CN108628836A - The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm - Google Patents
The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm Download PDFInfo
- Publication number
- CN108628836A CN108628836A CN201710172488.XA CN201710172488A CN108628836A CN 108628836 A CN108628836 A CN 108628836A CN 201710172488 A CN201710172488 A CN 201710172488A CN 108628836 A CN108628836 A CN 108628836A
- Authority
- CN
- China
- Prior art keywords
- translation
- neural network
- robot
- cloud computing
- computing center
- 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
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
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/55—Rule-based translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of robots carrying out voiced translation using artificial intelligence BP neural network algorithm, by robot body, cloud computing center BP neural network translation module, cloud computing center large database concept, three critical pieces are constituted, BP neural network module is linked and is trained to the data for translating large database concept in cloud computing center, to make BP neural network pass the rate of accuracy reached translated to 95% or more to handing over, to the rate of accuracy reached of simultaneous interpretation translation to 70% or more, when user needs translation, pronounce to robot, audio data is transmitted to cloud computing center by robot, robot is passed back after being translated by BP neural network module, robot again listens the speech play after translation to user.By the above-mentioned means, the present invention can substitute the advanced simultaneous interpretation translator of profession, translated for user, the benefit brought is：Translation will not lead to the mistake caused by fatigue for a long time；Greatly reduce the fund cost for engaging simultaneous interpretation translator.
Description
Technical field
The present invention relates to artificial intelligence fields, are not to be related to a kind of use artificial intelligence BP neural network algorithm progress voice
The robot of translation.
Background technology
With the quickening of internationalization process, simultaneous interpretation translation demand it is increasing, and existing simultaneous interpretation translation be by people Lai
It completes, professional simultaneous interpretation translator's labor intensity is big, and translation accuracy is vulnerable to the influence of personal physical factors, in international meeting
In view, if the duration of meeting is long, after the physical and energy constantly overdraw of translator, it will because fatigue makes translation
Accuracy declines；When individual travels abroad, since the simultaneous interpretation translation salary level of profession is high, general ruck is relatively difficult to connect
It is gone on a journey by translator is carried.
Invention content
Voice is carried out using artificial intelligence BP neural network algorithm the invention mainly solves the technical problem of providing a kind of
The robot of translation can substitute the advanced simultaneous interpretation translation of high wages, and providing to the user will not be because of translation time length and because tired
Translation error caused by labor.
In order to solve the above technical problems, one aspect of the present invention is：It provides a kind of using artificial intelligence BP
Neural network algorithm carries out the robot of voiced translation, and feature includes：Robot body, cloud computing center BP neural network are turned over
Module, cloud computing center large database concept are translated, three critical pieces are constituted.
The beneficial effects of the invention are as follows：The robot body of the present invention passes through the network interconnection, cloud computing with cloud computing center
Large database concept is translated by various countries' language voice with cloud computing center equipped with BP neural network algoritic module, the module in center
After progress data link, every data target is subjected to combined training to BP neural network model so that BP neural network module
It can be to handing over the rate of accuracy reached for passing translation to 95% or more, to the rate of accuracy reached of simultaneous interpretation translation to 70% or more.
BP neural network model carries the method that mandarin carries out data training with English：BP neural network be after to biography
Network is broadcast, by one group of training sample of iterative processing, the neural network forecast of each sample is compared progress with known actual value
Study.For each training sample, modification weight matrix makes the mean square deviation between neural network forecast and actual value reach minimum.This
Kind modification is " backward " to be carried out, i.e., passes through each hidden layer by output layer, then arrive input layer, specific training step is as follows：
Step（1）, to large database concept carry out data analysis with mark, form N number of training sample；
Step（2）, to n carry out assignment, for each node of the input layer of network output be equal to input；Intermediate is hidden
Layer, the input of node J are represented by：
Wherein：For the active deviator of unit J, generally take [- 1,1]
Step（3）, BP networks take the excitation function of continuous type, form is such as：
From the output that can obtain node j：
Step（4）, repeat step（2）And step（3）Calculating process, until obtain the reality output of output layerThen compare
Reality output and desired output change weight by errorAnd biasingSo that error reaches minimum, for output unit k
The form of error is：
Wherein,For the desired output of output layer unit, in order to avoid being absorbed in locally optimal solution, by updating weight and deviator,
Learning rate takes, can obtain
Similarly, the weight for implying layer unit j and last layer unit i is updatedAnd deviatorIt can obtain
Description of the drawings
Fig. 1 be the present invention it is a kind of using artificial intelligence BP neural network algorithm carry out voiced translation robot, data
The building-block of logic of transmission.
Specific implementation mode
The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
Referring to Fig. 1, the robot of voiced translation is carried out using artificial intelligence BP neural network algorithm, including：Robot
Main body, cloud computing center BP neural network translation module, cloud computing center large database concept, three critical pieces are constituted, are used
Robot acquisition user voice data is transmitted to cloud computing center, and the BP neural network translation module of cloud computing center passes through to cloud
Translation data are linked and are translated training in the large database concept at calculating center, the user speech number that can come to robotic transfer
According to being translated, and translation data are synchronized and pass robot back, the target state language translated is played into needs by robot
The user of translation listens to.
Example the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (6)
1. a kind of robot carrying out voiced translation using artificial intelligence BP neural network algorithm, which is characterized in that including：Machine
Human agent, cloud computing center BP neural network translation module, cloud computing center large database concept, three critical pieces are constituted.
2. a kind of robot carrying out voiced translation using artificial intelligence BP neural network algorithm according to claim 1,
It is characterized in that：Robot body can carry out the input and output of voice data, first, machine be set with conversational mode by user
The input and output language of device people needs the category of language translated, robot energy automatic identification user talks with therewith to be set
When the category of language that sends out, and carry out automatic adaptation；When translating progress：Robot body passes through net with high in the clouds cloud computing center
Network is connected in real time, the audio data transmitted from robot is obtained by cloud computing center, by carrying out audio number after identification
According to translation, then passing robot back, the audio data after translation is played to user by robot again.
3. a kind of robot carrying out voiced translation using artificial intelligence BP neural network algorithm according to claim 1,
It is characterized in that robot body part by：Robot shells, microphone, sound equipment, voice expression sound-optical controller, LED light group
Part, rechargeable battery, wifi module, 4G modules, USB interface and USB line are constituted.
4. a kind of robot carrying out voiced translation using artificial intelligence BP neural network algorithm according to claim 1,
It is characterized in that cloud computing center large database concept by：The audio large database concept of Chinese speech pronunciation, the sound of Chinese each place dialect pronunciation
The grammer number of frequency large database concept, the audio large database concept of countries in the world sound pronunciation, Chinese grammar database, countries in the world language
It is constituted according to the proper noun translation large database concept of the dictionary for translation large database concept of library, Chinese and countries in the world, industry-by-industry；Wherein
Each large database concept related with audio is read aloud the audio data of state's language by not less than 20 male and female, to carry
The error correction that high BP neural network comes in and goes out to subtle accent in translation improves translation accuracy rate.
5. a kind of robot carrying out voiced translation using artificial intelligence BP neural network algorithm according to claim 1,
It is characterized in that：Cloud computing center is equipped with BP neural network translation module, which passes through big with cloud computing center
Information in database is linked, and then carries out the training of BP neural network translation model so that hands over the accuracy rate for passing translation
Reach 95% or more, the rate of accuracy reached of simultaneous interpretation translation to 70% or more, with ensure when users use can be promptly and accurately progress
Translation.
6. the BP neural network translation module that cloud computing center according to claim 5 carries, training method includes such as
Lower step：
Step（1）, to large database concept carry out data analysis with mark, form N number of training sample；
Step（2）, to n carry out assignment, for each node of the input layer of network output be equal to input；Intermediate is hidden
Layer, the input of node J are represented by：
Wherein：For the active deviator of unit J, generally take [- 1,1]
Step（3）, BP networks take the excitation function of continuous type, form is such as：
From the output that can obtain node j：
Step（4）, repeat step（2）And step（3）Calculating process, until obtain the reality output of output layerThen compare
Reality output and desired output change weight by errorAnd biasingSo that error reaches minimum, for output unit k
The form of error is：
Wherein,It, by updating weight and deviator, is learned for the desired output of output layer unit in order to avoid being absorbed in locally optimal solution
Habit rate takes, can obtain
Similarly, the weight for implying layer unit j and last layer unit i is updatedAnd deviatorIt can obtain
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710172488.XA CN108628836A (en) | 2017-03-22 | 2017-03-22 | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710172488.XA CN108628836A (en) | 2017-03-22 | 2017-03-22 | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108628836A true CN108628836A (en) | 2018-10-09 |
Family
ID=63706912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710172488.XA Pending CN108628836A (en) | 2017-03-22 | 2017-03-22 | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628836A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110047505A (en) * | 2019-03-07 | 2019-07-23 | 永德利硅橡胶科技(深圳)有限公司 | The implementation method and Related product of Quan Yutong neural network based |
| CN110362837A (en) * | 2019-07-23 | 2019-10-22 | 闽南师范大学 | A kind of artificial intelligence translation integrated system |
| CN110362838A (en) * | 2019-07-23 | 2019-10-22 | 闽南师范大学 | A kind of translating equipment based on artificial intelligence |
| CN111046140A (en) * | 2019-11-25 | 2020-04-21 | 华中科技大学同济医学院附属协和医院 | Automatic office service communication robot and control method thereof |
| CN112395889A (en) * | 2019-08-01 | 2021-02-23 | 林超伦 | Machine-synchronized translation |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203812242U (en) * | 2014-05-23 | 2014-09-03 | 陈修志 | Desk-type translating machine |
-
2017
- 2017-03-22 CN CN201710172488.XA patent/CN108628836A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203812242U (en) * | 2014-05-23 | 2014-09-03 | 陈修志 | Desk-type translating machine |
Non-Patent Citations (2)
| Title |
|---|
| 孙晓 等: "基于神经网络技术的机器翻译模型", 《株洲工学院学报》 * |
| 贝特•麦克哈贝尔: "《R语言数据挖掘》", 30 November 2016 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110047505A (en) * | 2019-03-07 | 2019-07-23 | 永德利硅橡胶科技(深圳)有限公司 | The implementation method and Related product of Quan Yutong neural network based |
| CN110362837A (en) * | 2019-07-23 | 2019-10-22 | 闽南师范大学 | A kind of artificial intelligence translation integrated system |
| CN110362838A (en) * | 2019-07-23 | 2019-10-22 | 闽南师范大学 | A kind of translating equipment based on artificial intelligence |
| CN112395889A (en) * | 2019-08-01 | 2021-02-23 | 林超伦 | Machine-synchronized translation |
| CN111046140A (en) * | 2019-11-25 | 2020-04-21 | 华中科技大学同济医学院附属协和医院 | Automatic office service communication robot and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108628836A (en) | The robot of voiced translation is carried out using artificial intelligence BP neural network algorithm | |
| CN108170749A (en) | Dialogue method, device and computer-readable medium based on artificial intelligence | |
| CN107492382A (en) | Voiceprint extracting method and device based on neutral net | |
| CN108510976A (en) | A kind of multilingual mixing voice recognition methods | |
| Rennicke | Variation and change in the rhotics of Brazilian Portuguese | |
| CN110110337A (en) | Translation model training method, medium, device and calculating equipment | |
| CN109410974A (en) | Sound enhancement method, device, equipment and storage medium | |
| CN107230401A (en) | Utilize internet and the Teaching of Writing interactive system and implementation method of voice technology | |
| CN110010136A (en) | The training and text analyzing method, apparatus, medium and equipment of prosody prediction model | |
| CN109376360A (en) | A kind of method and apparatus of assisted learning language | |
| CN109493658A (en) | Situated human-computer dialogue formula spoken language interactive learning method | |
| CN112686056A (en) | Emotion classification method | |
| CN110598208A (en) | AI/ML enhanced pronunciation course design and personalized exercise planning method | |
| CN103810993B (en) | Text phonetic notation method and device | |
| CN109977401A (en) | A kind of method for recognizing semantics neural network based | |
| Duan et al. | Effective articulatory modeling for pronunciation error detection of L2 learner without non-native training data | |
| CN108091185A (en) | The word learning system and its word learning method combined into syllables based on syllable | |
| CN110489744A (en) | A kind of processing method of corpus, device, electronic equipment and storage medium | |
| Wang | Research on open oral English scoring system based on neural network | |
| Yuan et al. | Exploration of English speech translation recognition based on the LSTM RNN algorithm | |
| CN108717854A (en) | Method for distinguishing speek person based on optimization GFCC characteristic parameters | |
| CN108352126A (en) | Foreign language pronunciation and labelling apparatus and its method, including the use of the motor learning device based on foreign language rhythm action sensor, motor learning method and the electronic medium recorded to it and study teaching material of its device and method | |
| TWI594136B (en) | A system and method for training robots through voice | |
| CN108628841A (en) | The APP of Guangdong language accent and English is translated based on BIRCH clustering algorithms | |
| Duan et al. | Efficient learning of articulatory models based on multi-label training and label correction for pronunciation learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181009 |
|
| WD01 | Invention patent application deemed withdrawn after publication |