CN108228575A - Voiced translation exchange method and system - Google Patents
Voiced translation exchange method and system Download PDFInfo
- Publication number
- CN108228575A CN108228575A CN201711384184.6A CN201711384184A CN108228575A CN 108228575 A CN108228575 A CN 108228575A CN 201711384184 A CN201711384184 A CN 201711384184A CN 108228575 A CN108228575 A CN 108228575A
- Authority
- CN
- China
- Prior art keywords
- server
- translation
- speech
- data
- translation result
- 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.)
- Pending
Links
- 238000013519 translation Methods 0.000 title claims abstract description 353
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 76
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 76
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 8
- 235000013399 edible fruits Nutrition 0.000 claims description 6
- 230000006870 function Effects 0.000 abstract description 24
- 230000014616 translation Effects 0.000 description 302
- 230000005540 biological transmission Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000002194 synthesizing effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000007306 turnover Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010189 synthetic method Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the present invention provides a kind of voiced translation exchange method and system, belongs to voiced translation technical field.This method includes:After network connection is established with target voice interpreting equipment, voice data and language information are sent to first server, so that first server translates voice data based on language information;Receive the translation result that first server returns, translation result is sent to second server, so that translation result is forwarded to target voice interpreting equipment by second server, translation result acquisition speech synthesis data is based on by target voice interpreting equipment and reports speech synthesis data.Realize data forwarding and interpretative function since the network architecture can be based between source speech translation apparatus and target voice interpreting equipment, and the distance between unlimited speech translation apparatus so that linked up between speech translation apparatus with exchange it is more convenient.
Description
Technical field
The embodiment of the present invention relates to voiced translation technical field, more particularly, to a kind of voiced translation exchange method and is
System.
Background technology
At present in the case of language obstacle, user is wished in the form of session operational scenarios, by a kind of language conversion into another
Kind language, realizes more naturally across languages communications.Based on the demand, provided in the relevant technologies a kind of based on Bluetooth technology
Voiced translation exchange method.Specifically, the two side users linked up carry out voiced translation each by an interpreting equipment
Interaction, i.e., after two interpreting equipments establish bluetooth connection, an interpreting equipment by the voice data of user A by Bluetooth transmission extremely
Another interpreting equipment, another interpreting equipment to receive voice data translate and to translation result carry out voice conjunction
Into giving user B so that phonetic synthesis result be reported.Due to being only applicable to short haul connection in Bluetooth transmission, when two translations
Voiced translation interaction cannot be then carried out when distant between equipment, so as to less in linking up convenience between user.
Invention content
To solve the above-mentioned problems, the embodiment of the present invention provides one kind and overcomes the above problem or solve at least partly
State the voiced translation exchange method and system of problem.
It is according to embodiments of the present invention in a first aspect, providing a kind of voiced translation exchange method, this method includes:
After network connection is established with target voice interpreting equipment, voice data and language information are sent to the first clothes
Business device, so that first server translates voice data based on language information, language information is translated including at least target
Languages type;
The translation result that first server returns is received, translation result is sent to second server, so that the second clothes
Translation result is forwarded to target voice interpreting equipment by business device, and being based on translation result by target voice interpreting equipment obtains voice conjunction
Into data and report speech synthesis data.
Method provided in an embodiment of the present invention, source speech translation apparatus are establishing network connection with target voice interpreting equipment
Afterwards, voice data and language information are sent to first server, so that first server is based on language information to voice
Data are translated, and language information includes at least target and translates languages type.Source speech translation apparatus receives first server and returns
The translation result returned, is sent to second server, so that translation result is forwarded to target by second server by translation result
Speech translation apparatus is based on translation result acquisition speech synthesis data by target voice interpreting equipment and reports phonetic synthesis number
According to.Data forwarding and translation are realized since the network architecture can be based between source speech translation apparatus and target voice interpreting equipment
Function, and the distance between unlimited speech translation apparatus, so that communication is more convenient with exchanging between speech translation apparatus.
The possible realization method of with reference to first aspect the first, in second of possible realization method, this method is also
Including:
Log-on message is sent to third server, so that third server, which is based on log-on message, carries out login authentication;
If receive the return of third server is verified message, is established by second server and turned over target voice
Translate the network connection between equipment.
Second aspect according to embodiments of the present invention, provides a kind of voiced translation exchange method, and this method includes:
After network connection is established with source speech translation apparatus, the translation result of second server forwarding, translation knot are received
Fruit is sent to second server, the voice that translation result sends source speech translation apparatus by first server by source speech ciphering equipment
Data obtain after being translated;
Speech synthesis data is obtained, and report speech synthesis data based on translation result.
With reference to the first possible realization method of second aspect, in the first possible implementation, this method is also
Including:
Log-on message is sent to third server, so that third server, which is based on log-on message, carries out login authentication;
If receive the return of third server is verified message, established and source voiced translation by second server
Network connection between equipment.
With reference to the first possible realization method of second aspect, in second of possible realization method, based on translation
As a result speech synthesis data is obtained, including:
Translation result is sent to the 4th server, so that the 4th server, which is based on translation result, carries out phonetic synthesis,
Obtain speech synthesis data;
Obtain the speech synthesis data of the 4th server return.
The third aspect according to embodiments of the present invention, provides a kind of voiced translation interactive system, which includes:Source language
Sound interpreting equipment, target voice interpreting equipment, first server and second server;
After establishing network connection between source speech translation apparatus and target voice interpreting equipment, source speech ciphering equipment is by voice number
According to this and language information is sent to first server;First server translates voice data based on language information, languages
Information includes at least target translation languages type and the corresponding source languages type of voice data;
Source speech translation apparatus receives the translation result that first server returns, and translation result is sent to second service
Device;Translation result is forwarded to target voice interpreting equipment by second server, and target voice interpreting equipment is obtained based on translation result
It takes speech synthesis data and reports speech synthesis data.
With reference to the first possible realization method of the third aspect, in second of possible realization method, the system is also
Including:Third server;Third server, for being stepped on respectively to source speech translation apparatus and target voice interpreting equipment
Record verification, and in source speech translation apparatus and target voice interpreting equipment respectively by verification after, the source voiced translation of foundation is set
Network connection between the standby interpreting equipment with target voice.
With reference to the first possible realization method of the third aspect, in the third possible realization method, the system is also
Including:4th server;4th server for receiving the translation result of target voice interpreting equipment transmission, and is tied translation
Fruit carries out phonetic synthesis, obtains speech synthesis data;Target voice interpreting equipment, for obtaining the voice that the 4th server returns
Generated data, and report speech synthesis data.
Fourth aspect according to embodiments of the present invention, provides an introduces a collection speech translation apparatus, which includes:
First sending module, for after network connection is established with target voice interpreting equipment, by voice data and language
Kind information is sent to first server, so that first server translates voice data based on language information, languages letter
Breath includes at least target and translates languages type;
Translation result for receiving the translation result of first server return, is sent to the second clothes by the second sending module
Business device, so that translation result is forwarded to target voice interpreting equipment by second server, is based on by target voice interpreting equipment
Translation result obtains speech synthesis data and reports speech synthesis data.
5th aspect according to embodiments of the present invention, provides a kind of target voice interpreting equipment, which includes:
Receiving module, for after network connection is established with source speech translation apparatus, receiving turning over for second server forwarding
It translates as a result, translation result is sent to second server by source speech ciphering equipment, translation result is by first server to source voiced translation
The voice data that equipment is sent obtains after being translated;
Broadcasting module obtains speech synthesis data, and report speech synthesis data for being based on translation result.
It should be understood that above general description and following detailed description is exemplary and explanatory, it can not
Limit the embodiment of the present invention.
Description of the drawings
Fig. 1 is a kind of flow diagram of voiced translation exchange method of the embodiment of the present invention;
Fig. 2 is the flow diagram of another voiced translation exchange method of the embodiment of the present invention;
Fig. 3 is a kind of block diagram of voiced translation interactive system of the embodiment of the present invention;
Fig. 4 is the block diagram of another voiced translation interactive system of the embodiment of the present invention;
Fig. 5 is the block diagram of an introduces a collection speech translation apparatus of the embodiment of the present invention;
Fig. 6 is a kind of block diagram of target voice interpreting equipment of the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, the specific embodiment of the embodiment of the present invention is described in further detail.With
Lower embodiment is used to illustrate the embodiment of the present invention, but be not limited to the range of the embodiment of the present invention.
At present in the case of language obstacle, user is wished in the form of session operational scenarios, by a kind of language conversion into another
Kind language, realizes more naturally across languages communications.It is by real by Bluetooth technology between two interpreting equipments in the relevant technologies
Existing voiced translation interaction.Since Bluetooth transmission is only applicable to short haul connection, so as to when distant between two equipment then
It cannot carry out voiced translation interaction.For said circumstances, an embodiment of the present invention provides a kind of voiced translation exchange methods.The party
Method is applicable to " private chat pattern " between two voiced translation interactive devices, is equally applicable to more voiced translation interactive devices
Between " group chat pattern ", the embodiment of the present invention is not especially limited this.
It is respectively device A and equipment B with voiced translation interactive device for above-mentioned " private chat pattern ", the corresponding use of device A
For family first says that English, the corresponding user's second of equipment B are spoken Chinese.When user's first is made a speech, device A can be used as source voiced translation
Equipment, equipment B can be used as target voice interpreting equipment.The English speech of user's first, which is transferred to equipment B, to be reported with Chinese.
Conversely, when user's second is made a speech, equipment B can be used as source speech translation apparatus, and device A can be used as target voice interpreting equipment.
The Chinese speech of user's second, which is transferred to equipment B, to be reported with English.
It is respectively device A, equipment B and equipment C with voiced translation interactive device for above-mentioned " group chat pattern ", device A pair
The user's first answered says English, and the corresponding user's second of equipment B is spoken Chinese, and the corresponding users of equipment C third are said for French.When in tripartite
The speech of user's first when, device A can be used as source speech translation apparatus, and equipment B and equipment C can be translated respectively as target voice
Equipment.The English speech of user's first, which is transferred to equipment B, to be reported with Chinese, and the English speech of user's first is transferred to equipment C
It can be reported with French.I.e. each party can be used as source speech translation apparatus, be also used as target voice interpreting equipment.When
During either one speech, speaking party can be used as source speech translation apparatus, and remaining each party can be used as target voice interpreting equipment.
It should be noted that source speech translation apparatus all can be smart mobile phone, intelligent hand with target voice interpreting equipment
Any one in table and smart machine, the embodiment of the present invention is not especially limited this.For example, source speech translation apparatus and mesh
It can be intelligent translation machine to mark speech translation apparatus, and intelligent translation machine is one kind in smart machine.Smart machine in addition to for
Can also be computer or intelligent vehicle-carried equipment etc., the embodiment of the present invention is not especially limited this except intelligent translation machine.
With reference to above application scene, an embodiment of the present invention provides a kind of voiced translation exchange method, this method is applicable
In source speech translation apparatus.Referring to Fig. 1, this method includes:It 101st, will after network connection is established with target voice interpreting equipment
Voice data and language information are sent to first server so that first server be based on language information to voice data into
Row translation, language information include at least target and translate languages type;102nd, the translation result that first server returns is received, will be turned over
It translates result and is sent to second server, so that translation result is forwarded to target voice interpreting equipment by second server, by mesh
Mark speech translation apparatus is based on translation result and obtains speech synthesis data and report speech synthesis data.
Before step 101 is performed, the corresponding user of source speech translation apparatus use corresponding with target voice interpreting equipment
Family can pre-set languages type used in itself respectively.It is built between source speech translation apparatus and target voice interpreting equipment
After vertical network connection, it can be communicated between source speech translation apparatus and target voice interpreting equipment, to inform other side's local terminal
Languages type used by a user.In addition, source speech translation apparatus can also obtain voice data input by user.Specifically, source
It may be provided with voice key on speech translation apparatus, when detecting that user presses voice key, source speech translation apparatus can start to record
Sound.When detecting that user unclamps voice key, source speech translation apparatus can stop recording, and can obtain voice number input by user
According to.
Source speech translation apparatus can send voice data and language information after voice data input by user is obtained
To first server.Wherein, the languages type used by a user of target voice interpreting equipment side is may include in language information, i.e.,
Target translates languages type.Certainly, the languages used by a user of source speech translation apparatus side can also be included in language information
Type, i.e. source translate languages type, and the embodiment of the present invention is not especially limited this.
First server can be based on language after the voice data of source speech translation apparatus transmission and language information is received
Kind information translates voice data.Specifically, voice data first can be converted into text data, then will be literary by first server
Notebook data is converted to target translation languages type by source translation languages type, so as to obtain the translation result of voice data.First
Server is obtaining translation result, can translation result directly be back to source speech translation apparatus.
In addition to this, first server can also first be packaged translation result, then return and seal to source speech translation apparatus
Structural data after dress, so that source speech translation apparatus obtains translation result by way of parsing.Wherein, specific data
Structure can be set according to demand, and the embodiment of the present invention is not especially limited this.For example, with the corresponding text of voice data
Data are the weather of today " Hefei how ", and target translation languages type is for English.The structure that first server returns
It can be following form to change data:
{"ret":"0","calltime":"593.805000","result":{"uuid":"
bbe7e44e47834811d34219d7efaaad0eisap","results":[{"oriLangCountry":"cn","
translated":"How is the weather today in Hefei","transLangCountry":"en",
"original":" how is the weather of Hefei today"}],"pluginTime":590,"rc":0,"
allTime":591,"sourceNames":["translate"]}};
In the examples described above, " oriLangCountry " represents source translation languages type, " transLangCountry " table
Show that target translates languages type." original " represents the corresponding text data of voice data." translated " represents translation
As a result.Structural data can also carry the other information such as Universally Unique Identifier " uuid " other than carrying translation result,
The embodiment of the present invention is not especially limited this.
Source speech translation apparatus can carry out structural data after the structural data for receiving first server return
Parsing, so as to obtain translation result.Translation result directly can be sent to by source speech translation apparatus after translation result is obtained
Two servers, so as to which translation result can be forwarded to target voice interpreting equipment by second server.It should be noted that source voice
The facility information of target voice interpreting equipment can be also sent to by interpreting equipment when translation result is sent to second server
Second server.For example, the device id of target voice interpreting equipment can be sent to second server, so that second server
Target voice interpreting equipment is determined based on device id.Certainly, source speech translation apparatus to second server in addition to sending translation knot
Except fruit and facility information, other data can also be sent, the embodiment of the present invention is not especially limited this.When the data of transmission
When more, the data of transmission can be also packaged by source speech translation apparatus, then send the structure after encapsulation to second server
Change data.Wherein, structural data may include translation result, and specific data structure can be set according to demand, and the present invention is real
Example is applied to be not especially limited this.For example, using translation result as " How is the weather today in Hefei", source
The structural data that speech translation apparatus is sent can be following form:
{"messageType":"text","message":"How is the weather today in
Hefei","from":" device A ", " to ":" equipment B ", " messageTime ":"2017/10/1714:00:01"}
In the examples described above, " message " represents translation result.Field behind " from " is coming for translation result
Source namely the facility information of source speech translation apparatus, such as the device id of source speech translation apparatus, the field behind " to " is mesh
The facility information of speech translation apparatus is marked, such as the device id of target voice interpreting equipment.In addition, it can also be wrapped in structural data
The time for sending the data and the type of the data etc. are included, the embodiment of the present invention is not especially limited this.
Translation result can be forwarded to target by second server after the translation result that source speech translation apparatus is sent is connected to
Speech translation apparatus obtains speech synthesis data, and report voice conjunction so as to which target voice interpreting equipment can be based on translation result
Into data.
It should be noted that first server from second server can be two different class servers in the above process.
First server can also be same class server with second server, i.e., data forwarding and interpretative function are concentrated on one
In server, the embodiment of the present invention is not especially limited this.
Method provided in an embodiment of the present invention, source speech translation apparatus are establishing network connection with target voice interpreting equipment
Afterwards, voice data and language information are sent to first server, so that first server is based on language information to voice
Data are translated, and language information includes at least target and translates languages type.Source speech translation apparatus receives first server and returns
The translation result returned, is sent to second server, so that translation result is forwarded to target by second server by translation result
Speech translation apparatus is based on translation result acquisition speech synthesis data by target voice interpreting equipment and reports phonetic synthesis number
According to.Data forwarding and translation are realized since the network architecture can be based between source speech translation apparatus and target voice interpreting equipment
Function, and the distance between unlimited speech translation apparatus, so that communication is more convenient with exchanging between speech translation apparatus.
Content based on above-described embodiment, it is contemplated that the communication security between speech translation apparatus, speech translation apparatus can
To realize that voiced translation interacts again after by verification.As a kind of alternative embodiment, the embodiment of the present invention additionally provides one kind
Verification method, this method include:Log-on message is sent to third server so that third server be based on log-on message into
Row login authentication;If receive third server return be verified message, pass through second server establish and target language
Network connection between sound interpreting equipment.
In above process, log-on message can be login username.Wherein, user can be obtained by pre-registered mode
Take login username or can also be directly using the unique identifier of speech translation apparatus as login username, the present invention is implemented
Example is not especially limited this.Third server can turn over source voice after the log-on message for receiving source speech translation apparatus
The log-on message for translating equipment is compared with the log-on message in default log-on message list.If source speech translation apparatus is stepped on
Information is recorded in default log-on message list, then is verified message to the return of source speech translation apparatus.At this point, for by voice
The immediate news systems formed constructed by interpreting equipment, state of the source speech translation apparatus in immediate news systems be it is online,
And source speech translation apparatus can establish the network connection between target voice interpreting equipment by second server.
It should be noted that above-mentioned all alternative embodiments, may be used the optional implementation that any combination forms the present invention
Example, this is no longer going to repeat them.
Content based on above-described embodiment, an embodiment of the present invention provides a kind of voiced translation exchange methods, and this method can
Suitable for target voice interpreting equipment.Referring to Fig. 2, this method includes:201st, network connection is being established with source speech translation apparatus
Afterwards, the translation result of second server forwarding is received, translation result is sent to second server, translation result by source speech ciphering equipment
The voice data sent by first server to source speech translation apparatus obtains after translating;202nd, it is obtained based on translation result
Speech synthesis data, and report speech synthesis data.
Before step 201 is performed, the corresponding user of target voice interpreting equipment use corresponding with source speech translation apparatus
Family can pre-set languages type used in itself respectively.It is built between target voice interpreting equipment and source speech translation apparatus
After vertical network connection, it can be communicated between target voice interpreting equipment and source speech translation apparatus, to inform other side's local terminal
Languages type used by a user.Source speech translation apparatus can obtain voice data input by user.Specifically, source voiced translation
It may be provided with voice key in equipment, when detecting that user presses voice key, source speech translation apparatus can start to record.Work as detection
When unclamping voice key to user, source speech translation apparatus can stop recording, and can obtain voice data input by user.
Source speech translation apparatus can send voice data and language information after voice data input by user is obtained
To first server.Wherein, the languages type used by a user of target voice interpreting equipment side is may include in language information, i.e.,
Target translates languages type.Certainly, the languages used by a user of source speech translation apparatus side can also be included in language information
Type, i.e. source translate languages type, and the embodiment of the present invention is not especially limited this.
First server can be based on language after the voice data of source speech translation apparatus transmission and language information is received
Kind information translates voice data.Specifically, voice data first can be converted into text data, then will be literary by first server
Notebook data is converted to target translation languages type by source translation languages type, so as to obtain the translation result of voice data.First
Server is obtaining translation result, can translation result directly be back to source speech translation apparatus.
In addition to this, first server can also first be packaged translation result, then return and seal to source speech translation apparatus
Structural data after dress, so that source speech translation apparatus obtains translation result by way of parsing.Wherein, specific data
Structure can be set according to demand, and the embodiment of the present invention is not especially limited this.For example, with the corresponding text of voice data
Data are the weather of today " Hefei how ", and target translation languages type is for English.The structure that first server returns
It can be following form to change data:
{"ret":"0","calltime":"593.805000","result":{"uuid":"
bbe7e44e47834811d34219d7efaaad0eisap","results":[{"oriLangCountry":"cn","
translated":"How is the weather today in Hefei","transLangCountry":"en",
"original":" how is the weather of Hefei today"}],"pluginTime":590,"rc":0,"
allTime":591,"sourceNames":["translate"]}};
In the examples described above, " oriLangCountry " represents source translation languages type, " transLangCountry " table
Show that target translates languages type." original " represents the corresponding text data of voice data." translated " represents translation
As a result.Structural data can also carry the other information such as Universally Unique Identifier " uuid " other than carrying translation result,
The embodiment of the present invention is not especially limited this.
Source speech translation apparatus can carry out structural data after the structural data for receiving first server return
Parsing, so as to obtain translation result.Translation result directly can be sent to by source speech translation apparatus after translation result is obtained
Two servers, so as to which translation result can be forwarded to target voice interpreting equipment by second server.
It should be noted that source speech translation apparatus is by translation result when being sent to second server, it can also be by target
The facility information of speech translation apparatus is sent to second server.For example, the device id of target voice interpreting equipment can be sent
To second server, so that second server determines target voice interpreting equipment based on device id.Certainly, source voiced translation is set
For other than sending translation result and facility information to second server, other data, the embodiment of the present invention can also be sent
This is not especially limited.When the data of transmission are more, the data of transmission can be also packaged by source speech translation apparatus, then
The structural data after encapsulation is sent to second server.Wherein, structural data may include translation result, specific data structure
It can be set according to demand, the embodiment of the present invention is not especially limited this.For example, using translation result as " How is the
weather today in Hefei", the structural data that source speech translation apparatus is sent can be following form:
{"messageType":"text","message":"How is the weather today in
Hefei","from":" device A ", " to ":" equipment B ", " messageTime ":"2017/10/1714:00:01"}
In the examples described above, " message " represents translation result.Field behind " from " is coming for translation result
Source namely the facility information of source speech translation apparatus, such as the device id of source speech translation apparatus, the field behind " to " is mesh
The facility information of speech translation apparatus is marked, such as the device id of target voice interpreting equipment.In addition, it can also be wrapped in structural data
The time for sending the data and the type of the data etc. are included, the embodiment of the present invention is not especially limited this.
Translation result can be forwarded to target by second server after the translation result that source speech translation apparatus is sent is connected to
Speech translation apparatus.Target voice interpreting equipment can be based on translation result and obtain phonetic synthesis number after translation result is received
According to, and report speech synthesis data.
It should be noted that first server from second server can be two different class servers in the above process.
First server can also be same class server with second server, i.e., data forwarding and interpretative function are concentrated on one
In server, the embodiment of the present invention is not especially limited this.
Method provided in an embodiment of the present invention, target voice interpreting equipment are establishing network connection with source speech translation apparatus
Afterwards, the translation result of second server forwarding is received.Wherein, translation result is sent to second server by source speech ciphering equipment, turns over
It translates after result is translated by the voice data that first server sends source speech translation apparatus and obtains.Target voice translation is set
For after translation result is received, speech synthesis data is obtained, and report speech synthesis data based on translation result.Due to source language
The network architecture can be based between sound interpreting equipment and target voice interpreting equipment and realizes data forwarding and interpretative function, and it is unlimited
The distance between speech translation apparatus, so that communication is more convenient with exchanging between speech translation apparatus.
Content based on above-described embodiment, it is contemplated that the communication security between speech translation apparatus, speech translation apparatus can
To realize that voiced translation interacts again after by verification.As a kind of alternative embodiment, the embodiment of the present invention additionally provides one kind
Verification method, this method include:Log-on message is sent to third server so that third server be based on log-on message into
Row login authentication;If receive third server return be verified message, pass through second server establish and target language
Network connection between sound interpreting equipment.
In above process, log-on message can be login username.Wherein, user can be obtained by pre-registered mode
Take login username or can also be directly using the unique identifier of speech translation apparatus as login username, the present invention is implemented
Example is not especially limited this.Third server, can be by target language after the log-on message for receiving target voice interpreting equipment
The log-on message of sound interpreting equipment is compared with the log-on message in default log-on message list.If target voice translation is set
Standby log-on message is then verified message in default log-on message list to the return of target voice interpreting equipment.It is at this point, right
In the immediate news systems formed as constructed by speech translation apparatus, shape of the target voice interpreting equipment in immediate news systems
State is online, and the network that target voice interpreting equipment can be established by second server between the speech translation apparatus of source connects
It connects.
Content based on above-described embodiment, as a kind of alternative embodiment, the embodiment of the present invention additionally provides a kind of voice
Synthetic method.This method includes:Translation result is sent to the 4th server, so that the 4th server is based on translation result
Phonetic synthesis is carried out, obtains speech synthesis data;Obtain the speech synthesis data of the 4th server return.
In addition, the first server that above-described embodiment is related to is mainly used for realizing speech recognition and interpretative function (i.e. pair
Voice data is identified, and recognition result is translated), second server is mainly used for realizing that forwarding capability (will turn over
Translate result and target voice interpreting equipment be forwarded to by source speech translation apparatus), third server is mainly used for realizing login authentication
Function (carries out login authentication) to speech translation apparatus, and the 4th server is mainly used for realizing speech-sound synthesizing function (i.e. to turning over
It translates result and carries out phonetic synthesis).Above-mentioned four functions can be integrated in a kind of server namely first server, second service
Device, third server and the 4th server correspond to same class server.Also above-mentioned four functions can be split, and pass through
Different server is realized.For example, four class servers can be divided into;Alternatively, forwarding capability realizes that login is tested by a kind of server
Card, speech recognition, translation and phonetic synthesis are realized by another kind of server namely first server, third server and
Four servers correspond to same class server.Alternatively, forwarding capability is realized with login authentication by a kind of server, i.e. second service
Device same class server corresponding with third server;And speech recognition, translation and phonetic synthesis are realized by another kind of server,
That is first server same class server corresponding with the 4th server.
It should be noted that above-mentioned all alternative embodiments, may be used the optional implementation that any combination forms the present invention
Example, this is no longer going to repeat them.
Content based on above-described embodiment, an embodiment of the present invention provides a kind of voiced translation interactive systems.Referring to Fig. 3,
The system includes:Source speech translation apparatus 301, target voice interpreting equipment 302, first server 303 and second server
304;
After network connection being established between source speech translation apparatus 301 and target voice interpreting equipment 302, source speech ciphering equipment
Voice data and language information are sent to first server 303 by 301;First server 303 is based on language information to voice
Data are translated, and language information includes at least target translation languages type and the corresponding source languages type of voice data;
Source speech translation apparatus 301 receives the translation result that first server 303 returns, and translation result is sent to the
Two servers 304;Translation result is forwarded to target voice interpreting equipment 302, target voice interpreting equipment by second server 304
302 obtain speech synthesis data based on translation result and report speech synthesis data.
Content based on above-described embodiment, as a kind of alternative embodiment, which further includes:Third server;Third
Server, for carrying out login authentication to source speech translation apparatus 301 and target voice interpreting equipment 302 respectively, and in source
Speech translation apparatus 301 and target voice interpreting equipment 302 respectively by verification after, establish source speech translation apparatus 301 with
Network connection between target voice interpreting equipment 302.
Content based on above-described embodiment, as a kind of alternative embodiment, which further includes:4th server;4th
Server for receiving the translation result of the transmission of target voice interpreting equipment 302, and carries out phonetic synthesis to translation result, obtains
To speech synthesis data;Target voice interpreting equipment 302 for obtaining the speech synthesis data that the 4th server returns, and is broadcast
Report speech synthesis data.
It should be noted that voiced translation interactive system provided in an embodiment of the present invention can include at least two voiced translations
Equipment, every speech translation apparatus can be used as source speech translation apparatus, can also be used as target voice interpreting equipment, the present invention
Embodiment is not especially limited this.Source speech translation apparatus 301, target voice interpreting equipment 302, first server 303,
The function that two servers 304, third server and the 4th server respectively perform can be respectively with reference to figure 1 and the corresponding methods of Fig. 2
Embodiment, details are not described herein again.
In addition, the first server 303 that above-described embodiment is related to is mainly used for realizing speech recognition and interpretative function (i.e.
Voice data is identified, and recognition result is translated), second server 304 is mainly used for realizing forwarding capability (i.e.
Translation result is forwarded to target voice interpreting equipment by source speech translation apparatus), third server, which is mainly used for realizing, to be logged in
Authentication function (carries out login authentication) to speech translation apparatus, and the 4th server is mainly used for realizing speech-sound synthesizing function (i.e.
Phonetic synthesis is carried out to translation result).Above-mentioned four functions can be integrated in a kind of server namely first server 303,
Two servers 304, third server and the 4th server correspond to same class server.Also above-mentioned four functions can be torn open
Point, and realized by different server.For example, four class servers can be divided into;Alternatively, forwarding capability passes through a kind of server reality
It is existing, and login authentication, speech recognition, translation and phonetic synthesis are realized by another kind of server namely first server, third
Server and the 4th server correspond to same class server.Alternatively, forwarding capability is realized with login authentication by a kind of server,
And speech recognition, translation and phonetic synthesis are realized by another kind of server.
As shown in figure 4, giving a kind of dividing mode of server functionally in Fig. 4, it is specifically divided into two class servers.
" even if the message system (server) " being located above is one type server, is mainly used for realizing forwarding capability, i.e., corresponding
Second server 304.Underlying " identification+translation+synthesis (server) " is another kind of server, is mainly used for realizing language
Sound identification, translation and speech-sound synthesizing function, can correspond to 303 and the 4th server of first server.According to being taken in above-described embodiment
The function of business device divides, the also one login authentication function of being realized by third server.The function can be by being located in Fig. 4
" even if the message system (server) " of top is realized, can also " identification+translation+synthesizes (service by underlying in Fig. 4
Device) " it realizes, the embodiment of the present invention is not especially limited this.
System provided in an embodiment of the present invention establishes network company between source speech translation apparatus and target voice interpreting equipment
After connecing, voice data and language information are sent to first server by source speech ciphering equipment, and first server is based on language information
Voice data is translated.Source speech translation apparatus receives the translation result that first server returns, and translation result is sent out
It send to second server.Translation result is forwarded to target voice interpreting equipment, target voice interpreting equipment base by second server
Speech synthesis data is obtained in translation result and reports speech synthesis data.Since source speech translation apparatus and target voice are translated
The network architecture can be based between equipment and realizes data forwarding and interpretative function, and the distance between unlimited speech translation apparatus,
So that communication is more convenient with exchanging between speech translation apparatus.
It should be noted that above-mentioned all alternative embodiments, may be used the optional implementation that any combination forms the present invention
Example, this is no longer going to repeat them.
Content based on above-described embodiment, an embodiment of the present invention provides an introduces a collection speech translation apparatus.It, should referring to Fig. 5
Equipment includes:
First sending module 501, for after network connection is established with target voice interpreting equipment, by voice data and
Language information is sent to first server, so that first server translates voice data based on language information, languages
Information includes at least target and translates languages type;
Translation result for receiving the translation result of first server return, is sent to second by the second sending module 502
Server, so that translation result is forwarded to target voice interpreting equipment by second server, by target voice interpreting equipment base
Speech synthesis data is obtained in translation result and reports speech synthesis data.
As a kind of alternative embodiment, which further includes:
Third sending module, for log-on message to be sent to third server, so that third server is based on logging in
Information carries out login authentication;
Module is established, for when receiving when being verified message of third server return, then passing through second server
Establish the network connection between target voice interpreting equipment.
Equipment provided in an embodiment of the present invention, after network connection is established with target voice interpreting equipment, by voice data
And language information is sent to first server, so that first server translates voice data based on language information,
Language information includes at least target and translates languages type.Source speech translation apparatus receives the translation result that first server returns,
Translation result is sent to second server, so that translation result is forwarded to target voice interpreting equipment by second server,
Translation result acquisition speech synthesis data is based on by target voice interpreting equipment and reports speech synthesis data.Since source voice turns over
Network architecture realization data forwarding and interpretative function can be based on by translating between equipment and target voice interpreting equipment, and unlimited voice
The distance between interpreting equipment, so that communication is more convenient with exchanging between speech translation apparatus.
Content based on above-described embodiment, an embodiment of the present invention provides a kind of target voice interpreting equipments.Referring to Fig. 6,
The equipment includes:
Receiving module 601, for after network connection is established with source speech translation apparatus, receiving second server forwarding
Translation result, translation result are sent to second server by source speech ciphering equipment, and translation result turns over source voice by first server
It translates after the voice data that equipment is sent is translated and obtains;
Broadcasting module 602 obtains speech synthesis data, and report speech synthesis data for being based on translation result.
As a kind of alternative embodiment, which further includes:
Sending module, for log-on message to be sent to third server, so that third server is based on log-on message
Carry out login authentication;
Module is established, for when receiving when being verified message of third server return, then passing through second server
Establish the network connection between the speech translation apparatus of source.
As a kind of alternative embodiment, broadcasting module 602, for translation result to be sent to the 4th server, so that
4th server is based on translation result and carries out phonetic synthesis, obtains speech synthesis data;Obtain the voice of the 4th server return
Generated data.
Device provided in an embodiment of the present invention after network connection is established with source speech translation apparatus, receives second service
The translation result of device forwarding.Wherein, translation result is sent to second server by source speech ciphering equipment, and translation result is by first service
The voice data that device sends source speech translation apparatus obtains after translating.Target voice interpreting equipment is receiving translation knot
After fruit, speech synthesis data is obtained, and report speech synthesis data based on translation result.Due to source speech translation apparatus and target
The network architecture can be based between speech translation apparatus and realizes data forwarding and interpretative function, and between unlimited speech translation apparatus
Distance so that between speech translation apparatus link up with exchange it is more convenient.
Finally, the present processes are only preferable embodiment, are not intended to limit the protection model of the embodiment of the present invention
It encloses.With within principle, any modification, equivalent replacement, improvement and so on should be included in all spirit in the embodiment of the present invention
Within the protection domain of the embodiment of the present invention.
Claims (10)
1. a kind of voiced translation exchange method, which is characterized in that including:
After network connection is established with target voice interpreting equipment, voice data and language information are sent to first service
Device, so that the first server translates the voice data based on the language information, the language information is extremely
Include target less and translate languages type;
The translation result that the first server returns is received, the translation result is sent to second server, so that institute
It states second server and the translation result is forwarded to the target voice interpreting equipment, by the target voice interpreting equipment base
Speech synthesis data is obtained in the translation result and reports the speech synthesis data.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
Log-on message is sent to third server, is tested so that the third server based on the log-on message log in
Card;
If receive the third server return is verified message, passes through the second server and establish and the mesh
Mark the network connection between speech translation apparatus.
3. a kind of voiced translation exchange method, which is characterized in that including:
After network connection is established with source speech translation apparatus, the translation result of second server forwarding, the translation knot are received
Fruit is sent to the second server by the source speech ciphering equipment, and the translation result turns over the source voice by first server
It translates after the voice data that equipment is sent is translated and obtains;
Speech synthesis data is obtained, and report the speech synthesis data based on the translation result.
4. method according to claim 3, which is characterized in that the method further includes:
Log-on message is sent to third server, is tested so that the third server based on the log-on message log in
Card;
If receive the third server return is verified message, passes through the second server and establish and the source
Network connection between speech translation apparatus.
5. method according to claim 3, which is characterized in that described that speech synthesis data, packet are obtained based on the translation result
It includes:
The translation result is sent to the 4th server, so that the 4th server, which is based on the translation result, carries out language
Sound synthesizes, and obtains the speech synthesis data;
Obtain the speech synthesis data that the 4th server returns.
6. a kind of voiced translation interactive system, which is characterized in that including:Source speech translation apparatus, target voice interpreting equipment,
One server and second server;
After network connection being established between the source speech translation apparatus and the target voice interpreting equipment, the source speech ciphering equipment
Voice data and language information are sent to the first server;The first server is based on the language information to institute
It states voice data to be translated, the language information includes at least target translation languages type and the voice data is corresponding
Source languages type;
The source speech translation apparatus receives the translation result that the first server returns, and the translation result is sent to
Second server;The translation result is forwarded to the target voice interpreting equipment, the target language by the second server
Sound interpreting equipment is based on the translation result and obtains speech synthesis data and report the speech synthesis data.
7. system according to claim 6, which is characterized in that the system also includes:Third server;The third clothes
Business device, for carrying out login authentication to the source speech translation apparatus and the target voice interpreting equipment respectively, and in institute
State source speech translation apparatus and the target voice interpreting equipment respectively by verification after, establish the source speech translation apparatus
With the network connection between the target voice interpreting equipment.
8. system according to claim 6, which is characterized in that the system also includes:4th server;4th clothes
Business device for receiving the translation result that the target voice interpreting equipment is sent, and carries out phonetic synthesis to the translation result,
Obtain the speech synthesis data;The target voice interpreting equipment closes for obtaining the voice that the 4th server returns
Into data, and report the speech synthesis data.
A 9. introduces a collection speech translation apparatus, which is characterized in that including:
First sending module, for after network connection is established with target voice interpreting equipment, voice data and languages to be believed
Breath is sent to first server, so that the first server turns over the voice data based on the language information
It translates, the language information includes at least target and translates languages type;
The translation result for receiving the translation result that the first server returns, is sent to the by the second sending module
Two servers, so that the translation result is forwarded to the target voice interpreting equipment by the second server, by described
Target voice interpreting equipment is based on the translation result and obtains speech synthesis data and report the speech synthesis data.
10. a kind of target voice interpreting equipment, which is characterized in that including:
Receiving module, for after network connection is established with source speech translation apparatus, receiving the translation knot of second server forwarding
Fruit, the translation result are sent to the second server by the source speech ciphering equipment, and the translation result is by first server
It is obtained after being translated to the voice data that the source speech translation apparatus is sent;
Broadcasting module obtains speech synthesis data, and report the speech synthesis data for being based on the translation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711384184.6A CN108228575A (en) | 2017-12-20 | 2017-12-20 | Voiced translation exchange method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711384184.6A CN108228575A (en) | 2017-12-20 | 2017-12-20 | Voiced translation exchange method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108228575A true CN108228575A (en) | 2018-06-29 |
Family
ID=62652551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711384184.6A Pending CN108228575A (en) | 2017-12-20 | 2017-12-20 | Voiced translation exchange method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108228575A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109327613A (en) * | 2018-10-15 | 2019-02-12 | 华为技术有限公司 | A kind of machinery of consultation and electronic equipment based on voice communication translation ability |
CN112764539A (en) * | 2021-01-13 | 2021-05-07 | 温州职业技术学院 | Device convenient for communication between languages |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130191109A1 (en) * | 2006-10-10 | 2013-07-25 | Abbyy Software Ltd. | Translating Sentences Between Languages |
CN106919562A (en) * | 2017-04-28 | 2017-07-04 | 深圳市大乘科技股份有限公司 | A kind of real-time translation system, method and device |
CN107066453A (en) * | 2017-01-17 | 2017-08-18 | 881飞号通讯有限公司 | A kind of method that multilingual intertranslation is realized in network voice communication |
CN107343113A (en) * | 2017-06-26 | 2017-11-10 | 深圳市沃特沃德股份有限公司 | Audio communication method and device |
-
2017
- 2017-12-20 CN CN201711384184.6A patent/CN108228575A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130191109A1 (en) * | 2006-10-10 | 2013-07-25 | Abbyy Software Ltd. | Translating Sentences Between Languages |
CN107066453A (en) * | 2017-01-17 | 2017-08-18 | 881飞号通讯有限公司 | A kind of method that multilingual intertranslation is realized in network voice communication |
CN106919562A (en) * | 2017-04-28 | 2017-07-04 | 深圳市大乘科技股份有限公司 | A kind of real-time translation system, method and device |
CN107343113A (en) * | 2017-06-26 | 2017-11-10 | 深圳市沃特沃德股份有限公司 | Audio communication method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109327613A (en) * | 2018-10-15 | 2019-02-12 | 华为技术有限公司 | A kind of machinery of consultation and electronic equipment based on voice communication translation ability |
CN109327613B (en) * | 2018-10-15 | 2020-09-29 | 华为技术有限公司 | Negotiation method based on voice call translation capability and electronic equipment |
US11886830B2 (en) | 2018-10-15 | 2024-01-30 | Huawei Technologies Co., Ltd. | Voice call translation capability negotiation method and electronic device |
CN112764539A (en) * | 2021-01-13 | 2021-05-07 | 温州职业技术学院 | Device convenient for communication between languages |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102724324B (en) | Message pushes integrating apparatus and message pushes integration method | |
CN104603743B (en) | The computer implemented method of portable electric appts and the computer implemented method that the equipment is connected to safe WLAN | |
CN104023328B (en) | A kind of operator's mobile cellular network access system and corresponding communication means | |
CN109561430A (en) | A kind of implementation method and equipment of public network user access private network | |
CN105025475B (en) | Mobile secrecy terminal realizing method towards android system | |
CN102185716B (en) | Universal management method and system for communication equipment | |
CN109194427B (en) | Campus broadcasting system based on IP network | |
CN105635087B (en) | Pass through the method and device of voice print verification user identity | |
CN105551120A (en) | Building intercommunication method, near field communication (NFC) unlocking device and building intercommunication system | |
CN104967595A (en) | Method and apparatus for registering devices on Internet of things platform | |
CN102823218A (en) | Method and apparatus for identity federation gateway | |
CN102811422B (en) | A kind of Trunked Radio System | |
CN105438900A (en) | Mobile phone elevator taking system | |
CN106231572A (en) | Pseudo-base station refuse messages discrimination method and system | |
CN104820944A (en) | Method and system for bank self-service terminal authentication, and device | |
WO2007045136A1 (en) | A network-based communication system and method for translating multi-language speech and text information in real-time | |
CN105429958A (en) | Enterprise application platform system based on Android development | |
CN106879048A (en) | Smart machine networking method, system and smart machine | |
CN107995200A (en) | A kind of certificate issuance method, identity identifying method and system based on smart card | |
CN108228575A (en) | Voiced translation exchange method and system | |
CN109982451A (en) | Remote speech broadcasts cashing method | |
CN102811369A (en) | Security authentication method during video sharing and handheld equipment | |
CN106303989A (en) | A kind of intercommunication method based on mobile terminal and mobile terminal | |
CN107172616A (en) | Apparatus and method for connecting mobile device and field apparatus | |
CN107632916A (en) | The method and apparatus for checking mobile terminal operation note |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |