KR101814431B1 - Translation system and method for translation syncronization - Google Patents

Abstract

The present invention relates to a translation service system and method for synchronizing audio files, and more particularly, to a translation service system for synchronizing audio files, and more particularly, If the updated audio file is compared with the stored audio file, the audio file is synchronized to the other terminal so that the translation and audio file requested by the user can be repeatedly checked through the user terminal, Can be used regardless of the terminal used by the user.

Description

TECHNICAL FIELD [0001] The present invention relates to a translation service system and a method for synchronizing audio files,

The present invention relates to a translation service system and method for synchronizing audio files, and more particularly, to a translation service system for synchronizing audio files, and more particularly, If the updated audio file is compared with the stored audio file, the audio file is synchronized to the other terminal so that the translation and audio file requested by the user can be repeatedly checked through the user terminal, To a translation service system for audio file synchronization and a method thereof, which can be used regardless of a terminal used by a user.

Currently, major portal sites such as "Google", "Microsoft", and "Yahoo" provide an automatic translation service that automatically detects and translates the user's original language. As the accuracy of the translation increases, the user's interest and usage are increasing.

The users can easily grasp the contents of the translated texts in a language desired by the user through an automatic translation service, such as sentences or web pages in a foreign language. When the portal site outputs the translated sentence to the user by using the TTS (Text To Speech) function, the user can hear the translated sentence by voice.

Some portal sites, when the user inputs a Chinese sentence and then request to execute a sentence analysis, divides the Chinese sentence into words and displays a pronunciation symbol and a word meaning thereof. Here, the user can speak Chinese sentences separated by Chinese words through the TTS function.

However, users can listen to the translated text through the automatic translation services currently provided, but can not store the audio file in their own computer or terminal. Conventional automatic translation services provide sentence translation and a TTS function for it, but provide only a function of outputting them through a device such as a computer currently used by a user at one time. In addition, the automatic translation service does not provide a function to transmit an audio file of a translated sentence or word to another device and to store the transmitted audio file.

Therefore, users can not repeatedly hear the translated speech of a foreign language sentence for the purpose of learning or the like. Further, the user can not repeatedly hear the voice of the translated text in the device other than the device that requested the translation. That is, even if the user is a translation translated through an automatic translation service, in order to listen to the same on another device, the user has to input the same original text again and request the translation process and the voice output process again to execute the automatic translation service .

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above problems, and it is an object of the present invention to provide a method and apparatus for generating a translation for a original text and an audio file for the translation and transmitting the generated audio file to a user terminal, It is possible to repeatedly confirm the translation and the audio file requested by the user through the user terminal and to synchronize the translation and the audio file with the terminal used by the user And to provide a translation service system and method thereof for synchronizing audio files.

To this end, the system according to the first aspect of the present invention comprises: a first user terminal for transmitting a text to be translated, receiving a translation and an audio file, and requesting a voice synthesis and an audio file synchronization for the translation; A second user terminal for receiving and storing an audio file in response to an audio file synchronization request of the first user terminal, and outputting the stored audio file; Generating a translation from the original text received from the first user terminal, generating an audio file through speech synthesis for a word or a sentence in the generated translation according to the speech synthesis request of the first user terminal, An audio file stored in the second user terminal is compared with an audio file stored in the second user terminal according to a request to synchronize the audio file of the first user terminal, and the updated audio file and the translated text are transmitted to the second user terminal And a translation service device for synchronizing the translation service.

According to a second aspect of the present invention, there is provided an apparatus comprising: a communication interface for receiving a text from a first user terminal and transmitting a translation and an audio file to the first user terminal and the second user terminal; Extracting a sentence structure, word parts of speech and semantic information from a source text received through the communication interface unit through a natural language processing technique such as morphological analysis, syntax analysis, and semantic analysis based on user translation setting information, A translation unit for generating a translation and returning the translation to the first user terminal; An audio file generation unit for analyzing a text of a translated text with respect to the generated translated text according to a speech synthesis request of the first user terminal, generating an audio file through speech synthesis, and returning the generated audio file to the first user terminal; And comparing the audio file stored in the second user terminal with the stored audio file in response to an audio file synchronization request of the first user terminal and storing the updated audio file and the translated text in the second user terminal, And an audio file synchronization unit for synchronizing the audio file with the terminal.

The apparatus includes a user DB for storing user translation setting information received from the first user terminal or storing preset user translation setting information; A translation DB for storing the generated translation; And an audio DB for matching and storing the audio file of the stored translation with a word or a sentence of the corresponding translation.

The audio file generation unit generates an audio file corresponding to a word or a sentence in the generated translation according to a speech synthesis request for a word or a sentence in the generated translation.

The audio file generation unit generates an audio file according to a speech synthesis request for a word or a sentence in the generated translation and generates audio file path information for downloading the generated audio file.

The audio file synchronization unit may transmit an audio file for a word or a sentence in the generated translation to the second user terminal or transmit audio file path information for downloading.

The audio file path information is audio file path information of each word or sentence of the generated translation, or TTS (Text-To-Speech) path information for voiceing each word and sentences.

According to a third aspect of the present invention, there is provided a method for extracting a sentence structure from a first sentence received from a first user terminal through a natural language processing technique such as morphological analysis, syntax analysis, And a translation step of extracting semantic information, generating a translation using the extracted result, and returning the translation to the first user terminal; An audio file generation step of analyzing the text of the generated translation according to a speech synthesis request of the first user terminal, generating an audio file through speech synthesis, and returning the audio file to the first user terminal; Comparing the audio file stored in the second user terminal with the stored audio file in response to the audio file synchronization request of the first user terminal; And an audio file synchronization step of synchronizing the updated audio file and the translation with the second user terminal as a result of the comparison.

The audio file generation step generates an audio file corresponding to a word or a sentence in the generated translation according to a speech synthesis request for a word or a sentence in the generated translation.

The audio file generation step generates an audio file according to a speech synthesis request for a word or a sentence in the generated translation and generates audio file path information for downloading the generated audio file.

The audio file synchronization step transmits the audio file for the word or sentence in the generated translation to the second user terminal or transmits the path information of the audio file for downloading.

The audio file path information is audio file path information of each word or sentence of the generated translation, or TTS (Text-To-Speech) path information for voiceing each word and sentences.

In the present invention, a translation for the original text and an audio file for the translation are generated and transmitted to the user terminal. When the generated audio file is compared with the audio file stored in another user terminal, By synchronizing with the terminal, the translation and audio file requested by the user can be repeatedly checked through the user terminal, and the synchronized terminal can use the translation and the audio file irrespective of the terminal used by the user.

For example, the present invention provides an audio output and audio file storage function for a word and a sentence of a translation, and provides an audio file sync function for a mobile device such as a smart phone, In addition to the function of outputting a one-time output from the user, the user can repeatedly listen to audio files through a smart phone. Accordingly, the user can listen to the audio of the words and sentences of the translated text and store the audio file in the smart phone, so that the translated text and the audio service can be used at any time.

Furthermore, the present invention has the effect of assisting learning of a foreign language such as Chinese which requires repeated speech learning due to pronunciation and strong tongue.

1 is a configuration diagram of an embodiment of a translation service system for audio file synchronization according to the present invention;
2 is a detailed block diagram of an embodiment of a translation service apparatus for synchronizing audio files according to the present invention;
3 is a flowchart of an embodiment of a translation service method for synchronizing audio files according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The configuration of the present invention and the operation and effect thereof will be clearly understood through the following detailed description. Before describing the present invention in detail, the same components are denoted by the same reference symbols as possible even if they are displayed on different drawings. In the case where it is judged that the gist of the present invention may be blurred to a known configuration, do.

1 is a block diagram of an embodiment of a translation service system for synchronizing audio files according to the present invention.

1, a translation service system 10 for audio file synchronization includes a translation service apparatus 100, a first user terminal 101 and a second user terminal 102. [

The first user terminal 101 transmits the original text to be translated to the translation service apparatus 100 to request the original text translation. The first user terminal 101 can access the web page of the translation service apparatus 100 through the Internet browser, and can input the original text or transmit the original text file. Here, the first user terminal 101 may be a computer equipped with a web browser or various mobile devices such as a smart phone. The web browser may be a browser application installed on a computer or a mobile application on a smart phone. On the other hand, the original text includes a Web site page, a text file, a PDF (Portable Document Format) file, a Hangul (HWP) file, a MS office file, etc., which are made up of Hypertext Markup Language (HTML) and Extensible Markup Language ≪ / RTI >

The user sets user translation setting information for translation such as a translation language pair, a user word list, and a translation result format before the translation request for the original text through the first user terminal 101. The user translation setting information set by the user may be stored in the first user terminal 101 or in the translation service apparatus 100. Through the user translation setting information, the user can define the type of the translated text and the translation text generation method displayed on the translation result through the translation result format or the like.

When a translation is transmitted from the translation service apparatus 100, the first user terminal 101 receives the translation, requests the speech synthesis for the translation, and receives the audio file from the translation service apparatus 100. Then, the first user terminal 101 requests the translation service apparatus 100 to synchronize the audio file with the second user terminal 102.

On the other hand, the translation service apparatus 100 generates a translation from the original text received from the first user terminal 101 and returns it to the first user terminal 101.

The translation service apparatus 100 generates an audio file through speech synthesis in response to a speech synthesis request of the first user terminal 101 with respect to a word or a sentence in the generated translation. The translation service apparatus 100 stores the generated audio file in the audio DB 253.

The translation service apparatus 100 compares the audio file stored in the second user terminal 102 with the audio file stored in the audio DB 253 in response to the audio file synchronization request of the first user terminal 101, Transmits the translation to the second user terminal 102 and synchronizes them. Herein, the audio file synchronization is performed by keeping the audio file received by the first user terminal 101 and the audio file stored in the second user terminal 102 in the same state so that the first user terminal 101 and the second user terminal 102, To synchronize audio files between. Thereby, the user can listen to the audio file heard through the first user terminal 101 at the second user terminal 102 as well. The translation service apparatus 100 confirms the updated audio file through the list of the audio files stored in the second user terminal 102. [ The translation service apparatus 100 may check the audio file stored in the second user terminal 102 before transferring the audio file to the second user terminal 102, And the updated audio file can be confirmed.

On the other hand, the second user terminal 102 receives and stores the audio file from the translation service apparatus 100 according to the audio file synchronization request of the first user terminal 101. The second user terminal 102 outputs the stored audio file at the request of the user. Here, the second user terminal 102 may be a mobile device, such as a smart phone, that can execute an audio file stored when the user desires to listen to the audio file while the user is carrying it.

2 is a detailed configuration diagram of an embodiment of a translation service apparatus for synchronizing audio files according to the present invention.

2, the translation service apparatus 100 includes a communication interface unit 210, a translation unit 220, an audio file generation unit 230, an audio file synchronization unit 240, and a data storage unit 250, . Here, the data storage unit 250 includes a user DB 251, a translation DB 252, and an audio DB 253.

The communication interface unit 210 performs a communication interface function to transmit and receive data to and from the first and second user terminals 101 and 102 through a communication network. That is, the communication interface unit 210 receives the original text from the first user terminal 101, and transmits the translated text and the audio file to the first and second user terminals 101 and 102.

The translating unit 220 translates the sentence structure, the part-of-speech, and the meaning of the word, based on the user translation setting information, from the original text received through the communication interface unit 210 through a natural language processing technique such as morphological analysis, Extracts the information, generates a translation using the extracted result, and returns it to the first user terminal 101.

Specifically, the translation unit 220 includes a translation engine, analyzes the original text requested for translation through the translation engine, and analyzes the morpheme. The translating unit 220 sees the words of the original text in the morphological analysis process and separates the morpheme. This morphological analysis process is becoming more and more automated due to the development of computer, and accuracy is increasing. The morphological analysis process is the most basic process of natural language processing and can be seen as a process that must be preceded in order to proceed to the analysis of syntax or semantic analysis. Here, natural language refers to a language used by humans, and natural language processing refers to a field where computers can understand such natural language. The translator 220 performs machine translation using basic techniques such as morphological analysis, syntax analysis, semantic analysis, and phonetic analysis.

Then, the translation unit 220 performs sentence analysis and word sense extraction through syntax analysis. The translating unit 220 decomposes the sentence into components constituting a sentence in the parsing process and analyzes the hierarchical relationship between them to determine the structure of the sentence.

Then, the translating unit 220 interprets the sentence based on the meaning of the sentence in the semantic analysis process, which is one of the natural language understanding techniques, and extracts the parts of speech and semantic information for each word. Here, the translating unit 220 uses various semantic analysis methods and various types of grammar. These semantic analysis methods and various types of grammar refer to a kind of formal system that consists of rules that show how sentences are constructed.

Then, the translating unit 220 generates a translated text using the extracted result. The translation unit 220 generates a translation by performing translation such as word translation and position replacement in the translation target language.

Here, the translating unit 220 can generate the translation using the translation pair result sentence included in the user translation setting information set by the user and the electronic dictionary route information for the word meaning, word part part, pronunciation part, and word.

The audio file generation unit 230 analyzes the text of the translated text according to the speech synthesis request of the first user terminal 101 with respect to the translated text generated by the translation unit 220, generates an audio file through speech synthesis, And returns it to the terminal 101. The audio file generation unit 230 generates an audio file corresponding to a word or a sentence in the translation according to a speech synthesis request for a word or a sentence in the translation. The audio file generation unit 230 may generate the audio file path information when the capacity of the audio file is large. Then, the first user terminal 101 accesses the audio file path information and receives the audio-synthesized audio file through the path.

The audio file synchronizer 240 stores the audio file generated by the audio file generator 230 in the audio DB 253. In response to the audio file synchronization request of the first user terminal 101, the audio file synchronization unit 240 compares the audio file stored in the second user terminal 102 with the audio file stored in the audio DB 253, And synchronizes the audio file and the translation with the second user terminal 102. The audio file synchronization unit 240 may transmit an audio file for a word or a sentence in the translation to the second user terminal 102 or may transmit the audio file path information for downloading. Here, the audio file path information may be path information for downloading the audio files of the respective words, or may be text-to-speech (TTS) path information for voicing each word and sentences.

The user DB 251 of the data storage unit 250 stores user translation setting information received from the first user terminal 101 or stores predetermined user translation setting information. The user DB 251 stores user translation setting information for the user when the user sets various translation environments related to the translation service. The translating unit 220 reflects the user translation setting information stored in the user DB 251 in the translation result.

The translation DB 252 of the data storage unit 250 stores the generated translation. The audio DB 253 of the data storage unit 250 matches and stores the audio file corresponding to the word or sentence of the translation stored in the translation DB 252. [

3 is a flowchart of an embodiment of a translation service method for synchronizing audio files according to the present invention.

When the user inputs the original text through the browser of the computer, the first user terminal 101 transmits the original text input by the user to the translation service apparatus 100 to request translation (S302). If the user translation setting information set by the user is stored in the first user terminal 101, the first user terminal 101 transmits the user translation setting information to the translation service apparatus 100 as shown in the original text. On the other hand, if the user translation setting information set by the user is stored in the translation service apparatus 100, the translation service apparatus 100 can translate the original text using the previously stored user translation setting information.

The translation service apparatus 100 extracts the sentence structure, word-by-word parts, and semantic information through natural language processing techniques such as morphological analysis, syntax analysis, and semantic analysis on the basis of S304. Specifically, the translator 220 separates the morpheme by referring to the word of the original text in the morpheme analysis process. The translating unit 220 decomposes the sentence into constituent elements that are sentences in the parsing process and analyzes the hierarchical relationship between them to determine the structure of the sentence. Then, the translator 220 analyzes the sentence based on the meaning of the sentence, and extracts the part-of-speech and the semantic information for each word.

The translation service apparatus 100 generates a translation using the analyzed and extracted results based on the user translation setting information (S306). Here, the translation may include translated sentences, the original word meaning of translated words, phonetic symbols, parts of speech information, path information linked to dictionary services, path information linked to pronunciation services, and the like. The path information linked to the pronunciation service may be path information for the audio file of each word. Also, it may be TTS path information for voicing each word and sentences.

The translation service apparatus 100 transmits the generated translation to the first user terminal 101, and returns the translated request to the user (S308).

The first user terminal 101 confirms the translation result returned by the user and requests the translation service apparatus 100 to synthesize the word or sentence in the translated translation by pressing the pronunciation service menu (S310). The first user terminal 101 can hear an audio file for a word or a sentence through a speech synthesis request.

The translation service apparatus 100 analyzes the text of the translated text according to the speech synthesis request of the first user terminal 101 and generates an audio file through speech synthesis (S312).

The translation service apparatus 100 transmits the generated audio file to the first user terminal 101 and returns the audio synthesis request to the user (S314). Here, the first user terminal 101 may store a word or sentence audio file in a memory provided when the user presses the audio file storage menu.

The first user terminal 101 outputs the received audio file to the user (S316).

When the user requests synchronization of the translation result received by the first user terminal 101 to the second user terminal 101 which is another device by pressing the translation result synchronization menu, the first user terminal 101 transmits the translation result to the translation service device 100) (S318).

The translation service apparatus 100 compares the audio file stored in the second user terminal 102 with the audio file stored in the audio DB 253 according to the audio file synchronization request of the first user terminal 101 in operation S320.

If the comparison result (S320) and the audio file stored in the audio DB 253 are updated, the translation service apparatus 100 transmits the updated audio file or audio file path information to the second user terminal 102 (S322 ). On the other hand, if the audio file stored in the audio DB 253 is not updated, the translation service apparatus 100 does not transmit the audio file.

The second user terminal 102 stores the audio file received from the translation service apparatus 100 (S324). In this manner, when the user presses the audio file synchronization menu, the translation service apparatus 100 can transmit the same audio file as the audio file stored in the first user terminal 101 to the second user terminal 102.

Meanwhile, the first user terminal 101 may transmit the audio file through the communication network to the second user terminal 102 connected in advance according to the audio file synchronization request of the user. Here, the communication network can be a wired or wireless data network, a data cable between devices, a wireless data interface, or the like. At this time, data between the first user terminal 101 and the second user terminal 102, which is another device, is compared and only necessary translation data is transmitted.

In the meantime, the present invention can be applied to various reproduction apparatuses by implementing the above-described translation service method for synchronizing audio files with a software program and recording them on a computer-readable recording medium.

The various playback devices may be a mobile terminal, a PDA, a notebook, a navigation, a PMP, a smart phone, an electronic dictionary, an MPS, and the like as the user terminal described above.

For example, the recording medium may be a hard disk, a flash memory, a RAM, a ROM, or the like embedded in each reproduction apparatus, or an external optical disk such as a CD-R or a CD-RW, a compact flash card, a smart media, have.

In this case, the program recorded on the computer-readable recording medium may include at least one of a sentence structure, a word structure, and a sentence structure through a natural language processing technique such as morphological analysis, syntax analysis, A translation step of extracting a part of speech and semantic information, generating a translation using the extracted result, and returning the translation to the first user terminal, analyzing text of the generated translation according to a speech synthesis request of the first user terminal Generating an audio file through voice synthesis and returning the generated audio file to the first user terminal, storing the generated audio file, and transmitting the audio file to the second user terminal in response to the audio file synchronization request of the first user terminal Comparing an audio file that compares the stored audio file with the stored audio file And an audio file synchronization step of synchronizing the updated audio file and the translation with the second user terminal as a result of the comparison.

The foregoing description is merely illustrative of the present invention, and various modifications may be made by those skilled in the art without departing from the spirit of the present invention. Accordingly, the embodiments disclosed in the specification of the present invention are not intended to limit the present invention. The scope of the present invention should be construed according to the following claims, and all the techniques within the scope of equivalents should be construed as being included in the scope of the present invention.

The present invention generates an audio file corresponding to a translation of the original text and transmits the translated audio file to the user terminal and compares the generated audio file with the audio file stored in another user terminal, It is possible to repeatedly check the translation and audio file requested by the user through the user terminal and to use the translation and the audio file regardless of the terminal used by the user in another synchronized terminal. In this respect, it is not only the use of the related technology but also the possibility of commercialization or operation of the applied device, as it exceeds the limit of the existing technology.

10: translation service system 100: translation service apparatus
101: first user terminal 102: second user terminal
210: communication interface unit 220:
230: audio file generation unit 240: audio file synchronization unit
250: Data storage unit 251: User DB
252: Translation DB 252: Audio DB

Claims (12)

delete A communication interface for receiving a text from a first user terminal and transmitting a translation and an audio file to the first user terminal and the second user terminal;
Extracting sentence structures, parts of speech and semantic information from the original text received through the communication interface unit based on the preset user translation setting information, and extracting sentences and words included in the original text using the extracted information, A translation unit operable to generate a translated translation into an in-information meaning and return the generated translation to the first user terminal;
An audio file generation unit for analyzing a text of a translated text with respect to the generated translated text according to a speech synthesis request of the first user terminal, generating an audio file through speech synthesis, and returning the generated audio file to the first user terminal; And
Storing the generated audio file, comparing the audio file stored in the second user terminal with the stored audio file according to the audio file synchronization request of the first user terminal, and transmitting the updated audio file and the translated text to the second user terminal And an audio file synchronization unit
A translation service device for synchronizing audio files. [Claim 3 is abandoned upon payment of the registration fee.] 3. The method of claim 2,
A user DB for storing user translation setting information received from the first user terminal or storing preset user translation setting information;
A translation DB for storing the generated translation; And
An audio DB for matching the audio file for the stored translation with a word or a sentence of the corresponding translation,
Wherein the translation service apparatus further comprises: [Claim 4 is abandoned upon payment of the registration fee.] 3. The method of claim 2,
Wherein the audio file generating unit comprises:
And generates an audio file corresponding to a word or a sentence in the generated translation according to a speech synthesis request for a word or a sentence in the generated translation. [Claim 5 is abandoned upon payment of registration fee.] 3. The method of claim 2,
Wherein the audio file generating unit comprises:
Generating an audio file according to a speech synthesis request for a word or a sentence in the generated translation, and generating audio file path information for downloading the generated audio file. [Claim 6 is abandoned due to the registration fee.] 3. The method of claim 2,
Wherein the audio file synchronization unit comprises:
And transmitting the audio file path information for downloading the audio file to the second user terminal or the audio file path information for downloading the audio file for the word or sentence in the generated translation. [7] has been abandoned due to the registration fee. The method according to claim 6,
The audio file path information may include:
(TTS) path information which is audio file path information of each word or sentence of the generated translation, or TTS (Text-To-Speech) path information for voiceing each word and sentences. Extracting sentence structures, parts of speech and semantic information from the original text received from the first user terminal based on preset user translation setting information, and extracting sentences and words of at least some of the original texts from the user translations A translated text generating step of generating translated texts translated into the meaning of the setting information and returning the generated translated texts to the first user terminal;
An audio file generation step of analyzing the text of the generated translation according to a speech synthesis request of the first user terminal, generating an audio file through speech synthesis, and returning the audio file to the first user terminal;
An audio file comparison step of storing the generated audio file and comparing the stored audio file with an audio file stored in the second user terminal according to the audio file synchronization request of the first user terminal; And
An audio file synchronization step of synchronizing the updated audio file and the translation with the second user terminal
And a translation service method for synchronizing audio files. [Claim 9 is abandoned upon payment of registration fee.] 9. The method of claim 8,
The audio file generation step may include:
And generating an audio file corresponding to a word or a sentence in the generated translation according to a speech synthesis request for a word or a sentence in the generated translation. [Claim 10 is abandoned upon payment of the registration fee.] 9. The method of claim 8,
The audio file generation step may include:
Generating an audio file according to a speech synthesis request for a word or a sentence in the generated translation, and generating audio file path information for downloading the generated audio file. [Claim 11 is abandoned upon payment of the registration fee.] 11. The method of claim 10,
The audio file synchronization step may comprise:
And transmitting an audio file for a word or a sentence in the generated translation to the second user terminal or transmitting the path information of the audio file for downloading. [12] has been abandoned due to the registration fee. 11. The method of claim 10,
The audio file path information may include:
To-speech (TTS) path information that is audio file path information of each word or sentence of the generated translation, or TTS (Text-To-Speech) path information that voice each word and sentences.

Images