CN208314775U - The device of multi-functional real-time phonetic translation system - Google Patents

Abstract

The utility model is a kind of device of multi-functional real-time phonetic translation system, comprising be used to receive the voice of first language and form the receiving unit of first language signal, translation mould group that the first language signal is converted to second language signal, reception second language signal and issue second language voice output unit, second language signal is sent to the wireless module of communicator；In distally call or face-to-face talk, the utility model can be used directly in user, the voiced translation of first language is the voice of second language by " one-to-one " or " one-to-many " immediately, enable both sides' instant translation in distal end call or face-to-face talk, both sides are not limited by language, There is no impediment to speaking freely.

Description

The device of multi-functional real-time phonetic translation system

Technical field

The utility model be a kind of speech translation system device, particularly relate to one kind can distal end call and face-to-face When talk, immediately it is the voice of second language by the voiced translation of first language, links up both sides in call or talk and do not hinder Multi-functional real-time phonetic translation system device.

Background technique

There is many instant translating equipments or translation software on the market at present, but most translating equipment is all intended to The language of translation, using the translation software by its language translation at the languages of setting, then by the language after the translation utilize the electricity Screen or loudspeaker in sub-device play out, to achieve the effect that instant translation.

When participating in large-scale international conference or seminar, it will usually be provided with the earphone of synchronous translation, will be given a lecture with instant The language of person, interpretation immediately is the language for setting specific channel, and the mode of its instant translation is by multidigit at the scene point The interpreter that various language Fu Ze not translated, directly interprets language scene described in speaker, then in a broadcast manner, The content of interpretation is transmitted into the earphone of participant, to reach the effect interpreted immediately.

So, instant interpretation mode above-mentioned has following missing:

1. the one-side voice for receiving translation of user both can only be provided, and interactive talk can not be carried out, So when it is problematic need to put question to when, can not instant translation user put question to language, cause receive information on or deliver money When news, still by obstruction.

2. to interactive instant interpretation can be reached, it may be necessary to which everyone wears synchronous interpretation ear provided by meeting Machine, it is difficult to realize the synchronous interpretation in individualized talk, be still that obstruction is heavy in language communication.

Referring to Fig. 1, Fig. 1 is the schematic diagram that TaiWan, China announces M553001 Patent Case；At present just like Chinese platform The revealed technology contents of M553001 Patent Case are announced in gulf, may achieve the effect of synchronization interactive formula interpretation, as shown in Figure 1, The case discloses a kind of interpretation device 2 immediately, includes to receive the input unit 21 of first language voice stream, to should First language voice stream is converted into the processing unit 22 of second language voice stream, to compare the first language voice stream And the unit 23 of the second language voice stream is kept in, and the output list to export the second language voice stream Member 24, makes the first language voice stream be translated into the second language voice stream immediately, for the friendship of two kinds of different languages What is said or talked about person can achieve the effect that instant talk by the instant interpretation device.

Although the case can reach the effect for carrying out the instant translation talk of two interviewers face-to-face, the right case is only limitted to face Opposite can instant talk, if two interviewers be using communicator talk when, instant translation talk can not be carried out, therefore be still It is inconvenient.

In view of this, applicant satisfies the research and development experience for being engaged in related fields according to its many years, carried out deeply for the missing of preceding case Enter to inquire into, and carry out further investigated according to missing above-mentioned, and actively seek solution according to aforementioned need, after exerting for a long time Power research and repeatedly test, complete the utility model finally.

Utility model content

The main purpose of the utility model is to provide a kind of devices of real-time phonetic translation system, and particularly relating to one kind can In distally call or face-to-face talk, immediately it is the voice of second language by the voiced translation of first language, makes both sides remote The device of end call or multi-functional real-time phonetic translation system of linking up that nothing serious in talk face-to-face.

The purpose and effect of the device of the multi-functional real-time phonetic translation system of the utility model realized by technology below, It include receiving unit, translation mould group, output unit and communicator.

The receiving unit is corresponding language to receive the voice of first language, and by the speech recognition of first language Speech, and corresponding first language signal output is formed, it can be English, Spain which kind of language aforementioned first language, which does not limit, Language ... etc.；Wherein, which can connect identification unit, to recognize voice (English, Spanish ... of multilingual Deng), and in addition the identification unit can connect setting key, and preset identification language by setting key by user Priority picks.

The translation mould group is electrically connected with receiving unit, for receiving the first language signal from receiving unit, and The first language signal is translated to and is converted to corresponding second language signal, and the second language signal is exported.

The output unit connect with translation mould group, for receiving the second language signal of translation mould group, and issues correspondence The voice of second language.

The translation mould group connect wireless module with receiving unit, and wireless module can wireless transmission signal to communicator.

Connect it is aforementioned, when simultaneously someone say the voice of the language not of the same race such as English, Spanish, Japanese when, user can The cis-position of identification language is preset by setting key, such as can be set with English as the first identification language cis-position, Spain Language is the second identification language cis-position ..., and such identification unit can sequentially carry out language according to the identification language cis-position set by user Speech identification, so recognized unit forms speech signal after receiving unit receives the voice of multilingual after sequentially recognizing, and It the speech signal is transmitted to translation mould group according to cis-position carries out translation and form second language signal, then by communicator or defeated Unit issues the voice of second language out, finally, user can hear the voice of the second language after multilingual is translated.

By the combination of aforementioned structure, user issues the voice of first language to receiving unit, which will connect After the voice of the first language received, language corresponding to the voice of the first language can be first recognized, and form corresponding first Speech signal is sent to the translation mould group and translates into the first language pre- after translation mould group receives first language signal The second language first set, and form second language signal and be transmitted to output unit, second language letter is received by output unit Number, and the voice of second language is issued, when so that user hearing sound, it can directly hear the voice of second language.

Furthermore, user can directly communicate wirelessly transmission by communicator and wireless module, work as reception Instant translation can be directly carried out when incoming call or dial-out call, states it in detail, when receiving unit receives user's sending It can be automatically corresponding first language signal by the speech recognition of first language, and be sent to this and turn over when the voice of first language Mould group is translated, translation is carried out by translation mould group and forms second language signal, mould group is then translated and is sent to second language signal Wireless module, and second language signal is then transmitted back to communicator by wireless module, by communicator by second language signal It is communicated to conversation object with the voice of second language, so that conversation object can hear the voice of second language immediately；Meanwhile it conversing The voice of second language expressed by object, user can also be heard immediately by the utility model has translated into first language Voice, as long as therefore both sides have a side using the utility model, even if when distal end is conversed, after capable of also listening to other side's translation immediately Language, and language after expression translation, to other side, both sides, which link up, can break through aphasis, and overcomes arrogated to oneself using non-completely The fear that long language is talked.

In addition, the translation mould group has the built-in language chip for translating multilingual, and the expansion connecting with the chip Unit is filled, language chip can be carried out the expansion of language material by user by expansion unit, so that the utility model can carry out More accurately translate.

The device of the multi-functional real-time phonetic translation system is installed in ear microphone.

The earphone portion of the ear microphone set one group described in multi-functional real-time phonetic translation system device, and the ear The microphone part of machine microphone set another group described in multi-functional real-time phonetic translation system device.

Moreover, which can also be equipped with mobile application corresponding with the wireless module in ear microphone Program (APP) unit, so mobile applications (APP) unit can be exported by the sound that the ear microphone directly carries out Or input.

Detailed description of the invention

Fig. 1 is the schematic diagram of TaiWan, China bulletin M553001 Patent Case.

Fig. 2 is the preferred embodiment schematic diagram of the utility model.

Fig. 3 is the preferred embodiment application schematic diagram (one) of the utility model.

Fig. 4 is the preferred embodiment application schematic diagram (two) of the utility model.

Symbol description:

The device of 1 multi-functional real-time phonetic translation system, 11 receiving units, 12 translation mould groups, 13 output units,

14 wireless modules, 15 communicators, 16 ear microphones, 161 earphones, 162 microphones；

﹝ Xian You ﹞

2 instant interpretation devices, 21 input units, 22 processing units, 23 units, 24 output units.

Specific embodiment

There can be more detailed understanding for hope the purpose of this utility model, effect, feature and structure, hereby lift preferably real It applies example and cooperates Detailed description of the invention as after.

Firstly, referring to Fig. 2, Fig. 2 is the preferred embodiment schematic diagram of the utility model.

The device 1 of the multi-functional real-time phonetic translation system of the utility model preferred embodiment, include receiving unit 11, Translate mould group 12, output unit 13, wireless module 14, communicator 15.

The receiving unit 11 is corresponding to receive the voice of first language, and by the speech recognition of first language Language, and form corresponding first language signal output；Wherein, which can connect identification unit, more to recognize The voice of kind of language, can recognize the language such as English, Spanish ..., and the identification unit can connect setting key, and by User presets the priority picks of identification language by setting key.

The translation mould group 12 is electrically connected, for receiving the first language from receiving unit 11 with receiving unit 11 Signal, and the first language signal is translated to and is converted to corresponding second language signal, and the second language signal is exported.

The output unit 13 is connect, for receiving the second language signal of translation mould group 12, concurrently with translation mould group 12 The voice of second language is corresponded to out；Wherein, which can connect public address equipment, such as: everyone in Conference Hall Personal microphone on seat issues the voice of second language by individual's microphone.

The translation mould group 12 connect wireless module 14 with receiving unit 11, and wireless module 14 can wireless transmission signal to logical Talk about device 15；Wherein, wireless module 14 can carry out wireless transmission signal to communicator 15 by bluetooth.

Connect it is aforementioned, when simultaneously someone say the voice of the language not of the same race such as English, Spanish, Japanese when, user can To preset the cis-position of identification language by setting key, such as can set with English as the first identification language cis-position, western class Tooth language is the second identification language cis-position ..., and such identification unit can sequentially be carried out according to the identification language cis-position set by user Language idendification, so recognized unit forms language letter after receiving unit 11 receives the voice of multilingual after sequentially recognizing Number, and according to cis-position the speech signal is transmitted to translation mould group 12 and carries out translation and form second language signal, then filled by call Set 15 or output unit 13 issue the voice of second language, last user can hear second after multilingual is translated The voice of language.

By the combination of aforementioned structure, user issues the voice of first language to receiving unit 11, and receiving unit 11 It can be redefined for recognizing language automatically or manually set received language, first language is issued with user in the present embodiment Voice be English Phonetics for illustrate；After receiving unit 11 receives English Phonetics, it can first recognize and be confirmed as English, then will The voice of English is correspondingly formed English language signal, and is sent to the translation mould group 12, and translation mould group 12 receives English language After signal, i.e., English language signal being translated into preset second language signal, (the present embodiment is to set second language letter Number to illustrate for Chinese language signal), it is single that the Chinese language signal that translation is completed is transmitted to by output by translation mould group 12 Member 13 is issued the Chinese language signal that translation is completed with Chinese speech by output unit 13, when so that user hearing sound, It is exactly directly to hear Chinese speech.

In other words, when the interviewer of two different languages or one-to-many people talk with, as long as there is a side practical new using this Type can directly carry out the talk of instant translation, the either language of uppick other side by the utility model and other side, or The language that user is told about, all can be when being passed to both sides, and instant translation is the language of both sides' setting, reaches instant translation Effect.

Furthermore, transmission is communicated wirelessly by communicator 15 and wireless module 14, user can receive When incoming call or dial-out call, directly progress instant translation for example using user as Chinese language user, and is conversed Object is for English language user, when user issues Chinese speech to receiving unit 11, which is recognized User is issued when being Chinese, i.e., Chinese speech is switched to Chinese language signal and be sent to translation mould group 12, pass through translation Mould group 12 translates into English language signal and is sent to wireless module 14, which is transmitted back to by wireless module 14 Communicator 15, and conversation object is communicated to the voice of English, so that conversation object can listen to the language for being translated as English immediately Sound.

Connect it is aforementioned, when conversation object issue English Phonetics when, English Phonetics is wirelessly transferred by the communicator of user To wireless module 15, English Phonetics is then first sent to receiving unit 11 and recognized by wireless module 15, by receiving unit 11 When English is confirmed as in identification, i.e., English Phonetics is switched into English language signal and be sent to translation mould group 12, and translates 12 meeting of mould group English language signal is translated as corresponding Chinese language signal, and is sent to the Chinese language signal by wireless module 14 Communicator 15, and directly provide user by communicator 15 and listen to the Chinese speech that translation is completed, thus user The talk of instant translation call can be reached by the utility model with conversation object.

The preferred embodiment application schematic diagram (one) that Fig. 3,4, Fig. 3 are the utility model is please referred to, Fig. 4 is the utility model The application schematic diagram (two) of preferred embodiment.

As shown in Figure 3, wherein the utility model can be designed as to the aspect of ear microphone 16, and the ear microphone 16 161 part of earphone can set one group of the utility model, and 162 part of microphone can set another group of the utility model, so exist User synchronizes the language for hearing its setting, can also be translated as immediately the language of setting simultaneously when issuing the voice of language Speech.

Therefore, as long as user wears the ear microphone 16 and can directly carry out one-to-one or one-to-many talk, The language of (black arrow is that the voice of language passes direction in Fig. 3) either uppick, or the language told about, work as earphone 161 when receiving the voice of colloquist, directly by the voiced translation can be the language of user's setting, and issue set language Speech sound to user, as long as and user directly to microphone 162 issue voice, the microphone 162 i.e. can automatic translation, And the effect of issuing the voice for the interpreter language that setting is listened to colloquist, instant translation can be practiced.

Furthermore, earphone 161 part provide user listen to other side it is translated after voice, and microphone 162 Part, which then provides user, directly to go out the voice of other side by instant translation, and the language according to used in other side, setting are When the language translated, thus user will either be linked up with which kind of language with people, can all be advanced freely, or even also It can completely dispense with and the object of audience or dialogue is allowed to wear specific earphone or translating equipment 12, user in large size speech Set translation can directly be told about to the language of other side, thus user on one-to-one or one-to-many talk and communication more For convenience.

As shown in Figure 2,4, the wireless module 14 in ear microphone 16 is wirelessly transferred with communicator 15, when call fills The incoming call that 15 receive or the call transferred to are set, can directly be conversed by the utility model, user can be straight at this time It connected ear microphone 16 and hears that conversation object has translated into the voice of setting language, also capable of emitting translated completion is set It is set to the voice of other side's language, and then directly engages in the dialogue with conversation object.

In this way, which user, which either passes through communicator 15, carries out distal end dialogue, or talked all with people face-to-face Can direct synchronous translation, and can hear synchronous translation complete language, with people link up will completely it is unobstructed, and more into One step also can be applicable to open speech, directly synchronize translation by the utility model, cooperate public address equipment to make on the scene more Position audience can directly hear the language that translation is completed, overcome completely for it is non-be good at language carry out talk dialogue, or openly The fear of speech.

Still further, the utility model can also be installed on public address equipment, the personal Mike of such as large-scale lecture hall Wind, as long as so spokesman can be directly translated as to the language of speaker on special object or platform, greatly by individual's microphone Width reduce meeting in language communication difficulty problem, therefore pass through the utility model anyone all can with any language with it is any People's talk.

In addition, the translation mould group 12 has the built-in language chip for translating multilingual, and connect with the chip Expansion unit, language chip can be carried out the expansion of language material by user by expansion unit, so that the utility model can be into The more accurate translation of row.

Moreover, which can also be equipped with movement corresponding with the wireless module 14 in ear microphone Application program (APP) unit, so the sound that mobile applications (APP) unit can directly be carried out by the ear microphone Output or input.

In summary, the device of " multi-functional real-time phonetic translation system " described in this case is really existing similar technique field Technology cannot and, that is, this case really have the advantages that it is following:

1. face-to-face talk instant translation: cooperated by receiving unit, translation mould group, output unit three, it can be one As in the case of talk, reach to synchronize and listen to the language that translation is completed, and issue translation to the language of other side, solve language not Logical problem.

2. distal end talk instant translation: carrying out wireless transmission signal by communicator and wireless module, and can pass through The utility model directly carries out two-way translation (listen with says), so can in call, can also instant translation, make both ends converse not by Language limitation, talks animatedly and does not hinder.

3. instant translation is given a lecture: audience is without putting on specific earphone, and without specific channel is adjusted to, speaker can also pass through this The language that utility model directly completes translation, is communicated to multiple audiences by microphone or public address equipment.

Therefore the utility model has splendid creativeness and practicability in similar product, while looking through domestic and international pass After the technical data document of this class formation, identical or approximate construction is found no really and is present in front of this case application, because This this case should meet the patent requirement of " novelty ", " practicability " and " creativeness ", and whence is filed an application in accordance with the law.

Only, as described above, the only preferred embodiment of the utility model, such as apply the utility model specification And other equivalent structure variation persons carried out by claim, it ought to be included in the claim of the utility model.

Claims (9)

1. a kind of device of multi-functional real-time phonetic translation system includes receiving unit, translation mould group, output unit and call Device；

The receiving unit is corresponding language to receive the voice of first language, and by the speech recognition of first language, and Form corresponding first language signal output；

The translation mould group is electrically connected with receiving unit, for receiving the first language signal from receiving unit, and should Corresponding second language signal is translated and be converted to first language signal, and the second language signal is exported；

The output unit is connect with translation mould group, for receiving the second language signal of translation mould group, and issues corresponding second The voice of language；

It is characterized by: the translation mould group connect wireless module with receiving unit, and wireless module can wireless transmission signal to logical Talk about device.

2. the device of multi-functional real-time phonetic translation system as described in claim 1, which is characterized in that it is installed on earphone wheat In gram wind.

3. the device of multi-functional real-time phonetic translation system as claimed in claim 2, which is characterized in that the ear microphone Earphone portion set one group described in multi-functional real-time phonetic translation system device, and the microphone part of the ear microphone is set The device of multi-functional real-time phonetic translation system described in another group.

4. the device of multi-functional real-time phonetic translation system as claimed in claim 2, which is characterized in that the communicator is equipped with Mobile applications unit corresponding with the wireless module in the ear microphone.

5. the device of multi-functional real-time phonetic translation system as described in claim 1, which is characterized in that the wireless module is with indigo plant Tooth carries out wireless transmission signal to communicator.

6. the device of multi-functional real-time phonetic translation system as described in claim 1, which is characterized in that the translation mould group has The built-in language chip for translating multilingual, and the expansion unit being connect with the chip.

7. the device of multi-functional real-time phonetic translation system as described in claim 1, which is characterized in that output unit connection Public address equipment.

8. the device of multi-functional real-time phonetic translation system as described in claim 1, which is characterized in that receiving unit connection Identification unit, to recognize the voice of multilingual.

9. the device of multi-functional real-time phonetic translation system as claimed in claim 8, which is characterized in that identification unit connection Set key.