160. FIG.

FIG. 6 is a flowchart illustrating a speech automatic evaluation method in a speech automatic evaluation service providing method according to another embodiment of the present invention.

The content selection method of the speech automatic evaluation service providing method according to another embodiment of the present invention may be performed in the same manner as the content selection method shown in FIG.

Referring to FIG. 6, when a user requests to perform automatic speech evaluation according to another embodiment of the present invention (S205), the control unit 160 of the terminal device 100 determines whether the level of the user And provides the contents (S210). The user performs voice recording for evaluation using the contents (S215), and automatic speech evaluation is performed using the error DB 151 (S220). In addition, the error information generated as a result of the evaluation is updated and stored in the error DB 151 (S225).

The automatic speech evaluation method according to the present invention may be implemented in a form of software readable by various computer means and recorded in a computer-readable recording medium. Here, the recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Includes a hardware device that is specially configured to store and execute program instructions such as a magneto-optical medium such as a floppy disk and a ROM, a random access memory (RAM), a flash memory, do. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be apparent to those skilled in the art. Furthermore, although specific terms are used in this specification and the drawings, they are used in a generic sense only to facilitate the description of the invention and to facilitate understanding of the invention, and are not intended to limit the scope of the invention.

The present invention is applied to the foreign language learning of the present invention to select contents suitable for automatic speech evaluation from existing contents, thereby improving the accuracy of automatic evaluation and improving the utilization of contents, as well as a score that can be received when the subject has solved the selected contents Which can be used as a tool to determine the level of the overall problem.

In addition, evaluation can be performed accurately and quickly by predicting and predicting the place where the error occurs by using the error information in the database during speech evaluation.

100: terminal device 110: communication unit 120: input unit
130: audio processing unit 140: output unit 150:
151: error DB 152: selected content 160:
161: Error collecting module 162: Content sorting module
163: Level calculation module 164: Evaluation module 200: Service device
210: communication unit 220: storage unit 221: error DB
222: Selected contents 230: Service providing 231: Error collecting module
232: Content selection module 233: Level calculation module 234: Evaluation module

Claims (14)

An error collection module for collecting one or more error information and storing the error information in an error database, a content selection module for collecting and storing contents containing error information stored in the error database, and a level of the stored content And a level calculation module for calculating a level of the contents calculated by the level calculation module when performing speech automatic evaluation according to a request of the terminal device, Service provided by the device;
A communication unit for transmitting and receiving data to and from a terminal device via a network;
And an error DB in which error data is stored in a database, and a storage unit for storing the collected contents. The content browsing module according to claim 1,
Wherein the contents are selected and stored in the collected contents, the contents being capable of automatic speech recognition and speech evaluation. delete The method according to claim 1,
Wherein the at least one error information includes at least one of a pronunciation error, an accent error, a grammar error, and an accent error. The method of claim 1, wherein the service providing unit
Receiving at least one of the stored contents to the terminal device and receiving the user's voice from the terminal device, evaluating whether or not the user's voice has an error using the error information stored in the error DB, To the terminal device, and the evaluation module transmits the automatic evaluation service to the terminal device. 6. The apparatus of claim 5, wherein the error collection module
And counts the number of occurrences of the error generated as a result of the evaluation of the evaluation module and stores the count in the error DB. An error collection module for collecting and storing at least one piece of error information in an error DB, a content selection module for collecting and storing contents containing error information stored in the error DB, And a level calculation module for calculating a level of the content, and when the automatic evaluation of speech is performed according to a user request, content to be output is determined in consideration of the level calculated in the level calculation module, and the determined content is output to the user A control unit for evaluating the user's voice when the user's voice is input and outputting the evaluation result;
An input unit for receiving a request of a user for providing the automatic speech evaluation service;
An output unit outputting a user interface screen related to the speech automatic evaluation service;
An audio control unit for processing a voice of a user;
A communication unit for transmitting and receiving data through a network;
And a storage unit for storing contents including the error DB including the at least one error information and the error information. The content browsing method according to claim 7,
Wherein the contents are selected and stored in the collected contents, the contents being capable of automatic speech recognition and speech evaluation. delete 8. The method of claim 7,
Wherein the at least one error information includes at least one of a pronunciation error, an accent error, a grammar error, and an accent error. 11. The apparatus of claim 10, wherein the control unit
And an evaluation module for evaluating the presence or absence of the error with respect to the user's voice using the error information stored in the error DB and outputting the evaluation result when the user's voice is input after outputting at least one of the stored contents Wherein the automatic evaluation service is provided to the terminal device. 12. The apparatus of claim 11, wherein the error collection module
And counts the number of occurrences of the error generated as a result of the evaluation of the evaluation module, and stores the count in the error DB. Storing at least one error information including an error occurrence frequency in an error DB in providing automatic speech evaluation service;
Collecting content including an error stored in the error DB among a plurality of contents and storing the collected contents in a storage unit;
Calculating a level of the content in consideration of the occurrence frequency or the number of errors included in the content;
Selecting the at least one content by considering the calculated level;
Providing at least one content among the selected contents to a user when performing speech automatic evaluation according to a request of a terminal device; And
And evaluating the presence or absence of an error with respect to the user's voice using the previously stored error data and providing the evaluation result to the user when the user's voice acquired during the speech automatic evaluation process is received To provide automatic evaluation service. delete

Images