JP2017054038A - Learning support device and program for the learning support device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a learning support apparatus for appropriately supporting a user's learning.SOLUTION: A learning support apparatus 10 has means 11 that performs a series of processing including: recognizing voices which are input via a voice input section 12 to convert the same into a text; determining a pronunciation status of words included in the text; controlling to identify and display the text depending on the discrimination result; and providing a learning item corresponding to a specification of at least a part of the identified and displayed text made by a user.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a learning support apparatus and a program for the learning support apparatus.

For example, Patent Document 1 discloses a system for practicing conversation by associating text and voice in a conversation so that the voice of a specified part can be reproduced without sound.
Further, Patent Document 2 discloses an English conversation learning apparatus in which an answer to a problem is made by voice, this is recorded, and the recorded voice is reproduced and then the correct voice is heard.

JP 2004-205782 A Japanese Patent Laid-Open No. 10-228230

  Conventionally, learning support devices that support language learning as described above are known, but the emergence of learning support devices that support learning more appropriately is desired.

  The present invention has been made in view of such circumstances, and an object thereof is to provide a learning support apparatus and a program for the learning support apparatus that can support language learning and the like more appropriately.

The present invention is grasped by the following composition in order to achieve the above-mentioned object.
The learning support apparatus of the present invention recognizes input speech and converts it into text, means for discriminating the utterance status of a word included in the text, and identifying and displaying the text according to the discrimination result And means for providing corresponding learning items in response to a user specifying at least a part of the identified and displayed text.

  A program for a learning support apparatus according to the present invention includes: a procedure for recognizing input speech into a computer of a learning support apparatus and converting it into text; a procedure for determining the utterance status of a word included in the text; and a determination result And a procedure for controlling the text to be identified and displayed in accordance with the text, and a procedure for providing a corresponding learning item in response to a user specifying at least a part of the text that has been identified and displayed.

  ADVANTAGE OF THE INVENTION According to this invention, the learning assistance apparatus which supports learning more appropriately, and the program for the learning assistance apparatus can be provided.

It is a front view of the learning assistance apparatus which concerns on embodiment of this invention. It is a block diagram which shows the structure of the learning assistance apparatus which concerns on embodiment of this invention. It is a flowchart which shows the basic operation | movement of the learning assistance apparatus which concerns on embodiment of this invention. 4 is a flowchart showing a detailed procedure of “analysis result display” processing shown in FIG. 3. It is the screen transition figure which expanded and showed the operation | movement of the learning assistance apparatus which concerns on embodiment of this invention on a display screen. It is a figure showing an example at the time of constructing a learning support device concerning an embodiment of the present invention with a tablet terminal and a server.

DETAILED DESCRIPTION Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as embodiments) will be described in detail with reference to the accompanying drawings.
In the subsequent drawings, the same numbers or symbols are assigned to the same elements throughout the description of the embodiments.

(Configuration of the embodiment)
FIG. 1 is a front view of a learning support apparatus 10 according to the present embodiment, and FIG. 2 is a block diagram showing a control system of the learning support apparatus 10.
As illustrated in FIG. 1, the learning support device 10 according to the present embodiment includes a display unit 14 and an input unit 13.
In the present embodiment, since the display unit 14 has a touch panel function, the display unit 14 also constitutes a part of the input unit 13.

  In addition, the learning support apparatus 10 according to the present embodiment includes a voice input unit 12 (for example, a microphone) for inputting voice (not shown) and a voice output unit (for example, speaker) for outputting voice (not shown). Yes.

Next, the control system of the learning support apparatus 10 will be described with reference to FIG.
As shown in FIG. 2, the learning support apparatus 10 includes a processing unit 11, a storage unit 15, and a VRAM (Video RAM) 16, and the processing unit 11 includes the voice input unit 12 and the input described above. The unit 13 and the display unit 14 are connected.

  The processing unit 11 is a control center of the learning support device 10. For example, the processing unit 11 has a built-in microprocessor, and executes functions to be described later by reading and sequentially executing control programs and the like stored in a predetermined area of the storage unit 15. .

The voice input unit 12 recognizes the input voice and passes the recognition result to the processing unit 11.
The input unit 13 sends a command to the processing unit 11 in accordance with a user operation (key input or touch panel input).

  In the present embodiment, a learning support device having a learning support function as an example of a portable electronic dictionary function is taken as an example, but the main body of the learning support device is a notebook personal computer or the like. Therefore, the input unit 13 may be a mouse or a keyboard.

The display unit 14 is a display monitor that displays text converted by the processing unit 11.
Various displays can be used as the display monitor constituting the display unit 14, and for example, a display monitor composed of a liquid crystal display (LCD) or an organic electroluminescence display (OELD) is preferably used. be able to.
In the present embodiment, the display unit 14 is integrated with the touch panel so as to function as a part of the input unit 13, but the display unit 14 is not necessarily provided with the touch panel.
However, the display unit 14 with a touch panel is preferable because convenience of various operations can be achieved.

The storage unit 15 is mounted with, for example, a semiconductor memory such as a flash memory. In addition to an area for storing a program such as a control program, a speech recognition program, and a speaking program, an area for storing data such as a dictionary DB, A work area for storing various data (text data, frequency data, etc.) generated in the course of program execution is allocated, and these programs and data are stored.
Of various data generated during the execution of the program, data that only needs to be temporarily stored is stored in the temporary storage area. However, regarding data used at the next use of the learning support apparatus 10, for example, learning is performed. When the operation of the support device 10 is finished, the data is stored in a storage area that is not a temporary storage area.

  A VRAM (Video RAM) 16 is a display memory in which display data generated by the processing unit 11 is stored. The stored display data and the like are updated by the processing unit 11 and synchronized with the display timing of the display unit 14. Then, the data is read out by the processing unit 11 and output to the display unit 14.

  As will be described later, the processing unit 11 recognizes input speech and converts it into text (speech-text conversion unit), and determines a speech state of words included in the text (speech state determination unit). ), Means for controlling to display the text on the display unit 14 so as to identify and display the text according to the determination result (display control means), and responding according to the user designating at least a part of the identified and displayed text Means (display control means) for displaying learning items to be displayed on the display unit 14 and providing the learning items are provided.

As will be described later, the processing unit 11 includes means for searching for example sentences (example sentence search means) and means for searching for synonyms (synonym search means).
Each of these speech-text conversion means, speech state determination means, display control means, example sentence search means, and synonym search means causes the processing unit 11 to execute various programs with reference to various data stored in the storage unit 15. This is a function realized by.

(Operation of the embodiment)
The operation of the learning support apparatus 10 according to the present embodiment will be described in detail with reference to the flowcharts of FIGS. 3 and 4 and the screen transition diagram of FIG.
Hereinafter, the operation of the learning support apparatus 10 will be described in detail by taking the case of speaking learning for improving the speaking ability as an example.

When the speaking learning is started, the processing unit 11 presents the problem based on the program, and displays the problem on the display unit 14 as, for example, a speaking card screen shown in FIG. 5A (step S101 in FIG. 3).
Here, since a problem explaining “family” in English is displayed, the user answers the explanation of “family” in English.

  As shown in FIG. 5A, since the “recording” icon for starting “recording” by touching which functions as the input unit 13 is displayed on the upper right of the speaking card screen, the user starts answering. At this time, the user touches the “recording” icon, answers the problem presented when recording is started, that is, “family”, and inputs the answer by voice.

  When recording is started by touching the “recording” icon, the processing unit 11 stops the recording of the “recording” icon displayed on the display unit 14 as shown in FIG. Instead of the “stop” icon, you can stop recording when the answer is over.

  When the processing unit 11 detects that the “recording” icon has been touched, it starts accepting voice input via the voice input unit 12 (step S102 in FIG. 3), and the response by the user's voice is received by voice recognition processing. The data is converted into text data (hereinafter simply referred to as text data), and the recognition result (text) is temporarily stored in a work area for storing text data in the storage unit 15 (step S103 in FIG. 3). ).

At the same time, the processing unit 11 measures the time from the end of the utterance of the previous word to the start of the utterance of the next word as the utterance state of each word being answered by voice (FIG. 3). Step S104).
Note that the processing in steps S103 and S104 is continued until the above-described “stop” icon is touched (step S105 “No”).

When the user finishes answering by voice, the user touches the “stop” icon displayed on the upper right of the above speaking card screen to finish answering and recording.
When the processing unit 11 detects that the “stop” icon is touched (step S105 “Yes”), as shown in FIG. 5C, the processing unit 11 reproduces the voice of the answer in which the “stop” icon is recorded. When the user touches the “play” icon instead of the “play” icon, the recorded answer voice can be played, and the processing unit 11 can refer to the left corner and select a menu screen for analysis. Is displayed (step S106 in FIG. 3).

When the processing unit 11 displays the menu screen illustrated in FIG. 5C, the processing unit 11 is in a standby state until the user performs some operation.
Here, when the user operates the input unit 13 (touch operation or key operation) to perform any operation, the processing unit 11 detects the operation, and the processing unit 11 performs “reproduction” as the operation performed by the user. Is determined (step S107 in FIG. 3).

When the operation performed by the user is an operation for selecting “play” by touching the “play” icon (step S107 “Yes” in FIG. 3), the processing unit 11 plays the recorded data of the answer voice. (Step S108 in FIG. 3).
When the reproduction of the answer voice recording data is completed, the processing unit 11 again displays the screen in the state shown in FIG. 5C and enters a standby state until the next user operation occurs.

  If the operation performed by the user is not an operation for selecting “play” (step S107 “No” in FIG. 3), the processing unit 11 performs “reference” on the menu screen at the left corner. It is determined whether the operation is to be selected (step S109 in FIG. 3). If the operation is to select “reference” (step S109 “Yes” in FIG. 3), an example of an answer to the previous problem is displayed on the display unit 14. It is displayed (step S110 in FIG. 3).

  If the user operates the input unit 13 (touch operation or key operation) to return to the screen display in the state shown in FIG. The processing unit 11 displays the screen in the state shown in FIG. 5C and enters a standby state until the next user operation occurs.

  Further, when the operation performed by the user is not an operation for selecting “reference” (step S109 “NO” in FIG. 3), the processing unit 11 performs “analysis” on the menu screen in the left corner. It is determined whether the operation is to be selected (step S111 in FIG. 3). If the operation is not an operation to select “analysis” (step S111 “No” in FIG. 3), for example, a process of ending “speaking learning” is performed. Run.

On the other hand, when the operation performed by the user is an operation of selecting “analysis” on the menu screen in the left corner (step S111 “Yes” in FIG. 3), the processing unit 11 executes a process of displaying the analysis result ( Step S112 in FIG.
The process of displaying the analysis result is executed, for example, according to the procedure shown in the flowchart shown in FIG.

  When the user operates the input unit 13 (touch operation or key operation) and returns to the screen display in the state shown in FIG. The processing unit 11 displays the screen in the state shown in FIG. 5C and enters a standby state until the next user operation occurs.

Hereinafter, the process of displaying the analysis result in step S112 in FIG. 3 will be described with reference to FIGS. 4 and 5D.
When the analysis result display process is started, as shown in FIG. 4, the processing unit 11 updates the frequency data of words in the text (step S201).

  More specifically, the storage unit 15 stores the number of words used by the user in the previous speaking learning, and the processing unit 11 uses the voice of the user by the process of step S103 in FIG. The answer is converted into text data, and the word frequency data is updated by adding the number of times of use for the word in the text (in the text data) stored in the work area of the storage unit 15.

  When the update of the word frequency data is completed, the processing unit 11 then uses a large frequency of use in the text of the current answer (usage frequency exceeding a predetermined threshold) as the utterance status of the current speaking learning. (Step S202), if there is a word with a frequency of use exceeding the threshold (step S202 "Yes"), the first identification display information is added to the word (step S203).

  As will be described later, for example, when displaying a light blue marker for the frequently used word as the first identification display information, in step S203, a light blue marker flag for displaying a light blue marker on the frequently used word Is added.

  On the other hand, if there is no use frequency word exceeding the threshold in the text of the current answer (step S202 “No”), the process proceeds to step S204, which is the next step, without performing the process of step S203.

In step S204, the processing unit 11 determines the time until the utterance of each spoken word based on the measurement result of the time taken to utter the word measured in step S104 in FIG. Is confirmed (step S204).
In other words, by checking the time from the last word spoken to the next word utterance, it seems that words that took a long time to speak are not good at speaking, This is a process for confirming whether or not there is a word that takes time to speak.
Specifically, for each word, it is checked whether the time required for uttering each word measured in step S104 in FIG. 3 exceeds a predetermined threshold (step S204). If there is a word that took time (word that took time exceeding the threshold) (step S205 “Yes”), the second identification display information is added to the word (step S206).

  As will be described later, for example, as a second identification display information, when a purple marker is displayed for a word that took time to speak, in step S206, a purple marker is displayed for a word that took time to speak. Add a purple marker flag.

On the other hand, if there is no word whose utterance time exceeds the threshold in the text of the answer this time (step S205 “No”), the process proceeds to the next step, step S207, without performing the process of step S206.
In this manner, the processing unit 11 functions as a means for determining the utterance situation such as the frequency of use of words in the text and the time required for utterance by comparing with the threshold value.

  In step S207, if there is a word with a light blue marker flag in a word in the text, the processing unit 11 adds a light blue marker to the display portion of the word, and if there is a word with a purple marker flag, displays the word. The text is displayed on the display unit 14 so that a purple marker is added to the portion.

FIG. 5D is a diagram showing a place where the voice text in which the voice data of the current answer is text data is displayed on the display unit 14, but the color is not known in the figure, but “related” in this voice text is shown. The word "" is displayed with a purple marker added because the time required for utterance exceeds the threshold.
Similarly, the word “specially” is displayed with a light blue marker added because the usage frequency exceeds the threshold.
In this way, the processing unit 11 functions as a means for controlling the text to be identified and displayed according to the determination result such as the frequency of use and the time required for utterance, and the text reflecting the identification display is displayed on the display unit 14. When displayed, the processing unit 11 is in a standby state until the user's next operation is performed.

  When the user performs an operation, the processing unit 11 determines whether the first word to which the first identification information is added is specified (step S208). Here, when the user's operation is the first word designation by touching “especially” (step S208 “Yes”), the processing unit 11 determines that the utterance status is the frequency of the spoken word, and the English thesaurus dictionary. (Dictionary) is selected, and a synonym (synonym dictionary search) of a frequently used word (especially in this example) in which the first word is designated is searched (step S209). Then, the processing unit 11 displays the synonym on the display unit 14 based on the synonym search result so that another expression method using another word can be understood as the corresponding learning item according to the designation by the user. (Step S210), and provides the user with a learning item of another expression method using another word.

  For example, various types of dictionary data are stored in the dictionary DB of the learning support apparatus 10, and the processing unit 11 selects an English synonym dictionary (dictionary) from among these, and searches for synonyms of frequently used words. To display synonyms.

  On the other hand, when the user operation is not the first word designation (step S208 “No”), the processing unit 11 determines whether the second word to which the second identification information is added is designated (step S208). S211). If the user operation is not an operation for specifying the second word by touching “related” (step S211 “No”), the process proceeds to other processing, but the user operation touches “related”. If the operation is an operation for specifying the second word (step S211 “Yes”), the processing unit 11 stores the utterance status as the time elapsed until the utterance of the spoken word is stored in the dictionary DB. An example sentence search is performed from the data (step S212). Then, the processing unit 11 displays, on the display unit 14, an example sentence that shows how to use a word that took time to speak as a corresponding learning item according to the designation by the user (step S 213). Provide example sentences that show how to use words as learning items.

When an operation for returning to the original screen is performed in a state where the synonyms and example sentences are displayed on the display unit 14 in step S210 and step S213, processing for returning to the state in step S207 is performed again.
In the above description, when step S211 is No, only the process proceeds to other processes. For example, the other processes include a process that proceeds to the next speaking learning or a process that ends the speaking learning. Or

  As described above, according to the learning support apparatus 10 according to the present embodiment, in language learning such as English, words spoken by a user are recognized and analyzed, and frequently used words or time is required until utterances. The learning function can be enhanced by pointing out the words that have been used and jumping from those words to a dictionary search, and the user can efficiently overcome difficult words without being aware of them. Can do.

  From the user's side, voice answers are input to the speaking-type questions presented by the learning support device. After input, the user's answer is analyzed, and the time and bias required for utterances are analyzed. You can efficiently obtain relevant information by extracting the words you use and linking the extracted English expressions, which are your weak points, with a dictionary, and have the instantaneous correspondence and expressive power necessary for speaking You can train efficiently.

  In addition, as a separate function, a function to explain "human relations", "geographical landform relations", "history relations", etc. in a foreign language is prepared, and "human relations", If it is possible to learn what answers are given to problems such as “geography and terrain relation” and “history relation”, the learning support apparatus can be made more convenient.

In addition to extracting words at random, the question is not limited to questions, but the user learns by editing questions that are questioned by field such as “human relations”, “geographical topography relations”, “history relations”, etc. You may make it select the field to want and ask a question according to the selected field.
In the above, the marker display method is shown as a method of clearly indicating the word that the user is not good at. However, the display form is such that the color underline is drawn under the word or only the character color of the word is changed. It may be changed as appropriate.

Furthermore, although the case where it is the learning assistance apparatus which incorporates dictionary DB was shown above, the aspect of a learning assistance apparatus is not limited to such a thing.
For example, as illustrated in FIG. 6, a learning support apparatus 100 configured by a tablet terminal 101 and a server 102 may be used.

In this case, the user possesses a terminal (for example, a tablet terminal 101 such as a smartphone), causes the server 102 connected via the network 103 such as an IP network to transmit the voice data input to the tablet terminal 101, and causes the server 102 to Recognize voice data and convert it to text, determine the utterance status of words in the text, and create data that identifies and displays the text according to the determination result Thus, the text data identified and displayed may be returned to the tablet terminal 101 so that the text data identified and displayed on the tablet terminal 101 is displayed.
In this way, processing with a large amount of calculation can be performed on the server 102 side having sufficient processing capacity.

Then, when the user designates at least a part of the identified and displayed text displayed on the tablet terminal 101, for example, when the touch designation of the word displayed as a marker is performed as in the above example, the tablet terminal again responds to this designation. 101 transmits the designated content to the server 102 side, and based on the transmitted designated content, the learning item (synonyms and example sentences) corresponding to the designated content is returned from the server 102 side to the tablet terminal 101 side. The learning items (synonyms and example sentences) may be displayed on the screen.
In this way, it is possible to cause the server 102 to perform processing with a large amount of calculation such as search performed to display the learning items, and to provide the server 102 with a large storage capacity with a dictionary DB and the like. This is preferable.
In the case of the learning support apparatus 100 configured by such a tablet terminal 101 and the server 102, the voice input unit 12 is provided in the tablet terminal 101 serving as a display unit.

As mentioned above, although this invention was demonstrated using embodiment, it cannot be overemphasized that the technical scope of this invention is not limited to the range as described in the said embodiment.
For example, the dictionary DB itself may be a learning support apparatus that can be accessed via the network and the like and provided with other necessary functions, and various modifications or improvements are added to the above embodiment. It will be apparent to those skilled in the art that the embodiments described above are possible, and it is apparent from the scope of the claims that the embodiments added with such changes or improvements are also included in the technical scope of the present invention.

The invention described in the scope of claims attached to the application of this application will be added below. The item numbers of the claims described in the appendix are as set forth in the claims attached to the application of this application.
[Claim 1]
Means for recognizing input speech and converting it to text;
Means for determining the utterance status of a word included in the text;
Means for controlling and displaying the text according to the determination result;
Means for providing corresponding learning items in response to a user specifying at least a portion of the identified and displayed text;
A learning support apparatus characterized by comprising:
[Claim 2]
It has a means to search for example sentences,
The utterance state is a time elapsed until the utterance is made, and the means for searching for example sentences performs an example sentence search for the words for which the time exceeds a predetermined time as the learning items. The learning support device according to claim 1.
[Claim 3]
A means to search for synonyms,
The utterance status is the frequency of spoken words, and the synonym search means executes synonym search on the words that exceed a predetermined frequency to make the learning items. Learning support device.
[Claim 4]
A voice input means and a display unit for displaying a problem;
The learning support apparatus according to claim 1, wherein a problem is displayed on the display unit, and an answer to the problem is input by voice.
[Claim 5]
In the computer of the learning support device,
Recognizing input speech and converting it to text,
A procedure for determining the utterance status of a word included in the text;
A procedure for controlling to identify and display the text according to the determination result;
Providing a learning item corresponding to a user specifying at least a part of the identified and displayed text;
A program that executes

DESCRIPTION OF SYMBOLS 10 Learning support apparatus 11 Processing part 12 Voice input part 13 Input part 14 Display part 15 Memory | storage part 16 VRAM
100 learning support apparatus 101 tablet terminal 102 server 103 network

Claims (5)

Means for recognizing input speech and converting it to text;
Means for determining the utterance status of a word included in the text;
Means for controlling and displaying the text according to the determination result;
Means for providing corresponding learning items in response to a user specifying at least a portion of the identified and displayed text;
A learning support apparatus characterized by comprising: It has a means to search for example sentences,
The utterance state is a time elapsed until the utterance is made, and the means for searching for example sentences performs an example sentence search for the words for which the time exceeds a predetermined time as the learning items. The learning support device according to claim 1. A means to search for synonyms,
The utterance status is the frequency of spoken words, and the synonym search means executes synonym search on the words that exceed a predetermined frequency to make the learning items. Learning support device. A voice input means and a display unit for displaying a problem;
The learning support apparatus according to claim 1, wherein a problem is displayed on the display unit, and an answer to the problem is input by voice. In the computer of the learning support device,
Recognizing input speech and converting it to text,
A procedure for determining the utterance status of a word included in the text;
A procedure for controlling to identify and display the text according to the determination result;
Providing a learning item corresponding to a user specifying at least a part of the identified and displayed text;
A program that executes