阅读说明：本技术 一种免手操作的翻译机 (Hand-free translation machine ) 是由 付金龙 于 2019-11-20 设计创作，主要内容包括：本发明公开了一种免手操作的翻译机,涉及翻译设备技术领域,为解决现有技术中,翻译机存在的使用过程较为不便、翻译效率降低、实用效果不佳的技术问题,本发明的技术方案如下：包括：语音输入模块、VAD模块、语音识别模块、处理器、翻译云服务器及语音输出模块。(The invention discloses a hand-free translation machine, relates to the technical field of translation equipment, and aims to solve the technical problems that in the prior art, the translation machine is inconvenient to use, the translation efficiency is reduced, and the practical effect is poor, wherein the technical scheme is as follows: the method comprises the following steps: the system comprises a voice input module, a VAD module, a voice recognition module, a processor, a translation cloud server and a voice output module.)

1. A hands-free translator comprising:

the voice input module is used for acquiring voice information of a user;

the voice information processing device comprises a voice input module, a voice detection module and a voice extraction module, wherein the input end of the VAD module is connected with the output end of the voice input module and is used for detecting whether a voice signal exists in the voice information of a user and extracting the voice signal;

the voice recognition module, the input end of the said voice recognition module is connected with carry-out terminal of VAD module, the said VAD module sends the voice signal extracted to the voice recognition module, the said voice recognition module converts the voice signal of the user into the literal information;

the processor is provided with a wireless communication module, the input end of the processor is connected with the output end of the voice recognition module, and the processor receives the character information sent by the voice recognition module and translates the character information into appointed translated characters;

the translation cloud server is in communication connection with the processor through the wireless communication module, a translation voice library is prestored in the translation cloud server, and the processor searches translation voices corresponding to the specified translation characters in the translation voice library;

and the input end of the voice output module is connected with the output end of the processor, and the processor sends the searched translation voice to the voice output module for playing.

2. The hands-free translator of claim 1 further comprising a smart watch module, wherein the voice input module, the VAD module, the voice recognition module, the processor and the voice output module are disposed on the smart watch module.

3. A hands-free translator according to claim 2 wherein the smart watch module incorporates a touch screen display.

4. The hands-free translator of claim 3, further comprising an emergency help system, wherein the emergency help system comprises a satellite positioning module, a triggering module, a help controller and a help cloud server, the output ends of the satellite positioning module and the triggering module are connected with the input end of the help controller, the help controller is provided with a wireless communication module and is in communication connection with the help cloud server, and when the triggering module is started, the help controller collects position information through the satellite positioning module and sends the position information to the help cloud server for help.

5. A hands-free translator as claimed in claim 4, wherein the satellite positioning module is a Beidou navigation Module or a GPS module.

6. A hands-free translator as claimed in claim 5, wherein the wireless communication module is a 3G communication module, a 4G communication module or a 5G communication module.

7. The hands-free translator of claim 6, further comprising a noise reduction system, the noise reduction system comprising a noise reduction generation module, the noise reduction generation module playing out a noise reduction signal.

8. The hands-free translator of claim 7, wherein the noise reduction system further comprises a noise reduction module and a noise reduction controller, an input of the noise reduction controller is connected to an output of the voice input module, an output of the noise reduction controller is connected to an input of the noise reduction module, and an output of the noise reduction module is connected to an input of the noise reduction generation module; the voice input module collects external noise information and sends the noise information to the noise reduction controller, the noise reduction controller determines a noise reduction level according to the noise information, a noise reduction gain value is determined according to the noise level, the noise reduction gain value is sent to the noise reduction processing module, the noise reduction processing module obtains a noise reduction signal according to the noise reduction gain value, and the noise reduction signal is sent to the noise reduction generation module to be played.

9. A hands-free translator as claimed in claim 8 further comprising a power module, the power module being connected to the power consuming circuitry of the translator.

10. A hands-free translator according to claim 9 further comprising a watch housing, said watch housing being a shock-proof, water-proof, dust-proof, three-proof watch housing.

Technical Field

The invention relates to the technical field of translation equipment, in particular to a hand-free translation machine.

Background

The translating machine is used for converting one natural language into another natural language by using a computer. With the continuous acceleration of the global integration process, more and more people start to study, work and travel abroad, and meanwhile, the application of the translator is more and more extensive, however, the traditional translator can only realize the translation of voice-character and character-character, the output result is the translator in the form of character, a user must read or show the translator to the other side by using a handheld translator, the use process is inconvenient, meanwhile, although the translator similar to simultaneous interpretation appears in the prior art, the translator does not have the function of eliminating noise and noise, so that the translator is influenced by useless voice signals or noise signals when collecting the voice signals, the translation efficiency is reduced, and the practical effect is not good.

Disclosure of Invention

In order to solve the technical problems of inconvenient use, low translation efficiency and poor practical effect of the translation machine in the prior art, the technical scheme of the invention is as follows:

the invention relates to a hand-free translation machine, which comprises:

the voice input module is used for acquiring voice information of a user;

the voice information processing device comprises a voice input module, a voice detection module and a voice extraction module, wherein the input end of the VAD module is connected with the output end of the voice input module and is used for detecting whether a voice signal exists in the voice information of a user and extracting the voice signal;

the voice recognition module, the input end of the said voice recognition module is connected with carry-out terminal of VAD module, the said VAD module sends the voice signal extracted to the voice recognition module, the said voice recognition module converts the voice signal of the user into the literal information;

the processor is provided with a wireless communication module, the input end of the processor is connected with the output end of the voice recognition module, and the processor receives the character information sent by the voice recognition module and translates the character information into appointed translated characters;

the translation cloud server is in communication connection with the processor through the wireless communication module, a translation voice library is prestored in the translation cloud server, and the processor searches translation voices corresponding to the specified translation characters in the translation voice library;

and the input end of the voice output module is connected with the output end of the processor, and the processor sends the searched translation voice to the voice output module for playing.

And the voice input module, the VAD module, the voice recognition module, the processor and the voice output module are all arranged on the intelligent watch module.

Further, the touch display screen is configured to the intelligent watch module.

Further, still include the system of promptly seeking help, the system of promptly seeking help includes satellite positioning module, trigger module, seeks help the controller and seeks help the cloud ware, satellite positioning module and trigger module's output is connected with the input of seeking help the controller, it is furnished with wireless communication module to seek help the controller, establishes communication connection with seeking help the cloud ware, works as trigger module starts, and the controller of seeking help passes through satellite positioning module and gathers positional information to with positional information send to seeking help the cloud ware and seek help.

Furthermore, the satellite positioning module is a Beidou navigation module or a GPS module.

Further, the wireless communication module is a 3G communication module, a 4G communication module or a 5G communication module.

The system further comprises a noise reduction system, wherein the noise reduction system comprises a noise reduction generation module, and the noise reduction generation module plays a noise reduction signal outwards.

The noise reduction system further comprises a noise reduction processing module and a noise reduction controller, wherein the input end of the noise reduction controller is connected with the output end of the voice input module, the output end of the noise reduction controller is connected with the input end of the noise reduction processing module, and the output end of the noise reduction processing module is connected with the input end of the noise reduction generation module; the voice input module collects external noise information and sends the noise information to the noise reduction controller, the noise reduction controller determines a noise reduction level according to the noise information, a noise reduction gain value is determined according to the noise level, the noise reduction gain value is sent to the noise reduction processing module, the noise reduction processing module obtains a noise reduction signal according to the noise reduction gain value, and the noise reduction signal is sent to the noise reduction generation module to be played.

And the power supply module is connected with an electric circuit of the translator.

Furthermore, the watch further comprises a watch shell which is a shockproof, waterproof and dustproof three-prevention watch shell.

Compared with the prior art, the hand-free translation machine has the beneficial effects that:

1. the simultaneous interpretation of Chinese and English can be rapidly completed through the speech translation system, and the system is suitable for foreign language learning, travel communication and the like;

2. the translation result is displayed in an audio form, a user does not need to hold the translation machine all the time, and the use process is more convenient;

3. the VAD technology (voice endpoint detection) is used for identifying the voice signal of the user and eliminating a long mute period, so that the calculation amount of a voice identification system of the translator is reduced, and the meaningless energy consumption is reduced;

4. the parts of the translator are carried by the watch, so that hands are well liberated, the translator can be well carried with the translator, and the translator is convenient to use.

Drawings

FIG. 1 is a schematic diagram of the connection of one embodiment of the present invention;

FIG. 2 is a schematic diagram of the connection of another embodiment of the present invention;

FIG. 3 is a schematic diagram of a connection of yet another embodiment of the present invention;

FIG. 4 is a schematic diagram of a connection according to yet another embodiment of the present invention;

FIG. 5 is an external schematic view of a hands-free translator of the present invention.

Detailed Description

The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

As shown in fig. 1, a hands-free translator of the present invention comprises:

the voice input module 1, the voice input module 1 is used for gathering the voice information of the user.

And the input end of the VAD module 2 is connected with the output end of the voice input module 1 and is used for detecting whether voice signals exist in the voice information of the user and extracting the voice signals. The VAD module 2 separates an effective speech signal from a useless speech signal or a noise signal, so that subsequent speaker recognition, semantic recognition, speech emotion analysis and other work are more efficient, and the VAD module is a very necessary and key link in a speech processing process and is mainly used for: 1. under the scene of voice storage or transmission, the data volume of storage or transmission can be reduced by separating effective voice from continuous voice stream; 2. the recognition work is carried out aiming at the effective voice signals, and the calculation amount of a voice recognition system can be greatly reduced on the premise of not reducing the voice information amount; 3. because the interference of the noise in the non-voice signal is removed, the identification accuracy of the system is greatly improved.

Voice recognition module 3, voice recognition module 3's input is connected with VAD module 2's output, and VAD module 2 sends the speech signal who extracts to voice recognition module 3, and voice recognition module 3 converts user's speech signal into text message.

The processor 4, processor 4 are furnished with wireless communication module 14, and wireless communication module 14 is 4G communication module, and the input of processor 4 is connected with the output of speech recognition module 3, and processor 4 receives the literal information that speech recognition module 3 sent to translate the literal information into appointed translation characters. The processor 4 is an integrated circuit chip including a CPU and memory that stores a library of translated words, the process of which is the same as the process of text-to-text interconversion of the prior art.

The translation cloud server 5, the translation cloud server 5 and the processor 4 establish communication connection through the wireless communication module 14, the translation cloud server 5 prestores a translation voice library, and the processor 4 searches translation voices corresponding to specified translation characters in the translation voice library.

And the input end of the voice output module 6 is connected with the output end of the processor 4, and the processor 4 sends the searched translation voice to the voice output module 6 for playing.

For example, the translator selects a middle translation mode, a user speaks 'How to reach a railway station' to the voice input module 1, the VAD module 2 detects voice information, eliminates surrounding noise influence, extracts only key voice signals spoken by the user and sends the key voice signals to the voice recognition module 3 to convert the key voice signals into Chinese character information, the processor 4 converts the Chinese character information into English characters 'How to get the usability station', the processor 4 is connected with the translation cloud server 5 through a wireless network to find translation voice corresponding to each word in a translation voice library, and sends the translation voice to the voice output module 6 to be played.

As shown in fig. 2, the translator of the present invention uses a wristwatch as a carrier in order to improve the portability of the device. The concrete design is as follows: still include intelligent wrist-watch module 7, voice input module 1, VAD module 2, speech recognition module 3, treater 4 and voice output module 6 all set up on intelligent wrist-watch module 7.

The intelligent watch module 7 is provided with a touch display screen 8, and the translator is controlled through the touch display screen 8.

As shown in fig. 3, the emergency help system 9 is further included, the emergency help system 9 includes a satellite positioning module 10, a triggering module 11, a help-seeking controller 12 and a help-seeking cloud server 13, the satellite positioning module 10 is a GPS module, output ends of the satellite positioning module 10 and the triggering module 11 are connected with an input end of the help-seeking controller 12, the help-seeking controller 12 is provided with a wireless communication module 14, the wireless communication module 14 is a 5G communication module, the help-seeking controller 12 is connected with the help-seeking cloud server 13 through a network, when the triggering module 11 is started, the help-seeking controller 12 collects position information through the satellite positioning module 10 and sends the position information to the help-seeking cloud server 13 for help seeking. Wherein, trigger module 11 sets up in the sunken department of dial plate, avoids the mistake touching. In the spanish language system area of ramet, such as countries of mexico, columbia and the like, the treatment and security environment is poor, the translator used by a traveler needs help seeking and alarming functions, if danger is met, the translator can seek help, the trigger module 11 is started, the help seeking controller 12 sends position information to the help seeking cloud server 13, the help seeking cloud server 13 automatically contacts local police, and the position information with danger is sent to police in real time.

As shown in fig. 4, the translator of the present invention further includes a noise reduction system 15, where the noise reduction system 15 includes a noise reduction generation module 16, and the noise reduction generation module 16 plays a noise reduction signal to the outside. Wherein the noise reduction signal of the process is adjusted manually.

In order to increase the reaction speed of the noise reduction process and form an automatic adjustment noise reduction signal, the noise reduction system 15 further comprises a noise reduction processing module 17 and a noise reduction controller 18, wherein the input end of the noise reduction controller 18 is connected with the output end of the voice input module 1, the output end of the noise reduction controller 18 is connected with the input end of the noise reduction processing module 17, and the output end of the noise reduction processing module 17 is connected with the input end of the noise reduction generation module 16; the voice input module 1 collects external noise information and sends the noise information to the noise reduction controller 18, the noise reduction controller 18 determines a noise reduction level according to the noise information, then determines a noise reduction gain value (shown in table 1) according to the noise level, sends the noise reduction gain value to the noise reduction processing module 17, the noise reduction processing module 17 obtains a noise reduction signal according to the noise reduction gain value, and sends the noise reduction signal to the noise reduction generation module 16 for playing. The noise reduction generation module 16 emits sound waves with opposite phase and same amplitude as the noise to resist the noise, so that the noise disappears.

TABLE 1 decibel value of noise, noise level and noise reduction gain value comparison table

The invention also comprises a power module 19, the power module 19 is connected with an electric circuit of the translator, the invention also comprises a watch shell 20, the watch shell 20 is a shockproof, waterproof and dustproof three-proof watch shell 20, such as a shell of iWatch in the prior art, as shown in figure 5.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.