CN109949794A - A kind of intelligent sound converting system based on Internet technology - Google Patents
A kind of intelligent sound converting system based on Internet technology Download PDFInfo
- Publication number
- CN109949794A CN109949794A CN201910192338.4A CN201910192338A CN109949794A CN 109949794 A CN109949794 A CN 109949794A CN 201910192338 A CN201910192338 A CN 201910192338A CN 109949794 A CN109949794 A CN 109949794A
- Authority
- CN
- China
- Prior art keywords
- language
- module
- user
- unit
- mood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 19
- 238000013519 translation Methods 0.000 claims abstract description 61
- 230000036651 mood Effects 0.000 claims abstract description 53
- 230000001815 facial effect Effects 0.000 claims abstract description 4
- 230000002996 emotional effect Effects 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 5
- 230000008921 facial expression Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 241001672694 Citrus reticulata Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The invention belongs to speech conversion system technical field, specifically a kind of intelligent sound converting system based on Internet technology, including system switch area, translated region, report an error area and automatic learning region；The system switch area includes facial acquisition module and language acquisition module；The translated region includes mood data module, mood analysis module and mood matching module；The area that reports an error includes mark module, network uploading module, answer analysis module and automatic adding module；The network uploading module includes retrieval unit, puts question to unit and access unit；The automatic learning region includes language recording module, language analysis module and is automatically replenished module；The phenomenon that full automatic switching of realization system can be achieved in the present invention, facilitates the real time translation of different language, while keeping the language after translation no longer so stiff, prevents Chinese appearance from leading to polysemy due to the variation of mood；Category of language can be corrected automatically, be filled a vacancy and perfect simultaneously.
Description
Technical field
The invention belongs to speech conversion system technical field, specifically a kind of intelligent sound based on Internet technology
Converting system.
Background technique
Language is the most important the vehicle of communication of the mankind, is the main expression way that people are linked up, people are by language
It saves and the achievement of transmitting human civilization, language is national one of important feature, in general, each nationality has oneself
Language, language are the media that people rap off, it itself will necessarily generate our economy, our society and our politics, science and technology or even culture
It influences.This cultural phenomenon of language is to continue to develop, and spatial distribution now is also the result of development in the past.According to its language
Language in the world is divided into the family of languages by the something in common and Provenance relation of sound, grammer and vocabulary etc. feature.Each family of languages packet
Include languages in varying numbers, these family of languageies and languages geographically have certain distributed area, many cultural traits all with this
There is close relationship.
Languages switching system in the prior art is directed to the conversion of mandarin in China mostly, but in CHINESE REGION dialect
It is more popular, there is a local dialect in each place, mostly uses mandarin to carry out greatly when people communicate
Exchange, for those mandarins and slack people, exchange becomes a great problem, and existing speech conversion system is translated
Voice out is excessively stiff, has seriously affected the use feeling of user, at the same can not accomplish in translation process it is changeable in mood, it is right
It is different in the meaning that a word or a word are said under different moods, it can not accurately be translated.
Summary of the invention
In order to make up for the deficiencies of the prior art, a kind of intelligent sound based on Internet technology proposed by the present invention converts system
System.
The technical solution adopted by the present invention to solve the technical problems is: of the present invention a kind of based on Internet technology
Intelligent sound converting system, including system switch area, translated region, report an error area and automatic learning region；It uses the system switch area
In facial expression and language form according to user of service, system is made to switch to the mode suitable for the language, and to using
Person's language carries out typing；The translated region is used for the system switch area after system switching is completed in system switch area and identifies user
Language translated, while emotional change is added, it is no longer stiff after language translation to make；The area that reports an error in translated region for turning over
After there is mistake during translating, change is marked；It is identified locating for user for system switch area the automatic learning region
Language in environment, and learnt, it at the shortcoming of inquiry system, is supplemented, keeps system more perfect；The system switching
Area includes facial acquisition module and language acquisition module；The face acquisition module includes Mouth-Shape Recognition unit and Expression Recognition list
Member；Mouth-Shape Recognition unit user's shape of the mouth as one speaks for identification, to judge the used language form of user；The expression is known
Expression shape change of the other unit during user speaks for identification；The language acquisition module includes tone recognition unit and language
Meaning recognition unit；Tone variation of tone recognition unit when user speaks for identification；The semantics identity unit is used
In identification user, when speaking, language looks like, and analyzes the used language form of user in combination with tone recognition unit, and
By comparison with Mouth-Shape Recognition unit screening, language form used in user is obtained, and automatically switch to system suitable
Mode for the language form；When user uses system, Mouth-Shape Recognition unit identifies user's shape of the mouth as one speaks, semantics identity unit
It is by user's meaning of one's words, tone recognition unit identifies user's tone, thus by the shape of the mouth as one speaks, the tone and the meaning of one's words of user to making
User's category of language is screened, and is found category of language used in user and is switched to system suitable for the category of language
Mode, realize the full automatic switching of system, facilitate the real time translation of different language, reduce the mistake of user's language judgement
Rate.
Preferably, the translated region includes mood data module, mood analysis module and mood matching module；The mood
Data module is for storing mood data；The mood analysis module be used for according to Expression Recognition unit, tone recognition unit and
Semantics identity unit identifies the expression, the tone and the meaning of one's words of user, analyzes the emotional change when user speaks；It is described
Mood matching module is used to match the emotional change result analyzed in mood in mood data module and mood analysis module,
And be applied in language translation, make language translation with emotional change；Mood analysis module analyzes expression recognition unit, the tone is known
The data of other unit and the identification of semantics identity unit, mood matching module are found and user's mood phase in mood data module
Same mood is applied, and the language after making translation is no longer so stiff, while can prevent Chinese from the variation due to mood occur
The phenomenon that leading to polysemy, anti-locking system can not correctly express user's meaning.
Preferably, the area that reports an error includes mark module, network uploading module, answer analysis module and adds mould automatically
Block；The mark module is used in translated region translation user's language procedures, and erroneous point is marked after translation error；Institute
It states erroneous point of the network uploading module for marking mark module and is uploaded to network and the affiliated company of system, find correct
Answer；The answer analysis module show whether answer is correct for analyzing network uploading module；The automatic adding module is used
It is automatically added in system in the correct option for analyzing analysis module；Occur translation error in data when system is in translation,
System is by being mistakenly marked, network uploading module marks mark module belonging to content uploading to network and system automatically
Company, finds correct translation answer, and obtained answer guarantees the correctness of answer, automatically under the analysis of answer analysis module
Correct option is automatically added in system by adding module, and change in time, gradual perfection system are improved and used before translation next time
The use feeling of person.
Preferably, the network uploading module includes retrieval unit, puts question to unit and access unit；The retrieval unit is used
Network retrieval is carried out in the erroneous point for mark module internal labeling, to find out correct option；The enquirement module is used for needle
The erroneous point of mark module internal labeling is putd question in network, vast user name opinion is solicited, finds answer；The access unit is used for
It is artificially accessed for the erroneous point and the language mode of mark module label, the people of the category of language is proficient in interview, finds
Answer；After system marks erroneous point, retrieval unit is retrieved by internet, puts question to unit in internet to vast user name
It puts question to and finds answer, while access unit interviews the person of being proficient in, by the comparison of three's answer, find correctly translation answer, and
Be added in system by automatic adding module, go through a variety of ways obtain answer, and to the answer of acquisition carry out analysis and
Judgement, obtains correct option, and the correctness of answer has been effectively ensured, and reduces system translation error rate.
Preferably, the access unit includes go out for a visit component, collection access component and reward component；The outer visit
It asks that component goes to what mark module marked erroneous point language form to carry out interviewing prevailingly for associate to be outgoing, seeks
Look for answer；For the collection access component for company in publication collection article on network, mark module label error is proficient in searching
The people of overdue language form goes to company to access, and finds answer；The reward component is gone to for collecting in access component
Company accepts an interview and provides suitable answer and have the people of facilitation to this kind of language in system, is rewarded；System marks
After mistake, the component arrangement personnel that go out for a visit are outgoing to find answer for the translation error, while collecting access component in network
Article is collected in upper publication, finds suitable people's access, improves the accuracy of answer, while can solve the language form by accessing people
Other issues for translation, improve the solution efficiency of problem, after Resolving probiems, the degree of difficulty of reward component for this problem,
And the satisfaction that access people answers provides adaptation reward, improves enthusiasm and specifics that access people answers, obtains problem
To most fast most thin solution, while keeping system more perfect.
Preferably, the automatic learning region includes language recording module, language analysis module and is automatically replenished module；It is described
Language acquisition module collected surrounding other types language when language recording module uses system for typing user；It is described
Language analysis module for analyzing the language of typing in language recording module, judge be in its integrated degree and system
The no data translation for having this kind of language；The module that is automatically replenished does not have for going out system according to language analysis module analysis
The language for thering is translation ability and system to need, by the language replenishment system in language typing unit, to this kind in system
Language is corrected and is filled a vacancy, and keeps system more perfect；For user when using system, language recording module can be to user institute
Locate other language in environment and carry out typing, and feed back in language analysis module, language analysis module carries out the data of feedback
Analysis, and compared to having translation in system, the type of language is not contained in searching system and contained the kind for changing language
Class, but do not have the specific translation of the words is not directly applicable to system and keep in, may be directly applied to system
It feeds back to and is automatically replenished module, be automatically replenished module according to feedback information, be applied in system, improve the integrity degree of system, make
System corrected automatically, is filled a vacancy and perfect.
Preferably, the language analysis module includes internal analysis unit and temporary storage location；The internal analysis unit is used
In the category of language of typing in metalanguage recording module, and comparison system inner language type, judge in the language system whether
Has translation ability；The temporary storage location, which analyzes system for internal analysis unit, does not have the language of translation ability, into
Row is temporary, after the language integrity degree reaches in temporary storage location, feeds back to system, the speech range and translation that raising system is related to
Range；Internal analysis unit, which analyzes, not can be used directly when the language of system, feed back to temporary storage location, in temporary storage location
It is temporary, after internal analysis unit persistently obtains the type language, improve after the type language to after can be directly used for system,
It feeds back to and is automatically replenished in module together with the language that may be directly applied to system, the language form of system is supplemented, is mentioned
The scope of application of high system, while sophisticated systems have had the language form of translation ability.
Beneficial effects of the present invention are as follows:
1. a kind of intelligent sound converting system based on Internet technology of the present invention is switched by setting system
Area；By being screened by the shape of the mouth as one speaks, the tone and the meaning of one's words of user to user's category of language, find used in user
System is simultaneously switched to the mode suitable for the category of language by category of language, is realized the full automatic switching of system, is facilitated difference
The real time translation of language.
2. a kind of intelligent sound converting system based on Internet technology of the present invention, by the way that translated region is arranged；It is logical
Cross the data of mood analysis module analysis expression recognition unit, tone recognition unit and the identification of semantics identity unit, mood matching
Module is found mood identical with user's mood in mood data module and is applied, and the language after making translation is no longer so
It is stiff, while can prevent Chinese from the phenomenon that leading to polysemy due to the variation of mood occur, anti-locking system can not be expressed correctly
User's meaning.
3. a kind of intelligent sound converting system based on Internet technology of the present invention, by the way that the area that reports an error is arranged；It is logical
To automatically mistake be marked by crossing system, and network uploading module marks mark module belonging to content uploading to network and system
Company is found by diversified forms such as network retrieval, enquirement and artificial access and correctly translates answer, guarantees the correctness of answer,
Under the analysis of answer analysis module, correct option is automatically added in system for obtained answer, before translation next time in time more
Change, gradual perfection system improves the use feeling of user.
4. a kind of intelligent sound converting system based on Internet technology of the present invention, by the way that automatic study is arranged
Area；Typing is carried out to other language in user's local environment by language recording module, feeds back to the progress of language analysis module
Analysis, the information that system has had gives up, and system is not directly applicable in the information not having and keep in, can directly be applied
It is automatically replenished module in feeding back to for system, module is automatically replenished according to feedback information, is applied in system, improves the complete of system
Whole degree makes system be corrected, be filled a vacancy automatically and perfect.
Detailed description of the invention
The present invention will be further explained below with reference to the attached drawings.
Fig. 1 is overall structure block diagram of the invention；
Fig. 2 is the structural block diagram of network uploading module in the present invention；
Fig. 3 is the structural block diagram of automatic learning region in the present invention；
Specific embodiment
In order to be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, tie below
Specific embodiment is closed, the present invention is further explained.
As shown in Figure 1 to Figure 3, a kind of intelligent sound converting system based on Internet technology of the present invention, including
System switch area, translated region, report an error area and automatic learning region；The system switch area is used for the facial expression according to user of service
And language form, so that system is switched to the mode suitable for the language, and carry out typing to user's language；The translated region
It identifies that the language of user is translated for completing system switch area after system switches in system switch area, while feelings is added
Thread variation, it is no longer stiff after language translation to make；After the area that reports an error is for there is mistake in translated region translation process, marked
Note change；The language in user's local environment is identified for system switch area in the automatic learning region, and is learnt, and looks into
It at the shortcoming of inquiry system, is supplemented, keeps system more perfect；The system switch area includes that facial acquisition module and language are adopted
Collect module；The face acquisition module includes Mouth-Shape Recognition unit and Expression Recognition unit；The Mouth-Shape Recognition unit is for knowing
Other user's shape of the mouth as one speaks, to judge the used language form of user；User's Expression Recognition unit speaks for identification
Expression shape change in the process；The language acquisition module includes tone recognition unit and semantics identity unit；The tone identification
Tone variation of unit when user speaks for identification；Semantics identity unit user's language when speaking for identification
The meaning analyzes the used language form of user in combination with tone recognition unit, and passes through the comparison with Mouth-Shape Recognition unit
Screening, obtains language form used in user, and system is switched to the mode suitable for the language form automatically；It uses
When person uses system, Mouth-Shape Recognition unit identifies user's shape of the mouth as one speaks, and semantics identity unit is by user's meaning of one's words, and tone identification is single
Member identification user's tone is found so that the shape of the mouth as one speaks, the tone and the meaning of one's words by user screen user's category of language
System is simultaneously switched to the mode suitable for the category of language by category of language used in user, realizes the full automatic of system
Switching facilitates the real time translation of different language, reduces the error rate of user's language judgement.
As a kind of specific embodiment of the invention, the translated region includes mood data module, mood analysis module
With mood matching module；The mood data module is for storing mood data；The mood analysis module is used for according to expression
Recognition unit, tone recognition unit and semantics identity unit identify the expression, the tone and the meaning of one's words of user, analyze the use
Emotional change when person speaks；The mood matching module is used in mood in mood data module and mood analysis module points
The emotional change result of precipitation matches, and is applied in language translation, makes language translation with emotional change；Mood analysis module
The data of expression recognition unit, tone recognition unit and the identification of semantics identity unit are analyzed, mood matching module is in mood data
It finds mood identical with user's mood in module to apply, the language after making translation is no longer so stiff, while can prevent
The phenomenon that only Chinese appearance leads to polysemy due to the variation of mood, anti-locking system can not correctly express user's meaning.
As a kind of specific embodiment of the invention, the area that reports an error includes mark module, network uploading module, answer
Analysis module and automatic adding module；The mark module is used in translated region translation user's language procedures, translation error
Erroneous point is marked afterwards；The network uploading module be used for the erroneous point that marks mark module be uploaded to network and
Correct option is found by the affiliated company of system；Just whether the answer analysis module obtain answer for analyzing network uploading module
Really；The correct option that the automatic adding module is used to analyze analysis module is automatically added in system；When system is being turned over
Occurs translation error in data when translating, system is by automatically to being mistakenly marked, in network uploading module marks mark module
Appearance is uploaded to network and the affiliated company of system, finds correct translation answer, obtained answer under the analysis of answer analysis module,
Guarantee that correct option is automatically added in system by the correctness of answer, automatic adding module, the change in time before translation next time,
Gradual perfection system improves the use feeling of user.
As a kind of specific embodiment of the invention, the network uploading module include retrieval unit, put question to unit and
Access unit；The retrieval unit is used to carry out network retrieval for the erroneous point of mark module internal labeling, to find out correct
Answer；It is described that module is putd question to be used to put question to for the erroneous point of mark module internal labeling in network, vast user name opinion is solicited, is sought
Look for answer；The access unit is used to artificially be accessed for the erroneous point of mark module label and the language mode, interviews
It is proficient in the people of the category of language, finds answer；After system marks erroneous point, retrieval unit is retrieved by internet, is putd question to
Unit puts question to vast user name in internet and finds answer, while access unit interviews the person of being proficient in, and passes through pair of three's answer
Than, correctly translation answer is found, and be added in system by automatic adding module, goes to obtain answer through a variety of ways,
And the answer of acquisition is analyzed and judged, it obtains correct option, the correctness of answer has been effectively ensured, reduce system translation
Error rate.
As a kind of specific embodiment of the invention, the access unit includes go out for a visit component, collection access group
Part and reward component；The component that goes out for a visit goes out that mark module is gone to mark erroneous point language form for associate
Carry out interviewing prevailingly, find answer；The collection access component, in publication collection article on network, is sought for company
Looking for being proficient in mark module and marking the people of erroneous point language form goes to company to access, and finds answer；The reward component
It is accessed for collection and goes to company to accept an interview in component and provide suitable answer and have facilitation to this kind of language in system
People, rewarded；After system marks mistake, the component arrangement personnel that go out for a visit are outgoing to find answer for the translation error,
Access component is collected simultaneously in publication collection article on network, is found suitable people's access, is improved the accuracy of answer, while can lead to
It crosses access people and solves other issues for translation of the language form, improve the solution efficiency of problem, after Resolving probiems, reward component
Degree of difficulty for this problem, and the satisfaction that access people answers provide adaptation reward, improve the product that access people answers
Polarity and specifics make problem obtain most fast most thin solution, while keeping system more perfect.
As a kind of specific embodiment of the invention, the automatic learning region includes language recording module, language analysis
Module and it is automatically replenished module；The language recording module is collected for typing user using language acquisition module when system
Surrounding's other types language；The language analysis module is sentenced for analyzing the language of typing in language recording module
Whether the data translation of this kind language is had in its integrated degree and the system of breaking；The module that is automatically replenished is for according to language
Analysis module analyzes system and does not have the language of translation ability and system needs, and the language in language typing unit is mended
In charging system, this kind of language in system is corrected and filled a vacancy, keeps system more perfect；User when using system,
Language recording module can carry out typing to other language in user's local environment, and feed back in language analysis module, language
Analysis module analyzes the data of feedback, and compares to having translation in system, and language is not contained in searching system
Type and contained the type for changing language, but do not have the specific translation of the words, be not directly applicable to system into
Row is temporary, may be directly applied to feeding back to for system and is automatically replenished module, is automatically replenished module according to feedback information, applied to being
In system, the integrity degree of system is improved, so that system corrected, filled a vacancy automatically and perfect.
As a kind of specific embodiment of the invention, the language analysis module includes internal analysis unit and temporary list
Member；Category of language of the internal analysis unit for typing in metalanguage recording module, and comparison system inner language type,
Judge whether had translation ability in the language system；The temporary storage location, which analyzes system for internal analysis unit, not to be had
There is the language of translation ability, kept in, after the language integrity degree reaches in temporary storage location, feeds back to system, improve system
The speech range and translation range being related to；Internal analysis unit, which analyzes, not can be used directly when the language of system, feed back to
Temporary storage location, in temporary storage location keep in, it is complete to the type language after internal analysis unit persistently obtains the type language
It is apt to after can be directly used for system, feeds back to and be automatically replenished in module together with the language that may be directly applied to system, to system
Language form supplemented, improve the scope of application of system, while sophisticated systems have had the language form of translation ability.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the present invention is not limited to the above embodiments, and the above embodiments and description only describe originals of the invention
Reason, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes and improvements
It all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims and its equivalent circle
It is fixed.
Claims (7)
1. a kind of intelligent sound converting system based on Internet technology, it is characterised in that: including system switch area, translated region,
Report an error area and automatic learning region；The system switch area is used for according to the facial expression and language form of user of service, make be
System switches to the mode suitable for the language, and carries out typing to user's language；The translated region is used in system switch area
System switch area identifies that the language of user is translated after the switching of completion system, while emotional change is added, and turns over language
It is no longer stiff after translating；After the area that reports an error is for there is mistake in translated region translation process, change is marked；It is described automatic
The language in user's local environment is identified for system switch area in learning region, and is learnt, at the shortcoming of inquiry system,
It is supplemented, keeps system more perfect；The system switch area includes facial acquisition module and language acquisition module；The face
Acquisition module includes Mouth-Shape Recognition unit and Expression Recognition unit；Mouth-Shape Recognition unit user's shape of the mouth as one speaks for identification, from
And judge the used language form of user；Expression of the Expression Recognition unit during user speaks for identification becomes
Change；The language acquisition module includes tone recognition unit and semantics identity unit；The tone recognition unit makes for identification
Tone variation when user speaks；User's language when speaking looks like the semantics identity unit for identification, in combination with
Tone recognition unit analyzes the used language form of user, and is screened by the comparison with Mouth-Shape Recognition unit, obtains use
Language form used in person, and system is switched to the mode suitable for the language form automatically.
2. a kind of intelligent sound converting system based on Internet technology according to claim 1, it is characterised in that: described
Translated region includes mood data module, mood analysis module and mood matching module；The mood data module is for storing feelings
Thread data；The mood analysis module according to Expression Recognition unit, tone recognition unit and semantics identity unit for identifying
Expression, the tone and the meaning of one's words of user analyzes the emotional change when user speaks；The mood matching module is used for will
The emotional change result analyzed in mood and mood analysis module in mood data module matches, and is applied to language translation
On, make language translation with emotional change.
3. a kind of intelligent sound converting system based on Internet technology according to claim 1, it is characterised in that: described
The area that reports an error includes mark module, network uploading module, answer analysis module and automatic adding module；The mark module is used for
Translated region is translated in user's language procedures, and erroneous point is marked after translation error；The network uploading module is used for will
The erroneous point that mark module marks is uploaded to network and the affiliated company of system, finds correct option；Mould is analyzed in the answer
Block show whether answer is correct for analyzing network uploading module；What the automatic adding module was used to analyze analysis module
Correct option is automatically added in system.
4. a kind of intelligent sound converting system based on Internet technology according to claim 3, it is characterised in that: described
Network uploading module includes retrieval unit, puts question to unit and access unit；The retrieval unit is used to be directed to mark module internal standard
The erroneous point of note carries out network retrieval, to find out correct option；It is described that module is putd question to be used for for mark module internal labeling
Erroneous point is putd question in network, solicits vast user name opinion, finds answer；The access unit is used for for mark module label
Erroneous point and the language mode are artificially accessed, and the people of the category of language is proficient in interview, find answer.
5. a kind of intelligent sound converting system based on Internet technology according to claim 4, it is characterised in that: described
Access unit includes go out for a visit component, collection access component and reward component；The component that goes out for a visit is for associate
It is outgoing to go to what mark module marked erroneous point language form to carry out interviewing prevailingly, find answer；The collection is visited
Ask that component, in publication collection article on network, is found before being proficient in the people that mark module marks erroneous point language form for company
It accesses toward company, finds answer；The reward component goes to company to accept an interview and provide for collecting in access component
Suitable answer and the people for having facilitation to this kind of language in system, are rewarded.
6. a kind of intelligent sound converting system based on Internet technology according to claim 1, it is characterised in that: described
Automatic learning region includes language recording module, language analysis module and is automatically replenished module；The language recording module is for recording
Enter user and uses language acquisition module collected surrounding other types language when system；The language analysis module for pair
The language of typing is analyzed in language recording module, judges the number for whether having this kind of language in its integrated degree and system
According to translation；The module that is automatically replenished is for going out system according to language analysis module analysis and not having translation ability and system need
The language wanted is corrected in the language replenishment system in language typing unit and is filled a vacancy to this kind of language in system,
Keep system more perfect.
7. a kind of intelligent sound converting system based on Internet technology according to claim 6, it is characterised in that: described
Language analysis module includes internal analysis unit and temporary storage location；The internal analysis unit is in metalanguage recording module
The category of language of typing, and comparison system inner language type, judge whether had translation ability in the language system；It is described temporary
Memory cell, which analyzes system for internal analysis unit, does not have the language of translation ability, is kept in, to be somebody's turn to do in temporary storage location
After language integrity degree reaches, system is fed back to, the speech range that raising system is related to and translation range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192338.4A CN109949794B (en) | 2019-03-14 | 2019-03-14 | Intelligent voice conversion system based on internet technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192338.4A CN109949794B (en) | 2019-03-14 | 2019-03-14 | Intelligent voice conversion system based on internet technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949794A true CN109949794A (en) | 2019-06-28 |
| CN109949794B CN109949794B (en) | 2021-04-16 |
Family
ID=67009828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910192338.4A Active CN109949794B (en) | 2019-03-14 | 2019-03-14 | Intelligent voice conversion system based on internet technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949794B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112331209A (en) * | 2020-11-03 | 2021-02-05 | 建信金融科技有限责任公司 | Method and device for converting voice into text, electronic equipment and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02183371A (en) * | 1989-01-10 | 1990-07-17 | Nec Corp | Automatic interpreting device |
| CN1379392A (en) * | 2001-04-11 | 2002-11-13 | 国际商业机器公司 | Feeling speech sound and speech sound translation system and method |
| CN101937431A (en) * | 2010-08-18 | 2011-01-05 | 华南理工大学 | Emotional voice translation device and processing method |
| US20120078607A1 (en) * | 2010-09-29 | 2012-03-29 | Kabushiki Kaisha Toshiba | Speech translation apparatus, method and program |
| CN106294327A (en) * | 2015-05-12 | 2017-01-04 | 中国移动通信集团公司 | The method of real time translation, device and network element device in a kind of mobile communications network |
| CN107464292A (en) * | 2017-07-03 | 2017-12-12 | 浙江建林电子电气股份有限公司 | A kind of experience type ticket machine and its ticketing method |
| CN108766414A (en) * | 2018-06-29 | 2018-11-06 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and computer readable storage medium for voiced translation |
-
2019
- 2019-03-14 CN CN201910192338.4A patent/CN109949794B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02183371A (en) * | 1989-01-10 | 1990-07-17 | Nec Corp | Automatic interpreting device |
| CN1379392A (en) * | 2001-04-11 | 2002-11-13 | 国际商业机器公司 | Feeling speech sound and speech sound translation system and method |
| CN101937431A (en) * | 2010-08-18 | 2011-01-05 | 华南理工大学 | Emotional voice translation device and processing method |
| US20120078607A1 (en) * | 2010-09-29 | 2012-03-29 | Kabushiki Kaisha Toshiba | Speech translation apparatus, method and program |
| CN106294327A (en) * | 2015-05-12 | 2017-01-04 | 中国移动通信集团公司 | The method of real time translation, device and network element device in a kind of mobile communications network |
| CN107464292A (en) * | 2017-07-03 | 2017-12-12 | 浙江建林电子电气股份有限公司 | A kind of experience type ticket machine and its ticketing method |
| CN108766414A (en) * | 2018-06-29 | 2018-11-06 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and computer readable storage medium for voiced translation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112331209A (en) * | 2020-11-03 | 2021-02-05 | 建信金融科技有限责任公司 | Method and device for converting voice into text, electronic equipment and readable storage medium |
| CN112331209B (en) * | 2020-11-03 | 2023-08-08 | 建信金融科技有限责任公司 | Method and device for converting voice into text, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949794B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446286B (en) | Method, device and server for generating natural language question answers | |
| Schwartz et al. | Broadening the study of the self: Integrating the study of personal identity and cultural identity | |
| CN100495395C (en) | Data semanticizer | |
| CN109271529A (en) | Cyrillic Mongolian and the double language knowledge mapping construction methods of traditional Mongolian | |
| CN107562859A (en) | A kind of disaggregated model training system and its implementation | |
| CN109992671A (en) | Intension recognizing method, device, equipment and storage medium | |
| CN105989056A (en) | Chinese news recommending system | |
| CN104252507B (en) | A kind of business data matching process and device | |
| CN109740150A (en) | Address resolution method, device, computer equipment and computer readable storage medium | |
| CN109446376A (en) | A kind of method and system classified by participle to voice | |
| CN111311459A (en) | Interactive question setting method and system for international Chinese teaching | |
| CN109492105A (en) | A kind of text sentiment classification method based on multiple features integrated study | |
| CN116959433B (en) | Text processing method, device, electronic equipment and storage medium | |
| CN112052317A (en) | Medical knowledge base intelligent retrieval system and method based on deep learning | |
| Krishnamurti et al. | South Asian languages: Structure, convergence, and diglossia | |
| CN110222344A (en) | A kind of composition factor analysis algorithm taught for pupil's composition | |
| Tamburelli et al. | Revisiting the classification of Gallo-Italic: a dialectometric approach | |
| CN109949794A (en) | A kind of intelligent sound converting system based on Internet technology | |
| Cheng | Inquiries into classical Chinese logic | |
| CN112380868A (en) | Petition-purpose multi-classification device based on event triples and method thereof | |
| Paterson et al. | Quantifiers and discourse processing | |
| CN111522913A (en) | Emotion classification method suitable for long text and short text | |
| CN112035680B (en) | Knowledge graph construction method of intelligent auxiliary learning machine | |
| CN109857746A (en) | Automatic update method, device and the electronic equipment of bilingual word bank | |
| Henriksen et al. | Intervocalic phonemic stop realization in Amazonian Peru |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210331 Address after: 502, building 3, science and Technology Industrial Park, Shandong University, 2600 Yingxiu Road, Jinan area, China (Shandong) pilot Free Trade Zone, Jinan City, Shandong Province Applicant after: Shandong Yuanlian Information Technology Co.,Ltd. Address before: 230088 1136, South Building, No.19, Tianzhi Road, hi tech Zone, Hefei City, Anhui Province Applicant before: HEFEI KESU INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An intelligent voice conversion system based on Internet technology Effective date of registration: 20211125 Granted publication date: 20210416 Pledgee: Ji'nan rural commercial bank Limited by Share Ltd. high tech branch Pledgor: Shandong Yuanlian Information Technology Co.,Ltd. Registration number: Y2021980013251 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20221018 Granted publication date: 20210416 Pledgee: Ji'nan rural commercial bank Limited by Share Ltd. high tech branch Pledgor: Shandong Yuanlian Information Technology Co.,Ltd. Registration number: Y2021980013251 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An Intelligent Voice Conversion System Based on Internet Technology Effective date of registration: 20221019 Granted publication date: 20210416 Pledgee: Ji'nan rural commercial bank Limited by Share Ltd. high tech branch Pledgor: Shandong Yuanlian Information Technology Co.,Ltd. Registration number: Y2022980018916 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |