KR20190029238A - Method for interpreting - Google Patents

Abstract

According to the present invention, an interpretation method comprises the steps of: executing a client program necessary for receiving an interpretation service from a server by a user terminal; connecting the user terminal and the server through a universal serial bus (UBS); granting an access right to the server; and providing the interpretation service to the user terminal by the server. According to the present invention, offline interpretation is possible using the server. In addition, illegal use of the server may be prevented through authentication of a user, the server, and the user terminal.

Description

{METHOD FOR INTERPRETING}

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an interpretation method, and more particularly to an interpretation method using a portable server without connection to the Internet.

With the development of transportation and communication means, human and material exchanges between countries have become active. Despite the expansion of human and material exchanges, the heterogeneous language between countries is acting as a barrier in communication.

To reduce the inconvenience caused by heterogeneous languages, the conversion between characters in a heterogeneous language is called translation. And the spoken language translation system refers to the conversion between the voices of different languages, which is the interpretation of broadcast news.

Especially, the inconvenience between the speakers of different languages at various conferences between countries is solved through simultaneous interpretation. In particular, the automatic interpretation is to convert the voice of the first language into the voice of the first language in both directions.

Simultaneous interpreting, which was the exclusive use of past simultaneous interpreters, has been made automatic interpreting by machine due to the development of technology of speech recognition, automatic translation and voice synthesis.

The automatic interpretation means a process and a technique of converting the utterance of the first language into a second language through processes such as speech recognition and automatic translation, outputting it as a subtitle, or reproducing the voice through a speaker after synthesizing the voice.

1 is an exemplary view of a translation system 10 according to the prior art using a translation server.

Referring to FIG. 1, according to the related art, in the case of the interpretation device 11 of the user terminal type including the simultaneous interpretation system 10, a wired or wireless communication network 14 for speech recognition and translation, The server 12 and the database 130 connected to the radiotelephone network are used. Therefore, there is a problem that the portable interpretation device performs the interpretation function in an environment not connected to the network, such as an airplane traveling in the sky or a foreign tourist destination do.

First, Prior Art 1 and Korean Patent No. 10-1626109 (May 25, 2016) disclose techniques for interpreting devices and methods.

The prior art 1 includes a voice input unit, a control unit, a communication unit, a display unit, and a user input unit for receiving operational input on previously translated sentences from the user.

Prior Art 2 and Korean Patent No. 10-1747874 (Jun. 19, 2017) disclose an automatic interpretation system.

The prior art 2 relates to an automatic interpretation system for communicating with portable devices such as a PC or a mobile phone, a smart phone, a PDA, a laptop, or the like, or used for a direct automatic interpretation terminal, A wearable automatic interpretation input / output device for transmitting a microphone signal, a bone-cord microphone signal and a gesture signal of a speaking person through a network and outputting an interpretation result signal received through a network; And a voice recognition section for detecting voice data sections in the voice recognition microphone signal by using a bone-cord microphone signal or a gesture signal transmitted through the network from the wearable automatic interpretation input / output device and performing voice recognition and interpretation of voice data in the detected section And a server for transmitting an interpretation result signal to the wearable automatic interpretation input / output apparatus via a network.

Prior Art 3 and Korean Patent No. 10-1589433 (Jan. 22, 2016) disclose a simultaneous interpretation system.

In the simultaneous interpretation system described in the prior art 3, at least two or more headsets for inputting and outputting a voice and an interpreter voice language output from the headset are input, and an interpreter voice language in which the interpreter voice language is interpreted is designated as a designated headset The simultaneous interpretation system using short-distance communication between users via one portable terminal enables simultaneous interpretation, thereby enabling more efficient and free conversation.

The prior art 1 includes a communication unit that transmits a sentence to be translated in the first language to the translation server and receives a translated sentence of the second language from the translation server. Based on this, .

In addition, the prior art 2 receives a user's voice signal provided from the voice microphone, a user's golfer signal provided from a bone-cord microphone, and a user's action (gesture) detection signal provided from a motion sensor, And transmitting the voice recognition result information transmitted from the first server to the second to n-th servers or outputting the interpretation result information transmitted from the second to n-th servers, Based on this, it can be seen that the server performs speech recognition and interpretation on-line.

The control unit of the prior art 3 acquires the voice of the second language converted based on the voice of the first language by using an interpretation server for converting the voice of the first language into voice of the second language, It can be seen that the online interpretation server is used.

The interpreter apparatus and method according to the embodiment of the present invention relate to a technique that enables simultaneous interpretation without using an interpretation server on a network in a situation where an internet environment such as an airplane in flight or a foreign local travel destination is not established, The present invention is intended to solve the above problems as a technique different from the prior art that has been examined.

It is an object of the present invention to provide an interpretation method using a portable server, which is created to solve the above problems.

Another object of the present invention is to provide an interpretation method capable of interpretation in an environment where a remote network environment is not established.

It is another object of the present invention to provide an interpretation apparatus and method which can quickly output a reliable result by using a portable server including a memory of a high capacity which stores a DB relating to speech recognition and translation.

An interpretation method according to an embodiment of the present invention includes: executing a client program necessary for a user terminal to receive an interpretation service from a server; Connecting the user terminal to the server through a universal serial bus (USB); Granting an access right to the server; And providing the interpretation service to the user terminal by the server.

Here, the interpretation method may further include installing the client program in the user terminal.

Here, the interpretation method may further comprise setting a menu of the interpretation service.

Herein, the step of granting the access right includes a step of receiving user registration and authentication.

Here, the step of granting the access right may further include receiving the server registration and authentication.

Here, the step of granting the access right may include registering and authenticating the user terminal.

Herein, the user terminal can be registered in a plurality of at least one within a limited range.

Here, the registration and authentication of the user, the server, and the user terminal can be performed online, and the authentication of the server and the user terminal can be performed by the client program.

Here, the registration and authentication of the server can be performed for each service that the server can provide.

Here, the service may be added for a fee or free of charge.

Here, authentication of the server uses a unique identification factor stored in a write-protected hardware chip included in the server.

Here, the authentication of the server and the user terminal is performed by using a match between the first identification factor stored in the server and the second identification factor stored in the user terminal.

Herein, the registration and authentication of the user terminal uses a MAC address (Media Access Control Address) of the user terminal.

Here, the server includes a speech recognition engine, a translation engine, a speech recognition DB, and a translation DB.

Here, the speech recognition DB is a DB constructed by learning speech by various utterances using a deep learning algorithm and reducing or enlarging the recognition range according to the frequency of uttered contents.

Here, the translation DB is a DB constructed by learning various translation examples using an algorithm of deep learning, expanding colloquial expressions according to the frequency of translation examples, and reducing the expression of the written language.

Here, the speech recognition engine or the translation engine uses a low-capacity speech recognition DB or a translation DB compared to the DB in which the frequency is not taken into consideration.

Here, the step of installing the client program is characterized by using a client program to be installed stored in the server.

BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is an illustration of an interpretation system according to prior art using a translation server.
2 is an exemplary diagram of a server and a user terminal on which an interpretation method according to an embodiment of the present invention is performed.
3 is a block diagram of a server in accordance with an embodiment of the present invention.
4 is a block diagram of a user terminal in accordance with an embodiment of the present invention.
5 is a flowchart of an interpretation method according to an embodiment of the present invention.
6 is an exemplary diagram for online authentication according to an embodiment of the present invention.
Figure 7 is an illustration of an offline authentication in accordance with an embodiment of the present invention.

Hereinafter, preferred embodiments of the interpretation method of the present invention will be described in detail with reference to the accompanying drawings. Like reference symbols in the drawings denote like elements. It is also to be understood that the structural and functional descriptions that are specific to embodiments of the present invention are presented for purposes of describing embodiments of the present invention only and that, unless otherwise defined, all technical and scientific terms used herein, including technical and scientific terms, The terms have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as ideal or overly formal in the sense of the art unless explicitly defined herein .

Hereinafter, an interpretation method according to an embodiment of the present invention will be described.

2 is an exemplary diagram of a server and a user terminal on which an interpretation method according to an embodiment of the present invention is performed.

Referring to FIG. 2, an interpretation method according to an embodiment of the present invention is performed through the server 100 and a user terminal connected thereto.

The server 100 stores various kinds of digital data necessary for providing an interpretation service as a storage module.

3 is a block diagram of a server in accordance with an embodiment of the present invention.

3, the server 100 includes a speech recognition engine 110, a translation engine 120, a speech recognition DB 130, a translation DB 140, a TTS engine 150, a client program 160, A file 170 and a certificate 180.

Specifically, the server 100 includes a USB terminal and a main body in the form of a memory module, the main body includes a housing, and a circuit and a memory chip are mounted on the PCB substrate. The memory chip stores the components of the voice recognition engine 110 or the certificate 180.

The server 100 shown in FIG. 3 corresponds to a portable server in the form of a memory module. The server 100 provides an interpreter service to a client corresponding to the user terminal 200, which will be described later, and includes an engine and a core DB necessary for interpreting, and can be referred to as an interpreter 100. [

The speech recognition engine 110 records the voice of a speaking person and performs voice recognition using the recorded data. The speech recognition engine 110 automatically recognizes the speech signal from the mouth of the speaker and converts the speech signal into a character string. Another name for the speech recognition engine is ASR (Automatic Speech Recognition), Voice Recognition or STT (Speech-to-Text).

The speech recognition engine 110 may be based on a probability statistic. That is, the speech recognition engine 110 uses a probability model based on an acoustic model (AM) and a language model (LM) used in speech recognition. And the key algorithm, HMM (Hidden Markov Model), can also be based on probability statistics. The above models are examples and do not limit the present invention.

GMM (Gaussian Mixture Model) can be used as an acoustic model, and N-gram can be used as a language model. Furthermore, it is also desirable to use a Deep Neural Network (DNN), which is one of the Deep Learning architectures instead of the GMM. In order to improve speech recognition performance, a good speech model and a language model are set, and the set models can be learned by a deep learning algorithm. It is desirable that the learning DB necessary for learning includes a spoken and dialogue voice and a language DB.

The speech recognition DB 130 according to an exemplary embodiment of the present invention is a DB constructed by learning speech by various utterances using an algorithm of deep learning and reducing or enlarging the recognition range according to the frequency of speech contents . That is, in order to recognize the contents of the utterance having a high frequency, it is necessary to increase the DB amount relatively and reduce the amount of DB to recognize the contents of the utterance with a low frequency.

In order to obtain a high-quality speech recognition rate, the larger the amount of the speech recognition DB is, the more advantageous it is, but the time delay and the overload are problematic. According to the above method, it is possible to construct a low-capacity DB by reducing the total amount of the DB.

Also in the translation DB, as in the above method, various translation examples can be learned by using the deep learning algorithm, a colloquial expression can be expanded according to the frequency of translation examples, and a DB can be constructed by reducing the language expression.

Therefore, the speech recognition engine 110 and the translation engine 120 according to the present invention can use a low-capacity speech recognition DB or a translation DB compared to the DB constructed without considering the frequency.

The translation engine 120 translates the output text into characters of the target language when the speech of the speaking person uttered in the source language recognized by the speech recognition engine 110 is output as text. The interpretation apparatus 100 according to an embodiment of the present invention is characterized by including the translation engine 120 in addition to the speech recognition engine 110. [

The translation method performed by the translation engine 120 includes at least one of a rule-based method, a corpus-based method, and a neural machine translation (NMT).

Rules-based methods are divided into direct translation, indirect conversion, and intermediate language depending on the depth of analysis.

A corpus-based method is an example-based method and a statistical-based method.

Stochastic Machine Translation (SMT) technology is a technique of translating sentences by learning model parameters from bilingual corpus through statistical analysis. When developing a grammar or semantic representation, we make a model for translation from the corpus of language pairs that we want to translate rather than by hand. Therefore, if we can secure only a corpus, we can expand the language relatively easily.

A disadvantage of statistical-based automatic translation technology is that large bilingual corpus is required and there is no common semantic representation linking multiple languages.

Neural Machine Translation (NMT) is a technique to overcome these drawbacks.

SMT is a method of translating sentences based on a statistical model after breaking a word or a group of words into phrases. The key is to model statistical translation rules based on massive learning data.

On the other hand, NMT translates sentences as a whole through artificial intelligence (AI). This is because the artificial neural network converts the sentence information into a vector (coordinate value) which means a specific point in the virtual space.

For example, the word 'person' is' [a, b, c, ... , x, z] '. Since the vector contains all the information such as words, phrases, and word order, it is possible to translate sentence units that understand the context. Artificial neural networks place sentences with similar meanings close to each other.

Higher order vectors are utilized in the NMT technique. The artificial neural network is learned by using the learning data consisting of the sentence of the source language and the sentence of the destination language, and the learned artificial neural network recognizes the sentence information as a vector.

The TTS engine 150 outputs the synthesized voice corresponding to the voice of the speaker according to the translation of the translation engine 110. [ To this end, the TTS engine 150 converts the text, which is the speech recognition result, into TTS data, reproduces the TTS data, and outputs the result as a speaker, a headset, or an earpiece.

Text-to-speech (TTS) is speech synthesis and is also called Voice Synthesis. As a method of voice synthesis, a music composition method can be used. In the combination method, sentences are extracted from the score database according to the analysis and analysis results. The synthesized sounds of the various candidates are generated, and the most suitable one is adopted in consideration of the rhythm and smoothness. Further, the sound spectrum of the speaker's voice is used to determine the tone color of the speaker, and the synthesized sound is post-processed so as to match the tone color, so that a synthesized sound close to the tone of the original speaker can be output. In addition, the emotion of the speaker may be perceived, and the perceived emotion may be displayed in the synthesized sound.

Each of the speech recognition DB 130 and the translation DB 140 is used as a source of the speech recognition engine 110 and the translation engine 120.

The client program 160 refers to a file to be installed in the user terminal 200 connected to the server 100 and performing an interpretation service. Also, the user terminal 200 may access the file server on-line and download and use the client program.

The system file 170 is another file that is necessary for connection between the server 100 and the user terminal 200 and provision of an interpretation service.

The certificate 180 may be issued by the authentication server 300 for authentication of the server 100 or may be stored in memory at the manufacturing stage of the server 100. [ It is also common that the server 100 is assigned a product number assigned to the mass produced product.

Next, the user terminal 200 connected to the server 100 will be described. The following description is exemplary, and the configuration and function of the server 100 are not limited by the following description.

4 is a block diagram of a user terminal in accordance with an embodiment of the present invention.

4, a user terminal 200 connected to a server 100 according to an embodiment of the present invention includes a communication unit 210, a display 220, a storage unit 230, an input unit 240, A controller 250, a power supply 260, and a controller 270.

Various embodiments of the user terminal 200 may include a cellular telephone, a smartphone having wireless communication capabilities, a personal digital assistant (PDA) having wireless communication capabilities, a wireless modem, a portable computer having wireless communication capabilities, a digital Gaming devices with wireless communication, music storage and playback appliances with wireless communication capabilities, Internet appliances capable of wireless Internet access and browsing, as well as portable devices incorporating such combinations of functions Units or terminals, but is not limited thereto.

The communication unit 210 may include a communication module corresponding to various communication networks of the communication network 14, for example, a Bluetooth module, a WiFi module, an Ethernet, a USB module, and a cellular wireless communication module. It is most preferable to include a wired communication unit such as a USB module and a short-range communication module such as a Bluetooth module, a Zigbee module, and an NFC module.

The display 220 corresponds to a device for displaying a screen composed of pixels such as an LCD display and an LED display.

The storage unit 230 may store a client program required to provide an interpretation service in connection with the server 100. [ The storage unit 230 includes a volatile RAM, a non-volatile ROM, and a flash memory, and stores various digital files according to the functions thereof. In particular, the TTS engine 150 may not be stored on the server 100 side but may be stored on the user terminal 200 side.

The input unit 240 includes a keyboard, a touch screen, and a mouse for setting various parameters.

The output unit 250 includes a speaker, a headset, and an earset. Especially, the headset and earset formed integrally with the microphone have useful functionality in hands-free simultaneous interpretation.

The power supply unit 260 includes a power source and a charge / discharge device for charging and / or discharging the power source. A battery can be used as a power source. The battery is charged and discharged by the charge / discharge device, and the discharged power acts as an energy source for driving the user terminal 200.

The control unit 270 may be implemented as a CPU (Central Processing Unit) corresponding to a central processing unit in terms of hardware. Specifically, the control unit 270 may be connected to the server 100 and stored in a storage unit 230 Is a concept of integrating the loaded client program and the CPU operating in this state.

The control unit 270 can access the server 100 after being authorized according to the authentication of the user, the user terminal 200, and the server 100.

Hereinafter, an interpretation method according to an embodiment of the present invention will be described.

The interpretation method according to an embodiment of the present invention is performed by the server 100 and the user terminal 200 according to the provision of core data of the server 100. [

5 is a flowchart of an interpretation method according to an embodiment of the present invention.

Referring to FIG. 5, the interpretation method may include: installing the client program in the user terminal (S110); A step (S120) in which a client program necessary for the user terminal to receive the interpretation service from the server is executed; Connecting the server 100 to the user terminal 200 through a universal serial bus (USB) (S130); Setting a menu of the interpretation service (S140); A step (S150) of granting an access right to the server; And the server providing the interpretation service to the user terminal (S160).

Here, the step S130 may be performed before the step S110 or the step S120. If the client program is installed in the user terminal 200, step S140 may be performed after step S150 if it comes after step S120.

Hereinafter, the steps of authorizing access to the server 100 will be described in detail.

6 is an exemplary diagram for online authentication according to an embodiment of the present invention.

Referring to FIG. 6, a step of granting an access right to a server (S150) includes a user authentication process after user registration, a server authentication process after server registration, and a user terminal authentication process after registering the user terminal 200 . The certifications are available online. That is, in a state where the server 100 is connected to the user terminal 200, the user terminal 200 and the authentication server 300 are connected through the communication network 14, and authentication can be performed for each object in the online state .

User registration and authentication on-line can be performed by login after registration of the user's ID and password.

Registration and authentication of the server 100 on-line is registration and authentication of the server 100, which is a product purchased by the user.

Here, the registration and authentication of the server 100 can be performed for each service that the server 100 can provide. For example, if the server 100 includes an engine and DB (first service) capable of interpreting between Korean and English, and an engine and DB (second service) capable of interpreting between Korean and Japanese, The first service and the second service must be separately registered and authenticated. Here, the service is characterized in that it can be further added with a fee or free of charge.

Authentication of the server 100 is characterized by using a unique identification factor stored in a write-protected hardware chip included in the server 100. [ Specifically, the memory chip mounted on the PCB 100 included in the server 100 is write-protected. In the manufacturing stage of the server 100, the unique number of the server 100 or a corresponding unique Authentication with respect to the server 100 can be performed by having the identification factor stored and the stored identification factor being read by the authentication server 300. [

Registration and authentication of the user terminal 200 on-line means that the server 100 is connected to register and authenticate the user terminal 200 to provide the interpretation service. This is to prevent the server 100 product from being copied and used after it is purchased by the user.

Here, the registration and authentication of the user terminal 200 is characterized by using the MAC address (Media Access Control Address) of the user terminal 200. The MAC address is a unique value of an object having IP on the network. The authentication server 300 can identify the type and model of the user terminal 200 using the MAC address.

In addition, a plurality of user terminals 200 can be registered in at least one limited range. For example, the user can connect the server 100 to each of the three devices by registering the PC in the home connected to the network, the PC in the workplace, and the user terminal 200, which is a wireless communication device.

The authentication of the server 100 and the user terminal 200 may be performed by using the first identification factor stored in the server 100 and the second identification factor stored in the user terminal 200, 100 and the user terminal 200 at the same time.

Here, the first identification factor is the identification factor stored in the manufacturing step as described above, and the second identification factor is the identification factor given from the authentication server 300 at the time of online registration of the user terminal 200, It is created to match.

Figure 7 is an illustration of an offline authentication in accordance with an embodiment of the present invention.

Referring to FIG. 7, the authentication of the server 100 and the user terminal 200 may be performed by the client program in an offline manner.

One of the features of the present invention is an off-line interpretation method. When only the server 100 and the user terminal 200 are connected offline and the user terminal 200 is not connected to the external network, the interpretation method can be configured to enable offline authentication.

The control unit 270 may perform authentication of the server 100 connected to the user terminal 200 and authentication of the user while the client program installed in the user terminal 20 is loaded in the storage unit 230. [

Specifically, the user authentication is solved by login, and authentication for the server 100 can be performed using the above-described identifier or using a match of the first identifier and the second identifier.

On the other hand, in the step of installing the client program, the client program to be installed, which is stored in the server 100, can be used. When the server 100 is connected to the user terminal 200, the client program may be automatically installed.

In general, the interpretation method according to an embodiment of the present invention is a method for performing interpretation using the portable server 100 in a situation where a wireless communication environment is not established, and includes a user, a user terminal 200 and a server 100 The method includes a method for preventing unauthorized use of the server 100 by granting authority to a legitimate user through multi-angle authentication.

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 embodiments, but, on the contrary, I will understand the point. Accordingly, the technical scope of the present invention should be determined by the following claims.

11: user terminal 12: interpretation server
13: Database 14: Network
100: server 110: voice recognition module
120: translation module 130: speech recognition DB
140: translation DB 150: TTS engine
160: Client program 170: System file
180: certificate 200: user terminal
210: communication unit 220:
230: storage unit 240: input unit
250: output unit 260: power supply unit
270: control unit 300: authentication server

Claims (18)

Executing a client program necessary for a user terminal to receive an interpretation service from a server;
Connecting the user terminal to the server through a universal serial bus (USB);
Granting an access right to the server; And
And the server providing an interpretation service to the user terminal. The method according to claim 1,
Further comprising the step of installing the client program in the user terminal. The method of claim 2,
Further comprising setting a menu of the interpretation service. The method according to claim 1,
Wherein the granting of the access right comprises:
And receiving user registration and authentication. The method of claim 4,
Wherein the granting of the access right comprises:
Further comprising receiving the server registration and authentication. The method of claim 5,
Wherein the granting of the access right comprises:
Further comprising registering and authenticating the user terminal. The method of claim 6,
Wherein the user terminal can register a plurality of user terminals in a limited range. The method of claim 6,
The registration and authentication of the user, the server, and the user terminal can be performed online,
Wherein the authentication of the server and the user terminal is also capable of offline authentication by the client program. The method of claim 5,
The registration and authentication of the server includes:
Wherein the server is provided for each service that can be provided by the server. The method of claim 9,
Wherein said service can be added for a fee or free of charge. The method of claim 8,
The authentication of the server,
Characterized by using a unique identification factor stored in a write-protected hardware chip included in the server. The method of claim 8,
The authentication of the server and the user terminal,
Wherein whether the first identification factor stored in the server and the second identification factor stored in the user terminal match each other is used. The method of claim 8,
Wherein the registration and authentication of the user terminal comprises:
Wherein a MAC address (Media Access Control Address) of the user terminal is used. The method according to claim 1,
The server comprises:
A speech recognition engine, a translation engine, a speech recognition DB, and a translation DB. 15. The method of claim 14,
The speech recognition DB includes:
Wherein the DB is constructed by learning speech due to various utterances using an algorithm of deep learning and reducing or enlarging the recognition range according to the frequency of utterance contents. 15. The method of claim 14,
The translation DB,
Wherein the DB is constructed by learning various translation examples using an algorithm of deep learning, expanding colloquial expressions according to the frequency of translation examples, and reducing the expression of the written language. 16. The method according to claim 15 or 16,
The speech recognition engine or translation engine,
Wherein a voice recognition DB or a translation DB of a lower capacity than the DB in which the frequency is not taken into account is used. The method according to claim 1,
Wherein the installing the client program comprises:
And the client program to be installed, which is stored in the server, is used.

Images