JPH02302787A - Automatic conversation practice device - Google Patents

Abstract

PURPOSE:To practice conversation practically in conformity with the state of conversation by deciding the conversation skillfulness of a learner as the conversation advances and setting the best conversation level. CONSTITUTION:The state of conversation is explained before the conversation is practiced and a learner's answering voice corresponding to a question is inputted and compared with an example answer stored in an example answer storage part 11 for decision making a decision about whether or not the input answer is correct; and the input is compared with the contents of a storage part 13 stored with answer examples for conversation level decision making to decide a conversation level. Then the level and state of the conversation are changed according to the skillfulness of learner's conversation, the conversation level corresponding to the conversation skillfulness of the learner is set automatically, and the conversation practice is advanced. Consequently, the conversation can be practiced in the scene and state corresponding to the learner's conversation level.

Description

[Detailed Description of the Invention] [Industrial Application Field] An interactive conversation that automatically sets the conversation situation according to the conversation proficiency level and enables practice when practicing foreign language conversation. This relates to a training device.

[Prior Art] Conventionally, as shown in Fig. 4, for foreign language conversation practice,
This was a practice method that involved using text and audio tapes, or repeating the contents of the tapes while watching video tapes. Therefore, the learner will have to answer the next question regardless of whether or not he or she gave the correct answer, and after answering, the correct answer will be unilaterally output from the tape and the learner will have to figure out why the answer was incorrect. The situation soon changes to the next scene. Therefore, students had no choice but to practice conversation regardless of changes in the situation or the level of conversation proficiency of the learner.

Additionally, in general, learners judge the effectiveness of their practice by looking at the display of conversation proficiency written on the tape in advance, such as advanced, intermediate, or beginner level, and practice while changing conversation tapes. continued. Therefore, these conversation exercises are one-way exercises, and it is not possible to practice conversation according to the scene or situation, which is the basis of conversation. Also, it was not possible to know how much improvement had been made as a result of practice.

Recently, some pronunciation practice devices, as typified by the block diagram of FIG. 5, have come on the market.
The standard speech stored in the standard speech is played back and shown to the learner, and the characteristic parameters of the speech extracted by the analysis section 25 are stored in the storage section 26. Next, the learner inputs the same voice as the one reproduced through the microphone 24, and the analyzer 25 extracts the characteristics of the learner's voice and sends it to the collation unit 27.

The matching section 27 compares and matches the feature parameters of the standard speech stored in the storage section 26 and outputs the results to the display section 28 to show the degree of similarity to the learner.

In other words, learners learn the correctness of their pronunciation and the degree of similarity to the standard pronunciation, and by repeating this process, they practice bringing their pronunciation closer to the standard pronunciation, and practice the correct way to pronounce the pronunciation. That's what it was.

[Problem to be solved by the invention] With conventional technology, it is possible to practice correct pronunciation, but it is not possible to practice conversation, and it is not possible to practice conversation properly and smoothly in response to changes in situations and scenes. The device was not suitable for practicing. The present invention changes the situation and scene according to the conversation situation and the conversation level of the learner, explains the situation and scene with audio, makes the conversation situation known at the start of practice, and changes the situation and scene according to the conversation level of the learner. After imagining the situation, it was possible to practice. In addition, instead of having the learner replace tapes, the learner's conversation proficiency level is determined from the answers to questions, and the situation is automatically set freely according to the learner's conversation level, and the conversation level is automatically adjusted. This makes it possible to reset the settings.

[Means for Solving the Problems] In order to solve the above problems, the automatic conversation training device of the present invention explains the conversation situation in advance before practicing the conversation,
and a screen table, a receiving part, and an audio output part for outputting information from the teaching material storage part for providing conversation teaching materials and questions;
A voice input unit that inputs and recognizes the learner's voice; an answer correctness determination unit that determines whether the recognition input obtained by the voice input unit is the correct answer to the question from the device; and a model answer necessary for determination. In order to judge the level of a learner's conversational proficiency, accent, intonation, correctness of pronunciation, accuracy of syntax, etc. are extracted, and the correct answer model example storage section stores the conversational proficiency of the learner. a conversation level determination unit for determining a conversation level; a model answer example storage unit for storing model answer examples that serve as standards for conversation level determination; a conversation procedure control unit for controlling conversation procedures according to the conversation proficiency level of the learner; Conversation level change control unit to change the level when it is necessary to change the level, change the conversation situation, and display and explain the situation again, change the screen when changing the conversation level, and change the conversation procedure. and a main control section that gives instructions and controls the entire system.

[Function] Before practicing the conversation, the conversation situation is explained in advance, and the voice of the learner's answers in response to the questions is input, and the model answer storage unit is used to store the model answers necessary for judgment. It compares the answer with the model answer to determine whether it is correct, and compares it with the contents of the memory unit that stores example answers for determining the conversation level to determine the conversation level. To proceed with conversation practice by changing the conversation level and conversation situation and automatically setting the conversation level according to the conversation proficiency level of the learner.

[Example] FIG. 1 is a block diagram showing one embodiment of the present invention.

The learner listens to the audio output from the speaker 2 while looking at the screen read out from the teaching material storage section 4 and displayed on the display section 1, and grasps the situation of the conversation to be practiced.

The teaching material storage unit 4 stores information such as images and sounds using a storage medium such as a white disk, an optical disk, an IC memory, or a magnetic tape.

Each time the situation is changed, the screen display control section 3 reads the corresponding screen of each teaching material consisting of a plurality of screens from the teaching material storage section in response to a situation change instruction from the conversation level change control section 5, and displays the screen of each teaching material. Performs control to change the display screen.

The conversation level change control section 5 receives a screen change instruction from the main control section 6. Conversation level change control section 5 simultaneously issues a conversation level change instruction to voice conversation procedure control section 7 to change the conversation level.

The voice conversation procedure control unit 7 changes the conversation procedure and moxibustion to be used according to the instructed conversation level. When changing the conversation level, the vocabulary used can be changed by selecting and reading sentences and words that have been created in advance according to the conversation level from the memory, or by writing sentences using the words to be changed as key food. This can also be achieved by generating.

The audio output unit 8 follows instructions from the audio conversation procedure control unit 7.
A voice synthesizer synthesizes the voice and outputs the synthesized voice to the speaker 2.

The voice input unit 9 recognizes the voice uttered by the learner input from the microphone, and sends the recognition result to the correct answer determination unit 10.
send to The speech input unit 9 uses a word speech recognition device or a continuous speech recognition device to recognize words or sentence speech that are keywords necessary for conversation practice. The characteristic parameters of the voice used for recognition include spectrum information of the input voice, amplitude information of the input voice and its temporal change sequence, and a temporal change sequence of the fundamental frequency.

The answer correctness determining unit 10 collects spectrum information and amplitude information regarding the progress of the conversation from the voice conversation procedure control unit 7, the model answers read out from the correct answer example storage unit 11 synchronized therewith, and the answers manually entered by the learner. The degree of similarity, the degree of similarity of recognition results, etc. are compared, and the results are sent to the voice procedure conversation control unit 7.
send to At the same time, the input answer is sent to the conversation level determining section 12.

The conversation level determination unit 12 evaluates the quality of pronunciation, accuracy of syntax,
The learner's conversation level is determined based on the accent position, pause length, duration, etc. To determine the conversation level, model answer examples stored in advance in the conversation level determination model answer example storage unit 13 are retrieved and compared. The conversation level determination section 12 sends information as to whether or not the conversation level needs to be changed to the main control section 6 as a determination result.

In the embodiment shown in FIG. 1, a microphone is used for voice input and a speaker is used for outputting synthesized voice, but the same effect can be obtained even if a telephone or the like is used for voice input/output.

FIG. 2 is a flowchart illustrating an example of a conversation level automatic change procedure according to the present invention.

FIG. 3 shows a flowchart of conversation practice when the embodiment of the present invention described in connection with FIG. 1 is operated.

As described above, according to the embodiments of the present invention, learners can automatically practice conversation according to their proficiency level without being aware of their own conversation proficiency level, and can easily see the effects of their practice. We have created a device that can do this.

[Effects of the Invention] As is clear from the above description, the present invention makes it possible to determine the conversation proficiency level of the learner as the conversation progresses, set the optimal conversation level, and practice at that level.
This has the excellent effect of enabling immediate and practical conversation practice according to the conversation situation.

[Brief explanation of the drawing]

FIG. 1 is a block diagram of an automatic conversation training device according to the present invention;
FIG. 2 is a flowchart showing an example of the automatic conversation level changing procedure according to the present invention, and FIG. 3 is a flowchart of conversation practice when the embodiment of the present invention described in FIG. 1 is operated.
FIG. 4 is a block diagram when a conventional tape recorder or videotape is used, and FIG. 5 is a typical block diagram of a pronunciation practice device. 1: Display section 2: Speaker 3: Screen display control section 4: Teaching material storage section 5: Conversation level change control section 6: Main control section 7: Voice conversation procedure control section 8: Voice output section 9: Voice input section 10: Answer Correct answer determination unit 11: Correct answer model example storage unit 12: Conversation level determination unit 13: Conversation level determination model answer example storage unit 21.28:
Storage section 22: Playback section 23: Speaker 24: Microphone 25: Analysis section 27: Verification section 28: Display section

Claims (1)

[Scope of Claims] A screen display unit and an audio output unit for outputting information from a teaching material storage unit for explaining the conversation situation in advance and providing conversation teaching materials and questions prior to conversation practice; a voice input unit that inputs and recognizes the learner's voice; an answer correctness determination unit that determines whether the recognition input obtained by the voice input unit is a correct answer to the question from the device; There is a storage section for correct answer model examples that stores model answers, and a section that extracts accent, intonation, correctness of pronunciation, certainty of syntax, etc. to judge the level of conversational proficiency of the learner. a conversation level determination unit that determines the conversation level; a model answer example storage unit that stores model answer examples that serve as standards for conversation level determination; and a conversation procedure control unit that controls the conversation procedure according to the conversation proficiency level of the learner. A conversation level change control section that changes the level when it becomes necessary to change the conversation level, changes the conversation situation, and displays and explains the situation again, and a screen change when changing the conversation level. It is equipped with a main control unit that instructs changes to the conversation procedure and controls the whole thing, and when practicing foreign language conversation, it automatically advances the conversation, sets the conversation proficiency level, and improves the learner's conversation. An automatic conversation training device characterized by determining the level and changing the content of the conversation to an optimal level according to the level.