KR102170902B1 - Real-time multi-language interpretation wireless transceiver and method - Google Patents

Abstract

The present invention relates to a wireless earphone for real-time multi-way interpretation and a method for transmitting and receiving, and to an apparatus for enabling a conversation with a plurality of users using different languages by using the earphone. The earset includes an ID setting unit for setting language information of a user, a transmitting end receiving voice and encoding and transmitting ID data and voice data, and a receiving end receiving and decoding the ID data and voice data and outputting in a corresponding language. Include. In addition, ID data and voice data transmitted from the transmitter of a plurality of earphones composed of one to many or many to many are received, and ID data and voice data for each of a plurality of predefined languages are transmitted to the receiver of the plurality of transceivers. It is connected to the translation server.

Description

Real-time multi-language interpretation wireless transceiver and method}

The present invention relates to a real-time multi-party interpretation wireless earphone and method, and more particularly, to transmit and receive data in which the voice inputted by the real-time multi-party interpretation wireless earphone and the ID signal for the corresponding language information are combined through a translation server to transmit and receive translation in real time. The present invention relates to an apparatus and a method for enabling a conversation in real time even if a number of people use different languages through an earset wearable on a user's ear.

In recent years, with the development of transportation and communication technologies, international exchanges are actively taking place. As many people visit countries where different languages are spoken, the demand for human resources who can interpret and translate the language of that country into their own language is increasing rapidly.

In particular, due to the increase in international exchanges between companies, institutions and individuals with branches in foreign countries, there is a desperate need for interpretation and translation services in various fields.

As a result, technologies for various translation devices and methods have been continuously developed, and text translation services that interpret and translate a native language into a corresponding national language through the Internet have already provided a considerable level of translation. In addition, a certain level of interpretation and translation is possible by using a dedicated interpretation and translation application or a dedicated translator using a smart device.

Such a smart device or a dedicated translator interprets and translates the native language into the voice of the country in real time by setting the language of the country in advance when the user meets and faces a person in the country, or the exclusive translator recognizes the voice of the other party. .

However, when users who speak a variety of languages from different countries gather at the same time, such as a conference, the inconvenience of having to operate the translator directly occurs whenever the user communicates with a person who speaks different languages, even if the translator recognizes the voice. Thus, even if it is automatically translated into a corresponding language, a problem of delay due to speech recognition and a problem of poor speech recognition occur at the current technology level.

Therefore, in order to smoothly communicate with people of various nationalities such as conferences in real time, it is necessary to develop a translator that does not cause delay even if a plurality of users communicate simultaneously.

In addition, even if the translation is performed in real time, when the content is directly read and delivered, the user does not understand the conversation due to a difference in pronunciation or takes a lot of time, resulting in inconvenience.

A technology related to an automatic interpretation and translation system is disclosed in Korean Patent Laid-Open Publication No. 10-2016-0122371, "Automatic interpretation and translation system and method using an electronic device" (hereinafter, prior art).

The prior art is a system capable of automatically interpreting and translating for a number of unspecified languages by removing language barriers by using the native language in the electronic device used by the electronic device even under conditions where the language is not familiar or the language of another country is not communicated.

However, the prior art of the prior art as described above is limited to interpreting the voice call between a user and another person using a voice call device, but not interpreting it during a conversation through a meeting, and the mobile phone as the voice call device provides an interpretation service. There is a problem in that text costs are required to use. In addition, although the interpretation service is to be used using a smartphone, this is also useful for conversations through meetings rather than voice calls, and the disadvantage of not having an actual conversation environment because the user proceeds with the conversation through text messages. have.

The present invention was conceived to solve the above-described problem, and is to solve the problem that a conventional interpreter does not provide a direct conversation environment by performing translation using a voice communication device, regardless of the user's pronunciation. It is intended to provide a conversation environment in which users can directly communicate.

In addition, the present invention analyzes and recognizes a language by receiving an ID for corresponding language information in hardware by a conventional interpreter, so that real-time multi-party in order to solve the recognition delay and poor recognition that occurs when interpreting and translating multiple languages. Interpretation By transmitting and receiving data that combines the input voice and the ID signal for the corresponding language information through the translation server, you can immediately interpret the corresponding language by analyzing only the ID signal, so even when interpreting and translating multiple languages, speech recognition delay and It is an object of the present invention to provide a real-time multi-party interpretation wireless transmission/reception device capable of solving poor recognition.

The objects of the embodiments of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those of ordinary skill in the art from the following description. .

An earset including a microphone and earphone for recognizing a user's voice, the earset is composed of one to one, one to one or a plurality of ones, and an ID setting unit for setting the user's language information and the voice recognized by the microphone. And a transmitting end encoding ID data and voice data including language information, and a receiving end decoding ID data and voice data received from the transmitting end.

In addition, the earset is connected to a translation server that receives the ID data and voice data transmitted from the transmitting end, translates the ID data and voice data for each of a plurality of predefined languages, and transmits it to the receiving end of the corresponding other earset. To do.

In addition, the wireless transmission/reception apparatus includes a translation server for receiving the ID data and voice data transmitted from the earset and the transmitting end, translating the ID data and voice data for each of a plurality of predefined languages, and transmitting it to the receiving end of the corresponding tire set. Include.

Earset comprising an ID setting unit for setting language information of a user, a transmitting end for receiving voice input and encoding and transmitting ID data and voice data, and a receiving end for receiving and decoding the ID data and voice data and outputting in a corresponding language And a translation of receiving ID data and voice data transmitted from the transmitter of a plurality of earphones consisting of one to many or many to many, and transmitting the ID data and voice data for each of a plurality of predefined languages to the receiver of the plurality of earphones. May include a server.

Specifically, the transmitting end includes a voice input unit that receives voice and converts an electric signal, a first header analysis unit that receives and analyzes a signal from the ID setting unit, and an input voice and an ID analyzed by the first header analysis unit. It may include an encoding unit for converting and combining signals into data, and a transmission unit for transmitting the combined data of voice data and ID data converted by the encoding unit to the translation server.

Specifically, the receiving end includes a receiving unit that receives data in which voice data and ID data are combined from a translation server, and a decoding unit that decodes the data in which the voice data and ID data are combined and separates it into voice data and ID data, It may include a second header analysis unit for analyzing the ID data to extract and match corresponding language information, and a voice output unit for outputting the corresponding language as a voice.

In the real-time multi-party interpretation wireless transmission/reception method of the present invention for achieving the above object, a node setting step in which the translation server determines the number of target earphones, and a communication method in which the translation server determines a one-to-many or many-to-many communication method. A determination step, a master/slave determination step in which the translation server determines a master/slave among a plurality of earphones if the communication method is one to many, an ID definition step in which the translation server defines an ID, and a translation server from a plurality of earphones It may include an interpretation and translation step of receiving and interpreting the data.

Specifically, the transmission step in which the earphones transmit data through the translation server in the interpretation and translation step includes a voice input step of receiving a voice input through a voice input unit, and a transmission ID analysis in which the first header analysis unit receives and analyzes a signal from the ID setting unit. And an encoding step of converting and combining the voice transmitted in the voice input step and the signal analyzed in the transmission ID analysis step into data, and a data transmission for transmitting the voice data and ID data transmitted in the encoding step to a translation server. It may include steps.

Specifically, in the interpretation and translation step, the receiving step of receiving data from the earset through the translation server includes a data receiving step of receiving data combining voice data and ID data from the translation server, and analyzing the ID data to Receiving ID analysis step of extracting information and selecting ID data and voice data matching the ID set in the earset, and decoding the data combined with the voice data and ID data, separating it into voice data and ID data, and converting it into voice It may include a decoding step of performing the decoding step and a voice output step of outputting the corresponding language converted in the decoding step as a voice.

As described above, according to the present invention, a conventional interpreter receives an ID for corresponding language information in hardware, analyzes and recognizes the language, and transmits it to the user through text, reads it, or displays the translated text. Unlike the interpretation process that takes time through a real-time multi-party interpretation wireless earphone, the data that the input voice and the ID signal for the corresponding language information are combined is transmitted and received through the translation server so that the translated sentences can be actually heard. This has the effect of creating an actual conversation environment.

In addition, the real-time multi-way interpretation wireless earphone can interpret a corresponding language immediately by analyzing only an ID signal among data transmitted from the translation server, so that a recognition delay and poor recognition that occur when recognizing a voice does not occur.

1 is a view showing an operation example of a real-time multi-party interpretation wireless earphone according to an embodiment of the present invention.
2 is a view showing the operation of a real-time multi-party interpretation wireless earphone according to an embodiment of the present invention.
3 is a view showing the operation of a real-time multi-party interpretation wireless earphone according to another embodiment of the present invention.
Figure 4 is a view showing the structure of a real-time multi-party interpretation wireless earphone according to an embodiment of the present invention.
5 is a block diagram schematically showing the structure of data transmitted and received from an earset to a translation server according to an embodiment of the present invention.
Figure 6 is a flow chart showing a real-time multi-party interpretation wireless transmission and reception method according to an embodiment of the present invention.
Fig. 7 is a flow chart showing the transmission step of the interpretation and translation step shown in Fig. 6;
Fig. 8 is a flow chart showing the reception step of the interpretation and translation step shown in Fig. 6;
Fig. 9 is a diagram showing an example of one-to-many or many-to-many.
Fig. 10 is a diagram showing an example of being connected to a relay after being composed of a plurality of units.

Advantages and features of the embodiments of the present invention, and a method of achieving them will become apparent with reference to the embodiments described later in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, and only these embodiments make the disclosure of the present invention complete, and are common knowledge in the technical field to which the present invention pertains. It is provided to completely inform the scope of the invention to those who have, and the invention is only defined by the scope of the claims. The same reference numerals refer to the same components throughout the specification.

In describing the embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted. In addition, terms to be described later are terms defined in consideration of functions in an embodiment of the present invention, which may vary according to the intention or custom of users or operators. Therefore, the definition should be made based on the contents throughout this specification.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a view showing an operation example of a real-time multi-party interpretation wireless earphone according to an embodiment of the present invention, Figure 2 is a view showing the operation of the real-time multi-party interpretation wireless ear set according to an embodiment of the present invention.

As shown in Fig. 1, the real-time multi-party interpretation wireless earset according to an embodiment of the present invention uses the earset to perform interpretation in real time. That is, through the ear set, it is possible to simultaneously speak and listen. In addition, the earphones are connected to one-to-one, one-to-many, or many-to-many at the same time, so that several people can communicate in different languages at the same time, and they are connected to a mobile phone via Bluetooth to make a real-time call with a person who speaks a different language. It is also possible. The earset is a wearable earset connection type, and can be used in all smart phones, and can be used in a variety of smart devices as well as smart phones. The earset is a device according to an embodiment, and is not limited to the earset, and any device provided with a microphone and earphone may be used.

2 is an exemplary embodiment of the present invention, and will be described centering on a first user wearing the first earphone 111 and a second user wearing the second earphone 112. The first user wears the first earphone 111, and the first microphone 10 of the first earphone 111 recognizes the voice of the first user. The recognized voice is converted into identification ID and voice data and transmitted to the second earphone 112, and the transmitted voice is transmitted from the second earphone 112 to the translation server 200. The translation server 200 will be described later.

The translation server 200 transmits the data converted to TTS back to the second earphone 112, and the second earphone 112 outputs the result as voice data to the user.

That is, the second earphone 112 transmits the identification ID (language) and voice data received from the first earphone 111 to the translation server 200, and the TTS value processed by the translation server 200 Data is received and output as voice data.

The translation server 200 analyzes the received identification ID and voice data to perform language translation. The translated language is converted to TTS. The data converted to TTS by the translation server 200 is transmitted to the second earphone 112, and the second earphone 112 outputs the transmitted TTS data as voice data. The translation server 200 may have a separate server to communicate with the earphones.

In this case, as an API (Application Programming Interface) for performing language translation, an API such as Google Cloud Platform or PAPAGO may be used, and various APIs other than the above-described API may be used, but are not limited thereto.

In addition, although FIG. 2 shows the use between two users, it is not limited thereto, and it is also possible to connect one-to-one, one-to-many, or many-to-many conversations at the same time.

In addition, in FIG. 2, the voice recognized by the first microphone 10 of the first earphone 111 of the first user is transmitted from the second earphone 112 of the second user to the translation server 200 for translation. Although performed, it is not limited thereto, and according to an embodiment, the identification ID and voice data are transmitted from the first earphone 111 to the translation server 200 and translated, and then the converted TTS data is converted to the second earphone 112 It is also possible to pass it on.

That is, the earset including a microphone and earphone for recognizing a user's voice is composed of one to one, one to one or many to many, and the voice recognized by the microphone is converted into ID data and voice data including language information. And a transmitting end for encoding and a receiving end for decoding ID data and voice data and voice data received from the transmitting end. In addition, it includes a translation server 200 for receiving the ID data and voice data transmitted from the transmitting end and transmitting the ID data and voice data for each of a plurality of predefined languages to the receiving end of a corresponding tire set.

In addition, if the earphone is a Bluetooth type earphone, the translation server may be implemented in a smartphone to which the earphone is paired with Bluetooth. In this case, the translation server may be implemented in the form of software (for example, an application) on a smartphone, and may be interlocked with an earset capable of providing a real-time multi-party interpretation service.

In addition, as another specific embodiment of the translation server, a part that processes the translation API may be implemented in the cloud server, and only the part that interfaces with the user and interfaces with the smartphone may be implemented in the form of an application.

3 is a view showing the operation of a real-time multi-party interpretation wireless earphone according to another embodiment of the present invention. As shown in Figure 3, the earset may be manufactured in the form of a pendant. That is, instead of wearing it on the ear, the earset manufactured in the form of a pendant can be used by hanging it on a necklace.

For example, if an English-speaking user and a Korean-speaking user each have a pendant, when the English-speaking user speaks English, the pendant transmits the recognized English to the Korean-speaking user's pendant. The Korean-speaking user's pendant translates the received English into Korean.

The translated Korean is delivered to a user who speaks Korean, and the user listens to the contents and answers the word in Korean. The Korean-speaking user's pendant recognizes the Korean language, and delivers Korean to the English-speaking user's pendant, and the pendant translates Korean into English and outputs it to the user.

The earset or pendant-type translation earset as described above selects and translates an API in the translation server when translating the received language into another language. The earset according to an embodiment of the present invention can be customized to a user by selecting an API having a high recognition rate according to a user's preference when performing translation.

For example, in the case of a translation API such as Papago, the Korean recognition rate is excellent, while the Chinese recognition rate is relatively poor, so it is excellent at translating Hangul into Chinese, but not excellent at translating Chinese into Korean. Likewise, Google has a higher recognition rate in English, so it is excellent at translating English into other languages. In this case, the earset according to an embodiment of the present invention can select an API with a high recognition rate depending on the language, such as selecting and using Papago when recognizing Korean, and selecting Google to translate when recognizing English. Do.

Therefore, a plurality of APIs (Papago, Google, Baidu, etc.) are provided in advance in the translation server, so that when translating each language, an API with a high recognition rate of the corresponding language can be selected and used. That is, translation-related APIs can be easily changed by optimizing translation-related APIs for each language in the translation server, and migration according to the development or upgrade of the corresponding translation API is also easy.

When selecting the API, it is possible to automatically select the API by recognizing the corresponding language, or it is also possible for the user to directly select and use the API.

4 is a block diagram schematically showing the inside of an earset, and the transmission/reception apparatus 100 of the present invention may include an ID setting unit 110, a transmission terminal 120, and a reception terminal 130.

First, the earset 100 is assumed that the transmitting device and the receiving device are mounted together in one device in an embodiment of the present invention, but the present invention is not limited thereto, and the transmitting device and the receiving device are separated into separate devices. It may be mounted to be configured as a set while transmitting and receiving each other, or may be configured as a set of one transmitting device and a plurality of receiving devices. In other words, in the case of a conference in which a plurality of people communicate with each other at the same time, it is desirable to consist of a set with the transmitting device and the receiving device. In the case of a single presentation to a large number of people, it is composed of one transmitting device and a plurality of receiving devices. It can be said that it is desirable to lose.

The ID setting unit 110 performs a function of setting language information of a user. In other words, when a user sets his/her nationality, that is, the language of his/her country he/she wants to hear, information about the corresponding language is generated and transmitted to the transmitter 120 and the receiver 130 of the earphone 100. In an embodiment of the present invention, it is assumed that the ID setting unit 110 is a combination of a display and a button recognizable to the outside of the device, or is formed of a touch screen, but the ID setting unit 110 is limited to the above example. No, it is natural that it can be transformed by any other means of similar function.

The transmitter 120 receives voice and encodes and transmits ID data and voice data. The voice input unit 121, the first header analysis unit 122, the encoding unit 123, and the transmission unit 124 It may include.

The voice input unit 121 performs a function of receiving a voice and converting an electric signal. In an embodiment of the present invention, it is assumed that the voice input unit 121 is formed of various types of microphones. Of course, in addition to the voice input unit 121, various input devices such as a text input device or a touch pen may be used instead.

The first header analysis unit 122 performs a function of receiving and analyzing a signal from the ID setting unit 110. When the user sets his/her language, that is, the language to be heard, the ID setting unit ( 110) generates an ID signal including information of the corresponding language, and this signal is transmitted to the receiving end 120 and transmitted to the first header analysis unit 122, and the first header analysis unit 122 analyzes the signal. Accordingly, the encoding unit 123 generates a signal suitable for the data format to be converted.

The encoding unit 123 converts and combines the input voice and the ID signal analyzed by the first header analysis unit 122 into data. By doing so, the data transmitted to the translation server 200 is ID It consists of head data corresponding to the signal and voice data corresponding to the input voice.

The transmission unit 124 performs a function of transmitting the combined data of the voice data and the ID data converted by the encoding unit 123 to the translation server 200. In an embodiment of the present invention, the transmitter 124 assumes that the transmitter 124 is made of an RF communication module, a Wifi module, etc. so that it can wirelessly transmit/receive with the translation server 200 separated by a certain distance or more. It is natural that it can be used.

The receiving end 130 receives and decodes ID data and voice data and outputs it in a corresponding language. The voice output unit 131, the second header analysis unit 132, the decoding unit 133, and the receiving unit 134 ) Can be included.

The voice output unit 131 performs a function of outputting a corresponding language as a voice, and in one embodiment of the present invention, it may be composed of a normal speaker, may be configured to use an earphone, and include all of them. It can also be configured.

The second header analysis unit 132 performs a function of analyzing ID data to extract and match corresponding language information. In other words, the translation server 200 receives data for various languages propagated from the translation server 200 and quickly analyzes only the head of the transmitted data string, thereby easily extracting the corresponding language information of the ID data contained in the head. In this way, the corresponding translator can quickly interpret the desired language without recognizing the voice itself like a conventional translator and comparing it with an internal pre-stored language.

The decoding unit 133 performs a function of decoding data in which voice data and ID data are combined and separating the data into voice data and ID data. In other words, if the second header analysis unit 132 selects data suitable for the corresponding translator among data for various languages propagated from the translation server 200, the selected data is decoded, separated into voice data and ID data, and separated voice It converts the data so that it can be converted into an audio signal.

The receiving unit 134 performs a function of receiving data combined with voice data and ID data from the translation server 200. In an embodiment of the present invention, it is assumed that the receiving unit 134 is made of an RF communication module, a Wifi module, etc. so as to transmit and receive wirelessly to and from the translation server 200 separated by a certain distance, but various communication modules may be used. I will say of course.

The translation server 200 receives ID data and voice data transmitted from the transmitter 124 of a plurality of earphones 100 composed of one to many or many to many, and receives ID data and voice data for each of a plurality of predefined languages. It performs a function of transmitting to the receiving unit 134 of the plurality of earphones (100).

In one embodiment of the present invention, the translation server 200 includes a database for various languages inside, an algorithm for translating into each language using data contained in these databases, and transmitting and receiving data signals. It is assumed to include a communication unit.

A brief description of the operation of the real-time multi-party interpretation wireless transmission/reception system of the present invention configured as described above is as follows.

First, the user manipulates the ID setting unit 110 of the earset 100.

Next, the transmitting end 120 encodes the input voice and the signal of the ID setting unit 110, combines it, and transmits it to the translation server 200.

Next, the translation server 200 receives the data transmitted from the plurality of earphones 100, identifies the configuration of the earphones 100, defines the ID, and then stores the data of any one of the earphones 100 input in real time. According to a predefined ID, language data for each country is generated and propagated to the earset 100.

Finally, after receiving the language data for each country, the receiving end 130 analyzes the ID data of the received data, selects and decodes data matching the ID information of the corresponding device, and outputs it as a voice.

Figure 6 is a flow chart showing a real-time multi-party interpretation wireless transmission and reception method according to an embodiment of the present invention, the real-time multi-party interpretation wireless transmission and reception method of the present invention, the node setting step (S310), the communication method determining step (S320), the master / It may include a slave determination step (S330), an ID definition step (S340), and an interpretation and translation step (S350).

The node setting step (S310) is a step in which the translation server 200 determines the number of target earphones 100. As described above, in one embodiment of the present invention, it is assumed that a conference seat in which a plurality of users are simultaneously conversing, or a case in which one person makes a presentation to a plurality of persons, is required. Accordingly, a plurality of earphones 100 corresponding to a translator is required. Therefore, the translation server 200 needs to determine the total number of earphones 100 for real-time multi-party interpretation.

The communication method determination step (S320) is a step in which the translation server 200 determines a one-to-many or many-to-many communication method, and the plurality of earphones 100 identified as described above are connected to each other in some way. It is necessary to determine whether to operate the system in a broadcasting method or a multi-party interactive method by grasping whether it is configured.

In one embodiment of the present invention, it is assumed that the earphone 100 is configured in a large one-to-many or many-to-many communication method, but the earphones 100 are configured in various ways, and the system can be operated according to the communication method. It would be natural to be able to.

If the configuration of the earset 100 in the communication method determination step (S320) is one to many, proceed to the subsequent master/slave determination step (S330), and if the configuration of the earset 100 is not one to many, but many to multiple, ID It proceeds to the definition step (S340).

The master/slave determination step (S330) is a step of determining, by the translation server 200, a master/slave among a plurality of earphones 100 if the communication method is one to many, for example, the earphones 100 is a translation server ( When it is determined that the communication method is composed of one-to-many communication methods by 200), the earset 100 in charge of transmission is found and designated as a master, and the earset 100 in charge of reception is found and designated as a slave. For example, in the case of the earset 100 designated as a master, it can be expected that the speaker of the conference is the presenter, and in the case of the earset 100 designated as a slave, it can be expected that it is a participant who listens to the speaker's presentation.

The ID definition step (S340) is a step in which the translation server 200 defines an ID, and after determining a communication method by identifying the earset 100 as in the previous step, the data transmitted from the earset 100 is received. In this step, data is generated in each language according to the ID data stored in each ear set 100 to prepare for transmission. Therefore, after that, when a signal carrying voice data is transmitted from any one of the earphones 100, the purpose is to generate language-specific data of all the ID data determined in the ID definition step (S340) and transmit it to the earphones 100 in real time.

Interpretation and translation step (S350) is a step in which a plurality of earphones transmits or receives data through a translation server to interpret and translate. At this stage, the user finally hears the voice spoken by the other party in the corresponding language, and the voice spoken by the other party is interpreted and heard in the user's language.

The interpretation and translation step (S350) may be specifically divided into a transmission step and a reception step.

Figure 7 is a flow chart showing the transmission step of the interpretation and translation step shown in Figure 6, the transmission step in which the earset 100 transmits data through the translation server 200 in the interpretation and translation step (S350), the voice input step (S410) , Transmission ID analysis step (S420), encoding step (S430), and data transmission step (S440) may be included.

The voice input step (S410) is a step of receiving a voice through the voice input unit 121. When the user speaks through a microphone, the voice is received and converted into an electric signal.

In the transmission ID analysis step (S420), the first header analysis unit 122 receives and analyzes the signal from the ID setting unit 110 so that it can be converted into data in a subsequent encoding step (S430).

The encoding step (S430) is a step of converting and combining the voice transmitted in the voice input step (S410) and the signal analyzed in the transmission ID analysis step (S420) into data. As described above, the data signal sequence transmitted and received by the earset 100 to the translation server 200 is composed of the ID data of the head and the voice data of the voice part, so that the data signal corresponds to any language without directly recognizing the voice in the future. Make it easy and quick to figure out whether it is.

The data transmission step (S440) is a step of transmitting the voice data and ID data transmitted in the encoding step (S430) to the translation server 200.

Figure 8 is a flow chart showing the receiving step of the interpretation and translation step shown in Figure 6, the receiving step in which the earset receives data through the translation server in the interpretation and translation step, the data receiving step (S510), the received ID analysis step (S520), It may include a decoding step (S530) and a voice output step (S540).

The data receiving step (S510) is a step of receiving data in which voice data and ID data are combined from the translation server 200, and the translation server 200 has each of the predetermined values as defined in the ID definition step (S34). When data is created for each ID corresponding to the ear set 100 and transmitted at the same time, the ear set 100 receives it.

The reception ID analysis step (S520) is a step of analyzing ID data, extracting corresponding language information, and selecting ID data and voice data matching the ID set in the earset 100. In other words, after receiving the data signals for each language transmitted at the same time, only the ID data from each data signal is quickly analyzed to select a data signal containing the ID data for each language requested by the corresponding earphone 100.

The decoding step (S530) is a step of decoding the data in which the voice data and the ID data are combined, separating the data into voice data and ID data, and converting the data into voice. This is a step of converting the corresponding voice data into an electrical signal so that a speaker or earphone can sound.

The audio output step S540 is a step of outputting the corresponding language converted in the decoding step S330 as a voice.

9 and 10 schematically show the configuration method of the ear set 100 as a figure.

The upper left of Fig. 9 shows that the earset 100 is configured as a peer-to-peer one-way network. That is, the earset 100 used herein indicates that a transmitting device and a receiving device are configured separately and communicated only in one direction.

Below it is shown that the earphone 100 is configured as a peer-to-peer bidirectional network. That is, the earset 100 used herein indicates that a transmitting device and a receiving device are separately configured to communicate only in both directions.

Below it is shown that the earset 100 is configured as a one-to-many network. That is, in this case, the earset 100 is composed of one transmitting device and a plurality of receiving devices to indicate that it is propagated in one direction from one transmitting device. Since this is similar to the transmission method of a broadcasting station, it is also referred to as a broadcast network.

On the right, it is shown that a plurality of earphones 100 are configured to transmit and receive each other through a star network network. In other words, it is indicated that the earphones 100 are not separated and operate integrally so that a plurality of them communicate in both directions with each other.

In addition, as shown in FIG. 10, the earset 100 may be configured such that the star network network is relayed through an intermediate relay and connected to each other. In other words, it indicates that two star network networks are connected by a relay, which is a kind of communication device, for example, a case where one space and one space are connected to each other in a space separated place.

As described above, in the present invention, unlike the conventional interpreter in which the device receives an ID for the corresponding language information in hardware and analyzes and recognizes the language, the real-time multi-party interpreter wireless earphones input voice and ID for the corresponding language information. Since the data to which the signals are combined is transmitted and received through the translation server, the real-time multi-party interpretation wireless earphone can interpret the corresponding language immediately by analyzing only the ID signal among the data transmitted from the translation server. It has the effect of not causing delay and poor recognition.

In the above description, various embodiments of the present invention have been presented and described, but the present invention is not necessarily limited thereto, and those of ordinary skill in the art to which the present invention pertains, within the scope of the technical spirit of the present invention. It will be easy to see that branch substitutions, modifications and changes are possible.

111: first earphone
211: second earphone
10: first microphone 11: first earphone
20: first earphone 21: second earphone
100: earset 110: ID setting unit
120: transmitter 121: voice input unit
122: first header analysis unit 123: encoding unit
124: transmitter 130: receiver
131: audio output unit 132: second header analysis unit
133: decoding unit 134: receiving unit
200: translation server unit

Claims (8)

Earsets including a microphone and earphones for recognizing a user's voice;
The earset is
It is composed of 1 to 1, 1 to many or many to many,
An ID setting unit for setting language information of a user;
A transmitter for encoding the voice recognized by the microphone into ID data and voice data including language information; And
Includes; a receiving end for decoding the ID data and voice data received from the transmitting end,
The earset is
It is connected to a translation server that receives the ID data and voice data transmitted from the transmitter, translates the ID data and voice data for each of a plurality of predefined languages, and transmits it to the receiver of the corresponding tire set,
The transmitting end
A voice input unit for receiving voice and converting an electric signal;
A first header analysis unit for receiving and analyzing the signal of the ID setting unit;
An encoding unit converting and combining the input voice and the ID signal analyzed by the first header analysis unit into data; And
Includes; a transmission unit for transmitting the combined data of the voice data and ID data converted by the encoding unit to the translation server,
The receiving end
A receiver for receiving data combined with voice data and ID data from the translation server;
A decoding unit that decodes the data in which the voice data and ID data are combined and separates the data into voice data and ID data;
A second header analysis unit that analyzes the ID data to extract and match corresponding language information; And
Includes; a voice output unit for outputting the language as a voice,
The earset manually selects an API with high recognition rate or translation accuracy among APIs provided by the translation server when translating the received language into another language according to the user's preference, or
In the translation server, an API having a relatively high recognition rate or translation accuracy for each language is stored, and a specific API is automatically selected according to the language to be translated, and translation is performed.
The translation server operates the system in a broadcasting method when the configuration of the earset is one or more, and it finds the earset in charge of transmission among the plurality of earsets and designates it as a master. A wireless earphone for real-time multi-party interpretation, characterized in that receiving data transmitted from a designated earset, generating data in each language according to ID data stored in each earset designated as a slave, and transmitting the data to the earset designated as a slave.
delete delete delete delete A node setting step of determining, by the translation server, the number of target earphones;
A communication method determining step in which the translation server determines a one-to-many or many-to-many communication method;
A master/slave determination step of determining, by the translation server, a master/slave among a plurality of earphones when the communication method is one to many;
An ID definition step in which the translation server defines an ID;
Including; an interpretation and translation step in which the translation server receives data from a plurality of earphones and interprets and translates,
In the interpretation and translation step, the transmission step in which the earset transmits data to the translation server
A voice input step of receiving a voice through a voice input unit;
A transmission ID analysis step of receiving and analyzing a signal of the ID setting unit by the first header analysis unit;
An encoding step of converting and combining the voice transmitted in the voice input step and the signal analyzed in the transmission ID analysis step into data; And
A data transmission step of transmitting voice data and ID data transmitted in the encoding step to a translation server; and
In the interpretation and translation step, the receiving step in which the earset receives data from the translation server is
A data receiving step of receiving data combined with voice data and ID data from the translation server;
A reception ID analysis step of analyzing the ID data, extracting corresponding language information, and selecting ID data and voice data matching the ID set in the earset;
A decoding step of decoding the data combined with the voice data and the ID data, separating the data into voice data and ID data, and converting the data into voice; And
Including; a voice output step of outputting the language converted in the decoding step as voice,
The interpretation and translation step
When the earset translates the received language into another language, one of the APIs provided by the translation server with high recognition rate or translation accuracy is manually selected according to the user's preference, or
In the translation server, an API having a relatively high recognition rate or translation accuracy for each language is stored, and a specific API is automatically selected according to the language to be translated, and translation is performed.
The master/slave determination step
If the translation server has a configuration of one or more earphones, the system is operated in a broadcasting method,
The steps of finding the earset in charge of transmission among a plurality of earsets and designating it as a master, the steps of finding the earset in charge of receiving and designating it as a slave, and receiving data transmitted from the earset designated as a master to each earset designated as a slave. And generating data in each language according to the stored ID data and transmitting the data to an earset designated as a slave.
delete delete

Images