CN112770206A - Multilingual intelligent translation megaphone based on off-line machine translation - Google Patents

Multilingual intelligent translation megaphone based on off-line machine translation Download PDF

Info

Publication number
CN112770206A
CN112770206A CN202011529878.6A CN202011529878A CN112770206A CN 112770206 A CN112770206 A CN 112770206A CN 202011529878 A CN202011529878 A CN 202011529878A CN 112770206 A CN112770206 A CN 112770206A
Authority
CN
China
Prior art keywords
voice
translation
megaphone
main body
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011529878.6A
Other languages
Chinese (zh)
Other versions
CN112770206B (en
Inventor
姜蓓丽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Xinghongye Intelligent Technology Co ltd
Original Assignee
Anhui Xinghongye Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Xinghongye Intelligent Technology Co ltd filed Critical Anhui Xinghongye Intelligent Technology Co ltd
Priority to CN202011529878.6A priority Critical patent/CN112770206B/en
Publication of CN112770206A publication Critical patent/CN112770206A/en
Application granted granted Critical
Publication of CN112770206B publication Critical patent/CN112770206B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/08—Mouthpieces; Microphones; Attachments therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses a multilingual intelligent translation megaphone based on off-line machine translation, which comprises a play main body and a megaphone body, wherein the megaphone body is wirelessly connected with the play main body through Bluetooth; the front end of the playing main body is provided with a loudspeaker, the top end inside the playing main body is provided with a master control box, two threaded sleeves are respectively arranged at positions close to two sides inside the playing main body, threaded columns are arranged inside the threaded sleeves, and the bottom ends of the threaded columns penetrate through the playing main body; the outer surface of the rear end of the playing main body is fixedly provided with a placing box for placing the megaphone body; a display screen is embedded in the outer surface of the rear end of the megaphone body; the master control box comprises a data receiving module, a voice recognition module, a voice conversion module, a voice library, a voice translation module and a voice sending module. The invention has the function of off-line translation, meets different use requirements of users and is more worthy of popularization and use.

Description

Multilingual intelligent translation megaphone based on off-line machine translation
Technical Field
The invention relates to the field of megaphones, in particular to a multilingual intelligent translation megaphone based on off-line machine translation.
Background
The megaphone is equipment for expanding sound, has wide application range, is used in field commands such as tour guide, flood fighting, emergency rescue, film shooting and the like, and can also be used in the process of border megaphone;
in the prior megaphone, an operator carries out propaganda or public address megaphone by a hand-held translation and a hand-held common microphone or loud speaker under a frontier megaphone scene, and the megaphone cannot effectively guarantee the accuracy of pronunciation because the operator generally does not accept the study of a specific language and is also deficient in speed and tone of the language; in different places, the required language types are different, especially to the peripheral languages of China, such as korean, hindi, etc., this kind of language experts of our side are rare, can't support the daily operation needs of guarantee, and simultaneously, it is also not convenient enough to operate and use, especially under the operation scene, the operation personnel are inconvenient to vacate the hand to take the translation, can only remember a few sentences of commonly used phrases by force, very big reduction operation efficiency, the memory burden of operation personnel has also been increased, on the other hand, loud speaker on the market not only can not lack the translation function, and power is lower, it is limited to call the distance, it is inconvenient to carry and use, be not convenient for the operation scene to use, certain influence has been brought to the use of calling the ware, therefore, provide a multilingual intelligent translation calling ware based on off-line machine translation.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to solve the loud speaker on the market not only can't lack the translation function, and the power is lower, and it is limited to call the distance, and it is inconvenient to carry and use, and the scene of being not convenient for uses, has brought the problem of certain influence for the use of megaphone, provides a multilingual intelligence translation megaphone based on off-line machine translation.
The invention solves the technical problems through the following technical scheme that the electric megaphone comprises a playing main body and a megaphone body which is in wireless connection with the playing main body through Bluetooth;
the front end of the playing main body is provided with a loudspeaker, the top end inside the playing main body is provided with a master control box, two threaded sleeves are respectively arranged at positions close to two sides inside the playing main body, threaded columns are arranged inside the threaded sleeves, and the bottom ends of the threaded columns penetrate through the playing main body;
the outer surface of the rear end of the playing main body is fixedly provided with a placing box for placing the megaphone body;
a microphone, an induction lamp and a selection button are arranged on the outer surface of the front end of the megaphone body, and a display screen is embedded on the outer surface of the rear end of the megaphone body;
the master control box comprises a data receiving module, a voice recognition module, a voice conversion module, a voice library, a voice translation module and a voice sending module;
the data receiving module is used for receiving real-time voice information collected by the microphone and translation final language information selected by a user, the collected voice information is sent to the voice recognition module for voice content recognition, voice recognition content information is obtained, and the voice recognition content information is sent to the voice conversion module;
the voice conversion module converts the acquired voice recognition content into English text content, then extracts final language information to be translated, uploads the translated final language information to a voice library for matching, extracts the language word library after the matching is successful, and the obtained real-time voice information and the obtained English text information of the language word library are all delivered to a display screen, and after the real-time voice information and the obtained English text information are determined to be correct manually, the language word library is sent to the voice translation module, and meanwhile, the English text content is sent to the voice translation module;
the speech translation module performs matching processing on the English characters and the language word library derived from the speech library, and synthesizes the translation contents into electronic speech information after matching the translation contents;
the electronic voice information is sent to the voice sending module, and the electronic voice information voice sending module sends the synthesized electronic voice information to the broadcasting loudspeaker on the playing main body.
Preferably, the soft cushion layer is arranged inside the placing box, and the top end of the placing box is in threaded connection with the sealing piece.
Preferably, the sealing member comprises a sealing cover and a knob at the top end of the sealing cover.
Preferably, a supporting block with an equilateral hexagonal cross section is fixedly installed at the bottom end of the threaded column.
Preferably, the top end of the playing main body is provided with a handle, and the bottom end of the playing main body is provided with four casters.
Preferably, the voice library is automatically updated after accessing the network, and the specific process of the automatic update is as follows:
the method comprises the following steps: the method comprises the steps that after a voice library is accessed to a network, the voice library is connected with an automatically updated cloud storage, all language information stored in the voice library is exported, the size of the voice library is obtained, and the voice library is marked as Pi;
step two: all real-time single language Pi and the size Pi of the preset single language which is automatically updated in the cloud storagePreparation ofComparing the two to calculate the size Pi of the preset single languagePreparation ofThe difference between the size Pi of the single language class and the real-time size Pi of the single language class is used for obtaining PiDifference (D)When Pi isDifference (D)When Pi is 0, i.e. no update is requiredDifference (D)And updating when the value is any value other than 0.
Preferably, the microphone is a dual-microphone noise reduction system, and the noise reduction mode of the microphone is a dual-microphone algorithm.
Compared with the prior art, the invention has the following advantages: this ware is shouted to multilingual intelligence translation based on off-line machine translation, can come to carry out off-line translation, the effectual situation of having avoided no network connection just can't carrying out the translation takes place, and all translation contents all carry out the speech conversion again after the user confirms and report, the better translation degree of accuracy of having guaranteed, the unexpected emergence of having avoided the translation to make mistakes direct broadcast and leading to, and carry out the content renewal promptly automatically behind the speech library access network, the effectual thesaurus of guaranteeing the speech library thesaurus is filled, and the components of a whole that can function independently sets up, the effectual propaganda distance of shouting of having promoted, let this equipment be worth using widely more.
Drawings
FIG. 1 is an overall block diagram of the present invention;
FIG. 2 is an internal view of the play body of the present invention;
FIG. 3 is a view of the mounting structure of the placing box of the present invention;
FIG. 4 is a view of the interior of the holding box of the present invention;
FIG. 5 is a view of the display screen mounting structure of the present invention;
FIG. 6 is a block diagram of the overall control box structure of the present invention.
In the figure: 1. a main body is played; 2. a megaphone body; 21. a microphone; 22. an induction lamp; 23. a selection button; 24. a display screen; 3. a horn; 4. a handle; 5. a master control box; 6. a threaded bushing; 7. a threaded post; 8. a support block; 9. placing a box; 10. a cushion layer.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
As shown in fig. 1 to 6, the present embodiment provides a technical solution: a multilingual intelligent translation megaphone based on off-line machine translation comprises a playing main body 1 and a megaphone body 2 which is in wireless connection with the playing main body 1 through Bluetooth;
the front end of the playing main body 1 is provided with the loudspeaker 3, the top end inside the playing main body 1 is provided with the master control box 5, two threaded sleeves 6 are respectively arranged at positions, close to two sides, inside the playing main body 1, the threaded sleeves 6 are internally provided with the threaded columns 7, the bottom ends of the threaded columns 7 penetrate through the playing main body 1, supporting blocks 8 with cross sections being equilateral hexagons are fixedly installed at the bottom ends of the threaded columns 7, a user can adjust the height of each threaded column 7 according to the terrain of an installation place, so that the playing main body 1 can be stably placed, the supporting blocks 8 with the cross sections being equilateral hexagons increase the contact area, and the supporting stability is guaranteed;
a placing box 9 for placing the megaphone body 2 is fixedly arranged on the outer surface of the rear end of the playing main body 1;
the inside of placing case 9 sets up cushion layer 10, and cushion layer 10's setting can not shout the ware body 2 and avoid strikeing, and the top threaded connection who places case 9 has the sealing member.
The sealing element comprises a sealing cover and a knob at the top end of the sealing cover, the sealing element is used for sealing the placing box 9, the megaphone body 2 is better protected, and the knob is convenient for a user to open the placing box 9;
the external surface of the playing body 1 is provided with a microphone 21, an induction lamp 22 and a selection button 23, and the selection button 23 is used for selecting a translation language and confirming a translation result;
the master control box 5 comprises a data receiving module, a voice recognition module, a voice conversion module, a voice library, a voice translation module and a voice sending module;
the voice library stores character information of all languages which can be collected in the Internet and English translation corresponding to each character;
the data receiving module is used for receiving the voice information collected by the microphone 21 and the translation final language information selected by the user, the collected voice information is sent to the voice recognition module for voice content recognition, voice recognition content information is obtained, and the voice recognition content information is sent to the voice conversion module;
the voice conversion module converts the acquired voice recognition content into English text content, then extracts final language information to be translated, uploads the translated final language information to a voice library for matching, extracts the language word library after matching is successful, sends the language word library to the voice translation module, and sends the English text content to the voice translation module;
the speech translation module performs matching processing on the English characters and the language word library derived from the speech library, and synthesizes the translation contents into electronic speech information after matching the translation contents;
electronic voice information is sent to voice sending module, and electronic voice information voice sending module sends the electronic voice information after the synthesis to broadcast loudspeaker 3 on the broadcast main part 1.
The top of broadcast main part 1 is provided with handle 4, and the bottom of broadcast main part 1 is provided with four truckles.
The voice library is automatically updated after being accessed into the network, and the specific process of automatic updating is as follows:
the method comprises the following steps: the method comprises the steps that after a voice library is accessed to a network, the voice library is connected with an automatically updated cloud storage, all language information stored in the voice library is exported, the size of the voice library is obtained, and the voice library is marked as Pi;
step two: all real-time single language Pi and the size Pi of the preset single language which is automatically updated in the cloud storagePreparation ofComparing the two to calculate the size Pi of the preset single languagePreparation ofThe difference between the size Pi of the single language class and the real-time size Pi of the single language class is used for obtaining PiDifference (D)When Pi isDifference (D)When Pi is 0, i.e. no update is requiredDifference (D)And updating when the value is any value other than 0.
The noise of the microphone 21 is reduced by double microphones, and the noise reduction mode of the microphone 21 is a double-microphone algorithm.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (7)

1. The multilingual intelligent translation megaphone based on offline machine translation is characterized by comprising a playing main body (1) and a megaphone body (2) which is in wireless connection with the playing main body (1) through Bluetooth;
the front end of the playing main body (1) is provided with a loudspeaker (3), the top end of the interior of the playing main body (1) is provided with a master control box (5), two threaded sleeves (6) are respectively arranged at positions close to two sides in the interior of the playing main body (1), threaded columns (7) are arranged in the threaded sleeves (6), and the bottom ends of the threaded columns (7) penetrate through the playing main body (1);
the outer surface of the rear end of the playing main body (1) is fixedly provided with a placing box (9) for placing the megaphone body (2);
a microphone (21), an induction lamp (22) and a selection button (23) are arranged on the outer surface of the front end of the megaphone body (2), and a display screen (24) is embedded on the outer surface of the rear end of the megaphone body (2);
the master control box (5) comprises a data receiving module, a voice recognition module, a voice conversion module, a voice library, a voice translation module and a voice sending module;
the data receiving module is used for receiving real-time voice information collected by the microphone (21) and translation final language information selected by a user, the collected voice information is sent to the voice recognition module for voice content recognition, voice recognition content information is obtained, and the voice recognition content information is sent to the voice conversion module;
the voice conversion module converts the acquired voice recognition content into English text content, then extracts final language information to be translated, uploads the translated final language information to a voice library for matching, extracts the language word library after the matching is successful, and the obtained real-time voice information and the obtained English text information of the language word library are all delivered to a display screen (24), and after the real-time voice information and the obtained English text information are determined to be correct manually, the language word library is sent to the voice translation module, and simultaneously the English text content is sent to the voice translation module;
the speech translation module performs matching processing on the English characters and the language word library derived from the speech library, and synthesizes the translation contents into electronic speech information after matching the translation contents;
the electronic voice information is sent to the voice sending module, and the electronic voice information voice sending module sends the synthesized electronic voice information to the broadcasting loudspeaker (3) on the playing main body (1).
2. The multilingual intelligent translation megaphone based on offline machine translation of claim 1, wherein: the soft cushion layer (10) is arranged inside the placing box (9), and a sealing piece is connected to the top end of the placing box (9) in a threaded mode.
3. The multilingual intelligent translation megaphone, based on offline machine translation, of claim 2, wherein: the sealing piece comprises a sealing cover and a knob at the top end of the sealing cover.
4. The multilingual intelligent translation megaphone based on offline machine translation of claim 1, wherein: and a supporting block (8) with an equilateral hexagonal cross section is fixedly arranged at the bottom end of the threaded column (7).
5. The multilingual intelligent translation megaphone based on offline machine translation of claim 1, wherein: the top of broadcast main part (1) is provided with handle (4), the bottom of broadcast main part (1) is provided with four truckles.
6. The multilingual intelligent translation megaphone based on offline machine translation of claim 1, wherein: the voice library is automatically updated after being accessed into the network, and the specific process of automatic updating is as follows:
the method comprises the following steps: the method comprises the steps that after a voice library is accessed to a network, the voice library is connected with an automatically updated cloud storage, all language information stored in the voice library is exported, the size of the voice library is obtained, and the voice library is marked as Pi;
step two: all real-time single language Pi and the size Pi of the preset single language which is automatically updated in the cloud storagePreparation ofComparing the two to calculate the size Pi of the preset single languagePreparation ofThe difference between the size Pi of the single language class and the real-time size Pi of the single language class is used for obtaining PiDifference (D)When is coming into contact withPiDifference (D)When Pi is 0, i.e. no update is requiredDifference (D)And updating when the value is any value other than 0.
7. The multilingual intelligent translation megaphone based on offline machine translation of claim 1, wherein: the microphone (21) is used for double-microphone noise reduction, and the noise reduction mode of the microphone (21) is a double-microphone algorithm.
CN202011529878.6A 2020-12-22 2020-12-22 Multilingual intelligent translation megaphone based on off-line machine translation Active CN112770206B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011529878.6A CN112770206B (en) 2020-12-22 2020-12-22 Multilingual intelligent translation megaphone based on off-line machine translation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011529878.6A CN112770206B (en) 2020-12-22 2020-12-22 Multilingual intelligent translation megaphone based on off-line machine translation

Publications (2)

Publication Number Publication Date
CN112770206A true CN112770206A (en) 2021-05-07
CN112770206B CN112770206B (en) 2023-04-07

Family

ID=75694751

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011529878.6A Active CN112770206B (en) 2020-12-22 2020-12-22 Multilingual intelligent translation megaphone based on off-line machine translation

Country Status (1)

Country Link
CN (1) CN112770206B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN205581861U (en) * 2016-01-26 2016-09-14 北京纽思曼教育科技有限公司 Interpreting equipment
CN205584461U (en) * 2016-05-11 2016-09-14 青岛歌尔声学科技有限公司 Loudspeaker box
WO2016167619A1 (en) * 2015-04-17 2016-10-20 (주)에스앤아이스퀘어 Voice recognition interpreter based on near field communication network and method for operating voice recognition interpreter
JP3225366U (en) * 2019-10-29 2020-02-27 鋒霖科技股▲ふん▼有限公司Ｊｅｔｖｏｘ Ａｃｏｕｓｔｉｃ Ｃｏｒｐ． Earphone storage case device
CN110933536A (en) * 2018-09-20 2020-03-27 台山市恒东音响科技有限公司 Sound box
CN210804431U (en) * 2019-10-29 2020-06-19 锋霖科技股份有限公司 Translation equipment in car room and automatic teller machine translation equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016167619A1 (en) * 2015-04-17 2016-10-20 (주)에스앤아이스퀘어 Voice recognition interpreter based on near field communication network and method for operating voice recognition interpreter
CN205581861U (en) * 2016-01-26 2016-09-14 北京纽思曼教育科技有限公司 Interpreting equipment
CN205584461U (en) * 2016-05-11 2016-09-14 青岛歌尔声学科技有限公司 Loudspeaker box
CN110933536A (en) * 2018-09-20 2020-03-27 台山市恒东音响科技有限公司 Sound box
JP3225366U (en) * 2019-10-29 2020-02-27 鋒霖科技股▲ふん▼有限公司Ｊｅｔｖｏｘ Ａｃｏｕｓｔｉｃ Ｃｏｒｐ． Earphone storage case device
CN210804431U (en) * 2019-10-29 2020-06-19 锋霖科技股份有限公司 Translation equipment in car room and automatic teller machine translation equipment

Also Published As

Publication number Publication date
CN112770206B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
CN112435650B (en) Multi-speaker and multi-language voice synthesis method and system
US20090144048A1 (en) Method and device for instant translation
AU2018201474A1 (en) Systems and methods for name pronunciation
US11528568B1 (en) Assisted hearing aid with synthetic substitution
JP5094120B2 (en) Speech recognition apparatus and speech recognition method
CN109686363A (en) A kind of on-the-spot meeting artificial intelligence simultaneous interpretation equipment
KR20190021409A (en) Method and apparatus for playing voice
CN104485100B (en) Phonetic synthesis speaker adaptive approach and system
KR20190005103A (en) Electronic device-awakening method and apparatus, device and computer-readable storage medium
CN109346057A (en) A kind of speech processing system of intelligence toy for children
CN114464180A (en) Intelligent device and intelligent voice interaction method
JP2000207170A (en) Device and method for processing information
CN112770206B (en) Multilingual intelligent translation megaphone based on off-line machine translation
JP2002062891A (en) Phoneme assigning method
Botinis et al. Focus identification in English, Greek and Swedish
JPH11109991A (en) Man machine interface system
WO2021020825A1 (en) Electronic device, control method thereof, and recording medium
KR102296925B1 (en) Network broadcasting system
CN108735049A (en) Deaf-mute's assistant phonation system and its vocal technique
CN110992984A (en) Audio processing method and device and storage medium
Hanumante et al. English text to multilingual speech translator using android
CN209657654U (en) Dazzle the intelligently globe of cruel shape
CN218768704U (en) Display equipment
CN111640448A (en) Audio-visual auxiliary method and system based on voice enhancement
Patten et al. The difference between shrieks and shrugs: Spectral envelope correlates with changes in pitch and loudness

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant