JP3225514U - Multifunctional instant speech translator - Google Patents

Abstract

[PROBLEMS] Multi-functional instantaneous translation of a first language into a second language, which can overcome language barriers, whether speaking face-to-face, face-to-face, or speaking to many people A speech translation device is provided. A reception unit receives a voice of a first language, identifies the voice of the first language as a corresponding language, and forms and outputs a corresponding first language signal. A translation module 12 connected to receive the first language signal from the receiving unit, translate the first language signal, convert the first language signal into a corresponding second language signal, and output the second language signal; An output unit 13 connected to the translation module and receiving a second language signal of the translation module and emitting a voice corresponding to the second language, and a wireless module 14 connected to the translation module and the reception unit. Features. [Selection] Figure 2

Description

  The present invention relates to a voice translation device, and particularly to a multi-functional instant voice that can translate a voice in a first language into a second language instantly when communicating remotely, so that both parties can communicate without any problem. Related to a translation device.

  In general, there are many instant translation devices and translation software, but most translation devices set a language and translate it into the set language, and the translated language is transmitted through a screen or a speaker of an electric device. It is transmitted and instantly translated.

  When attending large international conferences and seminars, simultaneous translation headphones are usually provided, and by setting this speaker's language to a specific channel, you can instantly translate into that language. It has become. The immediate interpretation method is that the interpreter who interprets the language checks the language spoken directly by the interpreter on the spot, immediately identifies the language, and delivers the translated content to the participants' headphones. I have.

However, the above-mentioned instant interpretation method has the following disadvantages.
1. Since the two sides cannot receive the translated speech and cannot communicate interactively, the language cannot be translated immediately if the receiver wants to ask the sender the information. I cannot make calls.
2. Simultaneous interpretation of personal conversations is difficult because simultaneous interpretation in a meeting must be worn by both parties in order to achieve two-way immediate translation, which also hinders smooth communication. It has become.

  FIG. 1 is a schematic diagram of the Republic of China issue number M553001. As a conventional technique, as shown in FIG. 1, there is a technique capable of interactive simultaneous interpretation disclosed in the Republic of China Public Notice Number M553001 (Patent Document 1). In Patent Document 1, an input unit 21 for receiving first language audio information, a processing unit 22 for converting the first language audio information into second language audio information, a first language audio information, and a second language audio A learning unit 23 for temporarily storing information; and an output unit 24 for outputting second language voice information, so that two speakers using different languages can communicate with each other via an immediate interpreter. The audio information is instantaneously translated into second language audio information.

Taiwan Country Registration Bulletin M553001

  However, when two speakers are talking face-to-face, the effect of the immediate translation can be obtained. However, in the above-described invention, only direct face-to-face dialogue is limited. For this reason, when two talkers are having a conversation using a telephone, it is not possible to perform an immediate translation, and it is still very inconvenient.

  Therefore, the present inventor has accumulated many years of research and development experience in related fields, delves into and discusses the above-mentioned drawbacks, and, after many years of effort, actively seeks solutions based on the above-mentioned requirements, and finally finds out the book. The idea was completed.

  The main object of the present invention is to provide an instant speech translator, especially for instantly translating a first language voice into a second language voice when talking remotely or face to face. A method and a multi-function real-time speech translator when talking by phone or face to face.

  The purpose and function of the multi-function real-time speech translation device of the present invention are realized by technologies such as a reception unit, a translation module, and an output unit.

  The receiving unit is configured to receive the voice of the first language, identify the voice of the first language as a corresponding language, and form and output a corresponding first language signal. The first language described above is not limited to any language, and may be English, Spanish, or the like. The reception unit is connected to an identification unit for recognizing voices in a plurality of languages (English, Spanish, etc.), and a setting button is connected to the identification unit. The priority of the identification language can be set in advance.

  The translation module is electrically connected to the reception unit, receives the first language signal from the reception unit, translates the first language signal and converts the first language signal into a corresponding second language signal, and It is configured to output a language signal.

  The output unit is connected to the translation module, and is configured to receive a second language signal of the translation module and emit a voice corresponding to the second language.

  As a feature of the present invention, a wireless module is connected to the translation module and the reception unit, and the wireless module can wirelessly transmit a signal to the communication device.

  Subsequently, when the language is generated in a different language such as English, Spanish, Japanese, etc., the setting button is used to, for example, select a language to be recognized first, a language to be secondly recognized, and the like. The order of the recognition languages can be set in advance. As described above, since the identification unit sequentially identifies languages according to the identification language of the user, after the reception unit receives voices of a plurality of languages, the reception unit sequentially identifies the voice signals to generate a language signal and generates a language signal. Transmit audio signal as street. The translation module translates the voice signal to generate a second language signal, transmits the second language voice from the communication device or the output unit, and the user listens to the second language translated from the plurality of languages. Can be.

  By combining the above configurations, the user sends the voice of the first language to the receiving unit, and after the receiving unit receives the voice of the first language, recognizes the language corresponding to the voice of the first language and recognizes the corresponding language. Create The signal of the first language is transmitted to the translation module, and after receiving the signal of the first language, translates the first language into a predetermined second language, generates a signal of the second language, and transmits the signal to the output unit. I do. The output unit receives the second language signal and transmits the second language voice to the user, so that the user can directly hear the second language voice.

  In addition, the user can communicate directly with the wireless module via the calling device and translate immediately upon receiving or talking. Specifically, when the receiving unit receives the user's first language voice message, the first language voice is automatically recognized as a corresponding first language signal and transmitted to the translation module, and Is translated into a signal in a second language via Then, the translation module sends the signal in the second language to the wireless module, and the wireless module returns the signal in the second language to the communication device, and the signal in the second language is converted to the second language via the communication device. Then, the voice of the second language is transmitted to the callee. As a result, not only can the voice of the second language be immediately heard by the telephone, but also the voice of the second language is transmitted from the telephone. At the same time, the voice of the second language transmitted by the callee is translated into the first language, and the voice translated into the first language can be immediately heard. As long as the translation device is used, the language of the partner can be translated and transmitted to the partner. This allows both parties to break through language barriers and understand the other's language, thus completely overcoming the fear of speaking in an unfamiliar language.

  Further, the translation module includes a built-in language chip capable of translating a plurality of languages, and an extension unit connected to the built-in language chip. The user can extend the language data contained in the built-in language chip via the extension unit, thereby increasing the translation accuracy. The extension unit includes an artificial intelligence deep learning module having a language database to which a plurality of language outputs can be added, and the artificial intelligence deep learning module updates the translation module by continuously updating grammatical output information of the language database. Can be provided and translated using the grammar closest to the language user at the time of translation.

  In addition, the communication device is provided with a mobile application (APP) unit corresponding to a wireless module in the headphone microphone, and the mobile application (APP) unit can directly input and output audio through the headphone microphone.

  Using the multifunctional real-time speech translation device of the present invention, a method of instantly translating a first language voice into a second language voice when remotely speaking or face-to-face, and a telephone or face-to-face It shows an excellent effect that you can communicate smoothly when talking on face.

It is the schematic of the translation apparatus which concerns on Taiwan country registration publication M553001. FIG. 3 is a schematic view showing a preferred embodiment of the present invention. FIG. 2 is a schematic diagram (1) of a preferred application of the embodiment of the present invention. FIG. 2 is a schematic view (2) of a preferred application of the embodiment of the present invention.

  In order to more clearly understand the purpose, usefulness, features and structure of the present invention, preferred embodiments are illustrated and described below with reference to the drawings.

  First, refer to FIG. 2 for a schematic diagram showing a preferred embodiment of the present invention.

  The multifunctional real-time speech translation device 1 according to the preferred embodiment of the present invention includes a reception unit 11, a translation module 12, an output unit 13, a wireless module 14, and a communication device 15.

  The receiving unit 11 is configured to receive a voice of the first language, identify the voice of the first language as a corresponding language, and form and output a corresponding first language signal. The reception unit 11 is connected to an identification unit for recognizing sounds in a plurality of languages, and can recognize languages such as English and Spanish. Further, a setting button is connected to the identification unit, so that the user can preset the priority of the identification language through the setting button.

  The translation module 12 is electrically connected to the reception unit 11, receives the first language signal from the reception unit 11, translates the first language signal, converts the first language signal into a corresponding second language signal, and Output a second language signal.

  The output unit 13 is connected to the translation module 12, receives the second language signal of the translation module 12, and emits a voice corresponding to the second language. For example, it is possible to use a personal microphone placed on a seat in an international conference hall and transmit a second language voice via the personal microphone.

  A feature of the present invention is that a wireless module 14 is connected to the translation module 12 and the reception unit 11, and the wireless module 14 can wirelessly transmit a signal to the communication device 15. The wireless module 14 may perform wireless transmission of a signal to the communication device 15 via Bluetooth (registered trademark). The identification unit 111 includes a sensor module 112 capable of recognizing a sentence structure of a user. The translation module 12 can perform translation in real time, achieve an automatic translation effect at an appropriate time, and output Automatic translation is uttered via the unit 13.

  Subsequently, when a call is sent in a different language such as English, Spanish, or Japanese, the setting button is used to, for example, select a language to be recognized first, a language to be recognized second, and so on. The order of the recognition languages can be set in advance. As described above, the identification unit sequentially recognizes the language according to the identification language of the user. Therefore, after the reception unit 11 receives voices of a plurality of languages, the reception unit 11 sequentially recognizes the voice signals and generates a language signal. Audio signals can be transmitted in order. The translation module 12 translates the audio signal of the first language to generate an audio signal of the second language, and transmits the audio of the second language from the communication device 15 or the output unit 13. You can hear the translated second language.

  By combining such a configuration, the user can send a voice in the first language to the reception unit 11, and the reception unit 11 can be set in advance so that the language can be automatically recognized, or the reception language can be manually set. You can also. In this embodiment, the first language spoken by the user is English voice, and the receiving unit 11 receives the English voice, recognizes the voice as English, converts the English voice into an English signal, and converts the English voice into an English signal. Send to The translation module 12 is preset to translate the transmitted English signal into a second audio signal (in this embodiment, set as a Chinese signal), and is translated into Chinese by the translation module 12. Is done. The translated Chinese signal is transmitted to the output unit 13, and the output unit 13 transmits the Chinese signal in Chinese voice. This allows the user to directly hear Chinese voice.

  In other words, when two speakers in different languages talk to each other or one speaks to many people, as long as one speaker uses the invention, the other speaker will use the invention Regardless of whether or not they can communicate directly with each other through this invention. Even when the language spoken by each user is sent to both, it can be immediately translated into the language set for each user.

  In addition, by using wireless communication between the communication device 15 and the wireless module 14, it is possible to perform an immediate translation at the time of an incoming call or a call. For example, if the callees are a Chinese user and an English user, and the Chinese user sends a Chinese voice to the reception unit 11, the reception unit 11 will determine that the user has emitted a Chinese voice. Is converted to a Chinese signal and sent to the translation module 12. In the translation module 12, the Chinese signal is translated into an English signal and transmitted to the wireless module 14. The English signal is transmitted to the communication device 15 via the wireless module 14 and transmitted to the call target in English voice, so that the call target can instantly hear the voice translated into English.

  Subsequently, when the callee sends out the English voice, the user's telephone device wirelessly transmits the English voice to the wireless module 14, transmits the voice received by the wireless module 14 to the receiving unit 11, and the receiving unit 11 receives the voice. The converted speech is identified, and if it is in English, it is converted into an English signal, and the converted signal is sent to the translation module 12. The translation module 12 translates the English signal into a Chinese signal corresponding to the English signal, and the Chinese signal is transmitted from the wireless module 14 to the communication device 15, and the communication device 15 directly provides the translated Chinese voice to the user. Therefore, the user and the communication target can communicate with each other immediately by the present invention.

  FIG. 3 is a schematic diagram of an application example (1) of the preferred embodiment of the present invention, and FIG. 4 is a schematic diagram of an application example (2) of the preferred embodiment of the present invention.

  The present invention may be designed as a headphone microphone 16 as shown in FIG. 3, the present invention may be used for a part of the headphone 161 of the headphone microphone 16, or a part of the microphone 162 of the headphone bike 16. The present invention may be used as. In this way, by simultaneously listening to the set language, the user can immediately translate one language into the set language during a conversation.

  Therefore, as long as the user wears the headphone microphone 16, one-to-one conversation or one-to-many communication can be performed regardless of the transmitted language (the black arrow in FIG. 3 indicates the voice transmission direction). Is). When the headphone 161 receives the speaker's voice, the voice is translated into a language set by the user, and the voice in the set language is transmitted to the user. The user simply transmits the voice to the microphone 162, and the voice is automatically translated into the voice of the translation language set by the caller and transmitted, so that the effect of the immediate translation can be obtained.

  Further, the user can hear the other party's translated voice from a part of the headphones 161, and the microphone 162 can immediately translate the other party's voice and set the translation language so that it can be instantly translated into the other party's language. Can be. This allows the user to communicate smoothly with other callers, regardless of the user's language, and even in large-scale lectures, viewers and callees can use specific earphones and translators. No need to attach. In addition, since the user can set and speak the language used by the translation partner, the user is extremely convenient in one-on-one conversation or one-to-many communication.

  As shown in FIGS. 2 and 4, the wireless module 14 and the communication device 15 in the headphone microphone 16 are transmitted and received wirelessly, and the user directly listens to the translation language set by the callee via the headphone microphone 16. It can also translate and transmit the voice of the callee. As a result, both remarks are translated into the set language, so that communication with the call target can be performed directly.

  In this way, the user can make a remote call via the communication device 15 and can simultaneously translate both languages when communicating with a person in a different language, thereby hindering communication with other companies. Not even. Also, by using the present invention, simultaneous interpretation can be done even at lectures in front of the public, and by connecting to an audio amplifier, many audiences can directly hear the translated language, It is possible to completely overcome the fear that a lecture will fail due to language barriers.

  In addition, by installing an audio amplification device in a personal microphone or the like in a large-scale lecture hall, a speaker can translate into a specific language and transmit to the public through a personal microphone. Can be greatly reduced.

  Further, since the translation module 12 includes the built-in language chip 121 capable of translating into a plurality of languages and the extension unit 122 connected to the built-in language chip 121, the user can operate the built-in language chip 121 via the extension unit 122. By extending the language data, more accurate translation can be performed. The extension unit 122 includes an artificial intelligence deep learning module 1221 having a language database to which a plurality of language outputs can be added. The artificial intelligence deep learning module 1221 continuously updates grammatical output information of the language database. A translation module can be provided to translate the grammar closest to the language user at the time of translation.

  In addition, since the communication device 15 can be provided with a mobile application (APP) unit corresponding to the wireless module in the headphone microphone, the mobile application (APP) unit can directly input or output sound via the earphone microphone. can do.

From the above, the "multifunctional real-time speech translator" of the present invention is closely related to the existing technology in the same kind of conventional technology, and has the following advantages.
1. Face-to-face simultaneous translation: the cooperation of the reception unit, the translation module and the output unit, eliminates the inconvenience of language in common conversation situations, and both receive or transmit the language translated simultaneously with each other Can solve the language barrier problem.
2. Simultaneous interpretation of remote calls: By transmitting the language signal wirelessly via the communication device and the wireless module and performing two-way immediate translation (listening and speaking), you can freely talk without being limited to language differences can do.
3. Immediate translation lecture: No need to wear specific earphones or tune to a specific channel, the caller can use the microphone and speakerphone of the present invention to directly translate the translated language to many viewers Can be transmitted to

  Upon reviewing the above-mentioned domestic and foreign technical information documents relating to the present invention, it was clear that there was no identical or similar structure before the present invention was made. Therefore, the inventive step and the similar products of the present invention are recognized for their inventive step and practicality. Therefore, the present invention satisfies the utility model registration requirements of "creativity", "industrial applicability" and "inventive step".

  The above description is only a preferred embodiment of the present invention, and those utilizing the present invention and those having the same structural changes are included in the claims of the present invention. It is understood.

DESCRIPTION OF SYMBOLS 1 Multifunctional real-time speech translation apparatus 11 Reception unit 111 Identification unit 112 Sensor module 12 Translation module 121 Built-in language chip 122 Expansion unit 1221 Artificial intelligence deep learning module 13 Output unit 14 Wireless module 15 Talk device 16 Headphone microphone 161 Headphone 162 Microphone (conventional References in technical literature)
2 Instant translation device 21 Input unit 22 Processing unit 23 Learning unit 24 Output unit

Claims (3)

Including a reception unit, a translation module, an output unit, and a communication device;
The receiving unit receives a voice of a first language, identifies the voice of the first language as a corresponding language, forms and outputs a corresponding first language signal,
The translation module is electrically connected to the reception unit, receives a first language signal from the reception unit, translates the first language signal, converts the first language signal into a corresponding second language signal, and Output a second language signal,
The output unit is connected to the translation module, and receives a second language signal of the translation module, and in a multifunction real-time speech translation device that emits a voice corresponding to a second language,
A wireless module is connected to the translation module and the reception unit,
The wireless module is capable of wirelessly transmitting a signal to the communication device,
The translation module includes a built-in language chip capable of translating a plurality of languages, and an extension unit connected to the built-in language chip,
The extension unit has an artificial intelligence deep learning module with a language database to which a plurality of language applications can be added,
The artificial intelligence deep learning module, by continuously updating the grammar output information of the language database, translates using the grammar closest to the user of the language at the time of translation,
The reception unit is connected to an identification unit for identifying voices in a plurality of languages,
The multi-function real-time speech translation device, wherein the identification unit includes a sensor module that can recognize a sentence structure of a user.   The multifunctional real-time speech translator according to claim 1, which can be mounted in a headphone microphone.   The multi-function real-time speech translator according to claim 2, wherein the call device includes a mobile application (APP) unit corresponding to a wireless module in a headphone microphone.