CN109272983A - Bilingual switching device for child-parent education - Google Patents

Bilingual switching device for child-parent education Download PDF

Info

Publication number
CN109272983A
CN109272983A CN201811191473.9A CN201811191473A CN109272983A CN 109272983 A CN109272983 A CN 109272983A CN 201811191473 A CN201811191473 A CN 201811191473A CN 109272983 A CN109272983 A CN 109272983A
Authority
CN
China
Prior art keywords
cloud
module
voice
target language
bilingual
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
Application number
CN201811191473.9A
Other languages
Chinese (zh)
Inventor
谭辽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Liaojiang Technology Co Ltd
Original Assignee
Wuhan Liaojiang Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan Liaojiang Technology Co Ltd filed Critical Wuhan Liaojiang Technology Co Ltd
Priority to CN201811191473.9A priority Critical patent/CN109272983A/en
Publication of CN109272983A publication Critical patent/CN109272983A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00Speech synthesis; Text to speech systems
    • G10L13/02Methods for producing synthetic speech; Speech synthesisers
    • G10L13/04Details of speech synthesis systems, e.g. synthesiser structure or memory management
    • G10L13/047Architecture of speech synthesisers
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/40Processing or translation of natural language
    • G06F40/58Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00Electrically-operated educational appliances
    • G09B5/06Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
    • G09B5/065Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00Speech synthesis; Text to speech systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/28Constructional details of speech recognition systems
    • G10L15/30Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

The present invention relates to the bilingual switching devices for child-parent education, including the terminal device and cloud server mutually communicated, voice input module, bilingual switching executing module are provided on the terminal device, cloud processing module comprising communication unit, voice output module;The cloud server includes the cloud speech recognition module being sequentially electrically connected, cloud semantic understanding translation module, cloud target language voice synthetic module, further includes memory module.The device of the invention allow will not the parent of target language language bilingual education, such as English, French etc. swimmingly are carried out to child;The language for the person that can identify education and guidance simultaneously translates into target language language, then repeats and listens to child, and being added to picture (as) can be more intuitive, joined the effect of assessment device test child's study.

Description

Bilingual switching device for child-parent education
Technical field
The present invention relates to artificial intelligent voice identification, semantic understanding and speech synthesis solution technical applications, especially use In the bilingual switching device of child-parent education.
Background technique
In child-parent education, parent is in order to allow child preferably to learn two or more language, and parent is as child-parent education Guide (user), as teacher, child interacts between three as child-parent education object artificial intelligence device, to Achieve the purpose that education and training child learns multilingual, needs in multilingual set to artificial intelligence device, according to religion Trained child's language is educated to need that multilingual is enable mutually to switch.Currently, patent 201711194068.8, discloses one kind Intelligent sound interactive device is related to technical field of voice interaction, including sound acquisition module, PFGA preprocessing module, intelligence are handed over Mutual center;PFGA preprocessing module includes end-point detection unit;End-point detection unit is mentioned with sound pretreatment unit, feature respectively Unit is taken electrically to be electrically connected;Intelligent interaction center includes control unit;Control unit respectively with storage unit, speech recognition mould Block, semantic understanding module, interaction process module, voice synthetic module, feedback module, loudspeaker are electrically electrically connected;The storage Unit is electrically electrically connected with speech recognition module, semantic understanding module, interaction process module respectively;Voice synthetic module respectively with Semantic understanding module, interaction process module are electrically electrically connected;Be equipped in the storage unit language model library, sound model library, Semantic dictionary database, response message library;Acoustic model repository includes HMM model database and ANN model database;Language model Library includes N-Gram model database and Rule-based model database, using feedback module to the feedback of identification information, and It by control unit to present customers identification information, while controlling and changing Sound Match model and language model library, improve interaction The interactive identification accuracy of device.But without providing the bilingual handoff technique of child-parent education.
Summary of the invention
In view of the deficiencies of the prior art, using artificial intelligent voice interaction technique, the bilingual switching people of child-parent education is provided Work intelligent apparatus interacts parent, artificial intelligence device and child, realizes language learning child-parent education, use of the invention In the bilingual switching device of child-parent education, characterized by comprising: the terminal device and cloud server mutually communicated,
It is provided on the terminal device
Voice input module, for obtaining externally input original languages voice signal;
Bilingual switching executing module, for selecting or being arranged asking for the cloud target language speech synthesis result that need to switch It asks;
Cloud processing module comprising communication unit, the cloud processing module by communication unit and cloud server into Row data exchange, for the original languages voice signal to be sent to cloud server and executes cloud by the cloud server Speech recognition, the translation of cloud semantic understanding and cloud target language speech synthesis are held, the cloud that the cloud server is sent is received Hold speech recognition, the translation of cloud semantic understanding and cloud target language speech synthesis result;
Voice output module, the voice signal of the result for exporting cloud target language speech synthesis;
The voice input module is electrically connected bilingual switching executing module, and the bilingual switching executing module is electrically connected cloud Processing module, the cloud processing module are electrically connected voice output module;
The cloud server include the cloud speech recognition module being sequentially electrically connected, cloud semantic understanding translation module, Cloud target language voice synthetic module, further includes memory module, the memory module respectively with cloud speech recognition module, Cloud semantic understanding translation module, the electrical connection of cloud target language voice synthetic module.
Further, the bilingual switching executing module includes target language control unit, for double required for determining The target language of language switching sends the voice signal to cloud speech recognition module, then carries out the conversion of cloud language text With cloud target language speech synthesis.
Specifically, the voice output module includes loudspeaker, for providing cloud target language voice with speech form Composite result.
Optionally, the terminal device connects mutual communication by radio network interface with the cloud server.
Further, the terminal device further includes image display module, the corresponding cloud server further include with The corresponding image library of the cloud semantic understanding translation result provides cloud image library by image display module with image format Matching result, and be showed on the image display unit of terminal device;Described image display module and the cloud processing module Electrical connection carries out data exchange by the communication unit and cloud server.
Further, the terminal device further includes with reading module of testing and assessing, for child-parent education object with reading cloud target The voice content of languages speech synthesis result is tested and assessed with reading, is obtained by voice input module with reading voice signal, cloud processing Module is used to be sent to cloud server with reading voice signal for described and executes cloud speech recognition by the cloud server, According to cloud speech recognition result give with read voice assessment, it is described with read assessment module respectively with voice input module and cloud Processing module electrical connection.
Specifically, described with reading assessment module includes text semantic extraction method with reading unit of testing and assessing, and is mentioned using text semantic It follows the example of and carries out with reading to test and assess.
Bilingual switching device for child-parent education of the invention is led in multilingual set to artificial intelligence device Cross artificial intelligent voice interactive application technology, allow education and guidance person and child-parent education object (child) using the device (teacher) into Row interacts bilingual switching, and the original languages language of input can repeat to export, form bilingual education environment, come with target language language Realize that education and training child learns the purpose of multilingual, while the multimedia shows such as picture (as) of arranging in pairs or groups, voice is tested and assessed with reading Etc. functions allow the more interesting smoothness of bilingual exchange, reinforce the effect of bilingual education and user experience.
In short, the device of the invention dictates voice, translation, voice synthetic technology creatively reasonable combination to reach double The purpose of language education, and give figure and test and assess with reading.
Specifically, firstly, the device needs to carry out voice dictation function, i.e. recording voice is then converted into as text;It connects , device can show corresponding picture (as) according to the content and meaning of text, and such as the photo of article, figure, thing are described in movement The animation of part, the sound etc. of music;Meanwhile device can also translate text, be converted to the text of target language language;So Afterwards, the text present apparatus voice of target language language can be synthesized pronunciation and read out by device;Finally, device can use voice Dictation technology is with reading the content of translation and giving with reading voice assessment marking.
The device of the invention allow will not target language language parent swimmingly to child carry out bilingual education, than Such as English, French etc.;The language for the person that can identify education and guidance simultaneously translates into target language language, then repeats and listens to child, adds Add picture (as) more intuitive, joined the effect of assessment device test child's study.
Detailed description of the invention
Fig. 1 is the circuit theory schematic diagram of the device of the embodiment of the present invention one;
Fig. 2 is the circuit theory schematic diagram of the device of the embodiment of the present invention two;
Fig. 3 is the circuit theory schematic diagram of the device of the embodiment of the present invention three.
Wherein, 1- terminal device, 101-PC machine, 102- mobile phone, 11- voice input module, the bilingual switching of 12- execute mould Block, 121- target language control unit, 13- cloud processing module, 131- communication unit, 14- voice output module, 15- is with reading Assessment module, 16- image display module, 2- cloud server, the cloud 21- speech recognition module, the translation of the cloud 22- semantic understanding Module, the cloud 23- target language voice synthetic module, 24- memory module are (interior to be equipped with language model library, sound model library, semanteme Dictionary database, response message library), 25- image library.
Specific embodiment
The invention will be further described with reference to embodiments.
Embodiment one:
As shown in Figure 1, being used for the bilingual switching device of child-parent education, comprising: the terminal device mutually communicated and cloud clothes Business device, the terminal device are PC machine, install apple windos operating system;
It is provided on the terminal device
Voice input module, it is externally input original for obtaining including the microphone being mounted on the terminal device Languages voice signal is Chinese speech signal in the present embodiment;
Bilingual switching executing module, for selecting or being arranged asking for the cloud target language speech synthesis result that need to switch It asks;The voice signal is sent extremely for the target language of bilingual switching required for determining including target language control unit Cloud speech recognition module selects in the present embodiment or the cloud target language speech synthesis result that need to switch is arranged to be English language Sound signal;
Cloud processing module comprising communication unit, the cloud processing module by communication unit and cloud server into Row data exchange is known for the voice signal to be sent to cloud server and execute cloud voice by the cloud server Not, the translation of cloud semantic understanding and cloud target language speech synthesis receive the cloud voice that the cloud server is sent and know Not, the translation of cloud semantic understanding and cloud target language speech synthesis result;In the present embodiment, specifically: it is other that voice knows module The voice of Chinese is converted to Chinese text, Chinese text is translated into English text, speech synthesis by semantic understanding translation module English text is synthesized the voice of english language by module;
Voice output module, including the loudspeaker being mounted on the terminal device, for exporting cloud target language language The English voice signal of the result of sound synthesis, there are two loudspeakers for setting in the present embodiment;
The voice input module is electrically connected bilingual switching executing module, and the bilingual switching executing module is electrically connected cloud Processing module, the cloud processing module are electrically connected voice output module;
The cloud server include the cloud speech recognition module being sequentially electrically connected, cloud semantic understanding translation module, Cloud target language voice synthetic module, further includes memory module, the memory module respectively with cloud speech recognition module, Cloud semantic understanding translation module, the electrical connection of cloud target language voice synthetic module, the interior language that is equipped with of the memory module (contain Original languages language and target language language) model library, sound (containing original languages sound and target language sound) model library, language Adopted dictionary (containing original languages language and target language language) database, response message library.Wherein the cloud speech recognition (contains Original languages speech recognition and target language speech recognition) module, cloud semantic understanding translation module and cloud target language language Sound synthesis module is all made of Baidu's brain or Iflytek speech processes, semantic understanding and Speech Synthesis Algorithm.
The terminal device connects mutual communication by wired network interface with the cloud server.
Embodiment two:
As shown in Fig. 2, be used for child-parent education bilingual switching device, with embodiment one the difference is that: the terminal Equipment is mobile phone, installs Android operation system;The terminal device and the cloud server are connected by radio network interface Connect mutual communication;The terminal device further includes with reading module of testing and assessing, for child-parent education object with reading cloud target language language The voice content of sound composite result with read test and assess, by voice input module obtain with read voice signal, cloud processing module its In communication unit be used for by it is described with read voice signal be sent to cloud server and by the cloud server execute cloud Speech recognition, that is, cloud language text converts and receives text conversion results, is converted with reading assessment module according to cloud language text As a result give testing and assessing with reading voice, it is described to be carried out using text semantic extraction algorithm with reading assessment, such as 5 with reading assessment module Having 4 words in the text information of word is target word (word met the requirements), accounts for 80%, meeting threshold value, (threshold value is set as being not less than 80%) it requires, assessment is qualified.With read assessment module respectively with voice input module, cloud processing module and voice output module Electrical connection.The text results for showing " this test passes " on mobile phone screen or loudspeaker are sent out with reading assessment module The result (sound) of " this test passes ".
Remaining content is the same as embodiment one.
Embodiment three:
As shown in figure 3, be used for child-parent education bilingual switching device, with embodiment two the difference is that: the terminal Equipment further includes image display module, and the corresponding cloud server further includes and the cloud semantic understanding translation result phase Corresponding image library provides cloud image library matching result by image display module with image format, and is showed in terminal device Image display unit on, in the present embodiment be mobile phone display screen;Specifically, the cloud language received according to cloud processing module Sound identification, cloud semantic understanding translation result (text returned), extract keyword, then show these in the form of a list The relevant information of keyword, such as keyword are apple (apple), then show the example diagram of apple, the contents such as brief introduction;
Described image display module is electrically connected with the cloud processing module, passes through the communication list of the cloud processing module Member carries out data exchange with cloud server.
It include the photo of article in described image library, figure, the contents such as animation of event are described in movement.
The device of the present embodiment can show corresponding picture (as), such as article according to the semantic content and meaning of understanding Photo, movement describes figure, the animation of event, the sound etc. of music, by the comprehensive stimulation to child's eye, ear, brain, by force Change learning effect.

Claims (7)

1. being used for the bilingual switching device of child-parent education, characterized by comprising: the terminal device and cloud service mutually communicated Device,
It is provided on the terminal device
Voice input module, for obtaining externally input original languages voice signal;
Bilingual switching executing module, for selecting or being arranged the request for the cloud target language speech synthesis result that need to switch;
Cloud processing module comprising communication unit, the cloud processing module are counted by communication unit and cloud server According to exchange, for the original languages voice signal to be sent to cloud server and executes cloud language by the cloud server Sound identification, the translation of cloud semantic understanding and cloud target language speech synthesis, receive the cloud language that the cloud server is sent Sound identification, the translation of cloud semantic understanding and cloud target language speech synthesis result;
Voice output module, the voice signal of the result for exporting cloud target language speech synthesis;
The voice input module is electrically connected bilingual switching executing module, the bilingual switching executing module electrical connection cloud processing Module, the cloud processing module are electrically connected voice output module;
The cloud server includes the cloud speech recognition module being sequentially electrically connected, cloud semantic understanding translation module, cloud Target language voice synthetic module further includes memory module, the memory module respectively with cloud speech recognition module, cloud Semantic understanding translation module, the electrical connection of cloud target language voice synthetic module.
2. bilingual switching device according to claim 1, it is characterised in that the bilingual switching executing module includes target Languages control unit sends the voice signal to cloud voice and knows for the target language of bilingual switching required for determining Other module.
3. bilingual switching device according to claim 1, it is characterised in that the voice output module includes loudspeaker, is used In with speech form offer cloud target language speech synthesis result.
4. bilingual switching device according to claim 1, which is characterized in that the terminal device and the cloud server Mutually communication is connected by radio network interface.
5. bilingual switching device according to claim 1, which is characterized in that the terminal device further includes that image shows mould Block, the corresponding cloud server further includes image library corresponding with the cloud semantic understanding translation result, by image Display module provides cloud image library matching result with image format, and is showed on the image display unit of terminal device;Institute Image display module is stated to be electrically connected with the cloud processing module, by the image library of the communication unit and cloud server into Row data exchange.
6. bilingual switching device according to claim 1, which is characterized in that the terminal device further includes with reading mould of testing and assessing Block, for child-parent education object with read cloud target language speech synthesis result voice content with read test and assess, it is defeated by voice Enter module obtain with read voice signal, cloud processing module be used for by it is described with read voice signal be sent to cloud server and by The cloud server executes cloud speech recognition, is given according to cloud speech recognition result with reading voice assessment, described with reading Assessment module is electrically connected with voice input module and cloud processing module respectively.
7. bilingual switching device according to claim 6, which is characterized in that it is described with read assessment module include text semantic Extraction method is carried out using text semantic extraction method with reading to test and assess with reading unit of testing and assessing.
CN201811191473.9A 2018-10-12 2018-10-12 Bilingual switching device for child-parent education Pending CN109272983A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811191473.9A CN109272983A (en) 2018-10-12 2018-10-12 Bilingual switching device for child-parent education

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811191473.9A CN109272983A (en) 2018-10-12 2018-10-12 Bilingual switching device for child-parent education

Publications (1)

Publication Number Publication Date
CN109272983A true CN109272983A (en) 2019-01-25

Family

ID=65197190

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811191473.9A Pending CN109272983A (en) 2018-10-12 2018-10-12 Bilingual switching device for child-parent education

Country Status (1)

Country Link
CN (1) CN109272983A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110767005A (en) * 2019-09-26 2020-02-07 北京光年无限科技有限公司 Data processing method and system based on intelligent equipment special for children
CN112002325A (en) * 2020-10-27 2020-11-27 苏州思必驰信息科技有限公司 Multi-language voice interaction method and device
WO2021114617A1 (en) * 2020-05-28 2021-06-17 平安科技(深圳)有限公司 Voice synthesis method and apparatus, computer device, and computer readable storage medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110767005A (en) * 2019-09-26 2020-02-07 北京光年无限科技有限公司 Data processing method and system based on intelligent equipment special for children
WO2021114617A1 (en) * 2020-05-28 2021-06-17 平安科技(深圳)有限公司 Voice synthesis method and apparatus, computer device, and computer readable storage medium
CN112002325A (en) * 2020-10-27 2020-11-27 苏州思必驰信息科技有限公司 Multi-language voice interaction method and device
CN112002325B (en) * 2020-10-27 2021-02-09 苏州思必驰信息科技有限公司 Multi-language voice interaction method and device

Similar Documents

Publication Publication Date Title
CA2929018C (en) Natural expression processing method, processing and response method, device and system
CN109272983A (en) Bilingual switching device for child-parent education
CN110490213B (en) Image recognition method, device and storage medium
CN110288077A (en) A kind of synthesis based on artificial intelligence is spoken the method and relevant apparatus of expression
US20210233521A1 (en) Method for speech recognition based on language adaptivity and related apparatus
CN104380375A (en) Device for extracting information from a dialog
CN107992195A (en) A kind of processing method of the content of courses, device, server and storage medium
WO2020215966A1 (en) Remote teaching interaction method, server, terminal and system
CN107798931A (en) A kind of intelligent children education learning system and method
US20190371319A1 (en) Method for human-machine interaction, electronic device, and computer-readable storage medium
CN109360458A (en) Interest assistant teaching method, device and robot
Antunes et al. A framework to support development of sign language human-computer interaction: Building tools for effective information access and inclusion of the deaf
CN105551327A (en) Interactive pronunciation correcting system and method based on soft electronic skin
Bangalore et al. Balancing data-driven and rule-based approaches in the context of a multimodal conversational system
CN209625781U (en) Bilingual switching device for child-parent education
EP3404555A1 (en) Speech converter
KR20130086971A (en) Question answering system using speech recognition and its application method thereof
Oliveira et al. The VirtualSign Channel for the Communication Between Deaf and Hearing Users
CN110600033A (en) Learning condition evaluation method and device, storage medium and electronic equipment
WO2019156536A1 (en) Method and computer device for constructing or updating knowledge base model for interactive ai agent system by labeling identifiable, yet non-learnable, data from among learning data, and computer-readable recording medium
CN110444087A (en) A kind of intelligent language teaching machine device people
KR102098377B1 (en) Method for providing foreign language education service learning grammar using puzzle game
US20200004768A1 (en) Method for processing language information and electronic device therefor
Gayathri et al. Sign Language Recognition For Deaf And Dumb People Using Android Environment
CN108073572A (en) Information processing method and its device, simultaneous interpretation system

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