CN206711600U - The voice interactive system with emotive function based on reality environment - Google Patents
The voice interactive system with emotive function based on reality environment Download PDFInfo
- Publication number
- CN206711600U CN206711600U CN201720170435.XU CN201720170435U CN206711600U CN 206711600 U CN206711600 U CN 206711600U CN 201720170435 U CN201720170435 U CN 201720170435U CN 206711600 U CN206711600 U CN 206711600U
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- speech
- unit
- external server
- 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.)
- Active
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The utility model provides a kind of voice interactive system with emotive function based on reality environment,Including voice mobile terminal,Virtual environment terminal,External server,User speech is gathered by voice mobile terminal,And handled,It is control command or speech exchange information to obtain so as to obtain user speech information,And send to virtual environment terminal,Carry out corresponding control operation and corresponding emotion,Action display and broadcasting,So as to the exchange of more people in actual environment of Virtual User,Function of the present utility model is departing from the dependence to handle,And quantity is not influenceed by button,It is simple to operate,And pass through the operation of user's speech control system,In addition,The mood for going out user by extracting user from user speech information,Action message,So as to which Virtual User mutually exchanges and expressed oneself emotion in actual environment in multiplayer or application,Really realize emotion communication,Further increase experience effect of the user in virtual environment.
Description
Technical field
It the utility model is related to a kind of technical field of reality environment, it is especially a kind of based on reality environment
Voice interactive system with emotive function.
Background technology
Virtual reality (Virtual Reality, referred to as " VR ") is the new and high technology occurred in recent years, and its principle is to utilize
Computer simulation produces the virtual world of a three dimensions, and the mould on sense organs such as vision, the sense of hearing, tactiles is provided to user
Intend, allow user as on the spot in person, the things in three dimensions can be observed in time, without limitation.And interact control
Field processed is one of important application direction of virtual reality technology, and the also fast development for virtual reality technology has played huge need
Seek draw.
At present, some science-and-technology enterprises have been proposed corresponding virtual reality control device, for example, Oculus companies of the U.S.
HTC Vive that Gear, HTC company that Oculus Rift of release, Samsung of South Korea release release etc..However, these are empty
The control system for intending real world devices remains in the control method of handle.
A kind of interaction handle for virtual reality control of Chinese patent 201610869534.7, it is open a kind of for void
Intend the operation handle of actual environment, implementation method is complicated, control is not accurate, control instruction limited amount is in key number.And
These control modes can not but manipulate for the handicapped people of hand;The handle control flow for domestic consumer
It is more complicated, it is to be understood that the function of each button could operate.
Chinese patent is a kind of 201610270381.4 multi-user voice exchange method based on Virtual Reality scene
And device;The simply function of voice call exchange of the simple realization in the multiplayer of virtual environment, but can not be in void
Expression, mood, action of game role etc. are seen in the game in near-ring border;See that the personage in game is simply simple fixed
Expression, nozzle type action speaking, have no emotion in speech exchange.
The content of the invention
In view of the shortcomings of the prior art, the utility model provides the voice with emotive function based on reality environment
Interactive system, so as to avoid dependent on complex operation caused by button, sensing equipment in virtual environment, function is by by bond number
The problems such as amount limitation.
The technical solution of the utility model is:A kind of interactive voice system with emotive function based on reality environment
System, it is characterised in that:Including voice mobile terminal, virtual environment terminal, external server, the external server respectively with language
Sound mobile terminal, the connection of virtual environment terminal called, the voice mobile terminal are connected with virtual environment terminal called;
The voice mobile terminal includes processor, and what is be connected with processor is used to gather the voice signal of user, and right
The voice acquisition module that the voice signal of collection is pre-processed;
It is connected to the voice signal of pretreatment being converted into the sound identification module of text message with processor;
What is be connected with processor is used to extract the speech emotional characteristic parameter of the parameter with affective characteristics in text message
Extraction module;
What is be connected with processor is used to store voice recognition data, the voice control command from external server loading renewal
The memory module of database and speech emotional database;
What is be connected with processor is used to be connected with virtual environment terminal called, so as to the control command or voice that will identify that
Exchange of information is sent to virtual environment terminal, and is connected for being communicated with external server, so as to by phase in external server
The packet answered loads renewal to the wireless communication module in memory module;
The voice acquisition module is connected with sound identification module respectively, the connection of speech emotional characteristic parameter extraction module,
The memory module is connected with sound identification module and speech emotional characteristic parameter extraction module respectively;
The virtual environment terminal include be used for store from external server loading renewal virtual portrait emotional facial expressions and
The memory cell of intonation and word speed database corresponding to the model library of action, speech emotional;
For playing in the speech exchange information received there is intonation and the word of word speed or the voice of sentence to broadcast
Amplification module,
For showing the emotional facial expressions of virtual portrait and the display module of action in speech exchange information,
For being connected with voice communication of mobile terminal, and communicate and connect with external server, so as to by external server
In corresponding packet load that to update into memory cell be communication module.
Described voice acquisition module is mainly microphone.
Described sound identification module includes speech feature extraction unit, phonetic feature comparing unit, comparative result output
Unit, the speech feature extraction unit are connected with phonetic feature comparing unit, and the phonetic feature comparing unit is tied compared with
Fruit output unit connects.
The speech emotional characteristic parameter extraction module includes affective feature extraction unit, affective characteristics comparing unit, feelings
Feel feature output unit, the affective feature extraction unit is connected with affective characteristics comparing unit, and the affective characteristics is more single
Member is connected with affective characteristics output unit.
The voice playing module includes intonation matching unit, voice playing unit, the intonation matching unit and voice
Broadcast unit connects.
The display module includes action matching unit, display unit, and the action matching unit is connected with display unit.
Voice mobile terminal is attached with virtual environment terminal, after successful connection, the processor of voice mobile terminal, void
Near-ring border terminal sends database version querying command to external server respectively, in the memory module of voice inquirement mobile terminal
The voice recognition data of storage, the version of voice control command database and speech emotional database and virtual environment terminal
Memory cell in intonation and word speed data corresponding to the virtual portrait emotional facial expressions that store and the model library of action, speech emotional
Whether the version in storehouse is consistent with external server, updates corresponding latest edition from external server loading if inconsistent
Data are into corresponding memory module, memory cell, so that memory module is last state with the data in memory cell;
Voice acquisition module gathers the voice signal of user, and the voice signal of collection the pre- place such as be filtered to, quantified
Sent after reason to sound identification module, speech emotional characteristic parameter extraction module;
The voice recognition data stored in sound identification module combination memory module converts voice signals into text message
Form, and whether it is control command that text message is matched with the order data in voice control command database;If
It is that control command then generates corresponding control command and parameter, and exports to virtual environment terminal and carry out corresponding control operation;
If not control command, then it is speech exchange information, then passes through speech emotional characteristic parameter extraction module analysis
The waveform of pretreated voice signal, and the parameter with affective characteristics is extracted, there is affective characteristics by what is extracted
Parameter is matched with the mood data of speech emotional database, then that the emotion is special so as to draw corresponding affective characteristics
Sign information MAP corresponding word or sentence are simultaneously delivered to virtual environment terminal,
The action matching unit of virtual environment terminal is by visual human's principle in the affective characteristics and memory cell that receive
Sense expression and the model library of action are matched, and obtain the emotional facial expressions corresponding to the affective characteristics and action, single by showing
Member shows corresponding emotional facial expressions and action;Intonation matching unit is by word corresponding to affective characteristics or sentence and speech emotional pair
Data in the intonation and word speed database answered are matched, and so as to obtain intonation and word speed corresponding to the word or sentence, are led to
Cross voice playing unit and play the corresponding speech exchange information with intonation and word speed, pass through voice playing module and display
Module synchronization plays, so as to the exchange of more people in actual environment of Virtual User.
The beneficial effects of the utility model are:Systemic-function is departing from the dependence to handle, and quantity is not by button shadow
Ring, it is simple to operate, and by the operation of user's speech control system, in addition, by extracting user from user speech information
Go out mood, the action message of user, and by being played accordingly by the way that voice playing module is synchronous with display module, so as to virtual
User mutually exchanges and expressed oneself emotion in actual environment in multiplayer or application, really realizes emotion communication, enters one
Step improves experience effect of the user in virtual environment.
Brief description of the drawings
Fig. 1 is Tthe utility model system frame diagram;
Embodiment
Specific embodiment of the present utility model is described further below in conjunction with the accompanying drawings:
As shown in figure 1, a kind of voice interactive system with emotive function based on reality environment, its feature exist
In:Including voice mobile terminal, virtual environment terminal, external server, the external server respectively with voice mobile terminal,
Virtual environment terminal called is connected, and the voice mobile terminal is connected with virtual environment terminal called;
The voice mobile terminal includes
Voice acquisition module, pre-processed for gathering the voice signal of user, and to collection voice signal;
Sound identification module, for the voice signal of pretreatment to be converted into text message;
Speech emotional characteristic parameter extraction module, there is the ginseng of affective characteristics for extracting in pretreated text message
Number;
Memory module, for storing voice recognition data, voice control command data from external server loading renewal
Storehouse and speech emotional database;
Wireless communication module, control command or speech exchange information for will identify that are sent to virtual environment terminal,
And connected for being communicated with external server, arrive memory module so as to which corresponding packet in external server is loaded into renewal
In;
Processor, loaded more for handling the user speech information of collection or sending more newer command to external server
The voice messaging of new memory module storage;
The processor respectively with voice acquisition module, sound identification module, speech emotional characteristic parameter extraction module, deposit
Store up module, wireless communication module connection;
The voice acquisition module is connected with sound identification module respectively, the connection of speech emotional characteristic parameter extraction module,
The memory module is connected with sound identification module and speech emotional characteristic parameter extraction module respectively;
The virtual environment terminal includes
Memory cell, for storing the virtual portrait emotional facial expressions from external server loading renewal and the model of action
Intonation corresponding to storehouse, speech emotional and word speed database;
Voice playing module, for playing the speech text information received;
Display module, for showing emotional facial expressions and the action of virtual portrait phonetic representation;
Communication module, for voice communication of mobile terminal, and with external server communicate connect, so as to by outside take
Corresponding packet loads renewal into memory cell in business device.
Described voice acquisition module is mainly microphone.
Described sound identification module includes speech feature extraction unit, phonetic feature comparing unit, comparative result output
Unit, the speech feature extraction unit are connected with phonetic feature comparing unit, and the phonetic feature comparing unit is tied compared with
Fruit output unit connects.
The speech emotional characteristic parameter extraction module includes affective feature extraction unit, affective characteristics comparing unit, feelings
Feel feature output unit, the affective feature extraction unit is connected with affective characteristics comparing unit, and the affective characteristics is more single
Member is connected with affective characteristics output unit.
The voice playing module includes intonation matching unit, voice playing unit, the intonation matching unit and voice
Broadcast unit connects.
The display module includes action matching unit, display unit, and the action matching unit is connected with display unit.
Voice mobile terminal is attached with virtual environment terminal, after successful connection, the processor of voice mobile terminal, void
Near-ring border terminal sends database version querying command to external server respectively, in the memory module of voice inquirement mobile terminal
The voice recognition data of storage, the version of voice control command database and speech emotional database and virtual environment terminal
Memory cell in intonation and word speed data corresponding to the virtual portrait emotional facial expressions that store and the model library of action, speech emotional
Whether the version in storehouse is consistent with external server, updates corresponding latest edition from external server loading if inconsistent
Data are into corresponding memory module, memory cell, so that memory module is last state with the data in memory cell;
Voice acquisition module gathers the voice signal of user, and the voice signal of collection the pre- place such as be filtered to, quantified
Sent after reason to sound identification module, speech emotional characteristic parameter extraction module;
The voice recognition data stored in sound identification module combination memory module converts voice signals into text message
Form, whether it is control command that text message is matched with the order data in voice control command database;If
Control command then generates corresponding control command and parameter, and exports to virtual environment terminal and carry out corresponding control operation, tool
The control operation of body can be System menu associative operation, such as " menu ", " return ", " exiting ", " beginning ", " it is determined that ", " take
Disappear " etc.;Can also be man-machine interactive operation, such as related behaviour in gaming is empty, " advancing 50 meters ", " turning left 60 degree ",
" being moved right 30 seconds with the speed of 10 metre per second (m/s)s " etc. operates;
Then it is speech exchange information if not control command, it is pre- by speech emotional characteristic parameter extraction module analysis
The waveform of voice signal after processing, and extract the parameter with affective characteristics, the ginseng with affective characteristics that will be extracted
Number is matched with the mood data of speech emotional database, so as to draw corresponding affective characteristics, then by the affective characteristics
Information MAP corresponding word or sentence, and affective characteristics and the affective characteristics information MAP corresponding word or sentence are conveyed
To virtual environment terminal,
The action matching unit of virtual environment terminal is by visual human's principle in the affective characteristics and memory cell that receive
Sense expression and the model library of action are matched, and obtain the emotional facial expressions corresponding to the affective characteristics and action, single by showing
Member shows corresponding emotional facial expressions and action;Intonation matching unit is by word corresponding to affective characteristics or sentence and speech emotional pair
Data in the intonation and word speed database answered are matched, and so as to obtain intonation and word speed corresponding to the word or sentence, are led to
Cross voice playing unit and play the corresponding speech exchange information with intonation and word speed, pass through voice playing module and display
Module synchronization plays, so as to the exchange of more people in actual environment of Virtual User.
Speech emotional data in the speech emotional database are mainly defeated using classifier training of the prior art
Go out, be used as training sample by first collecting emotion voice data;Then MFCC parameters, formant and zero-crossing rate are extracted to it
Three characteristic parameters simultaneously carry out combinations of features, establish gauss hybrid models;Gauss hybrid models are classified by emotional category, formed
The acoustic model database of each emotional category;When receiving the speech data with emotional culture, characteristic parameter is extracted to it, so
Match afterwards with the acoustic model under each mood classification, finally obtain the emotion information of the voice.
The virtual portrait emotional facial expressions, action model storehouse are mainly established corresponding to all kinds of emotions by 3D modeling software
The 3D person models for the action that expression and the mood habituation of some exaggerations are made.
Speech emotional data in the speech emotional database are mainly defeated using classifier training of the prior art
Go out, be used as training sample by first collecting emotion voice data;Then MFCC parameters, formant and zero-crossing rate are extracted to it
Three characteristic parameters simultaneously carry out combinations of features, establish gauss hybrid models;Gauss hybrid models are classified by emotional category, formed
The acoustic model database of each emotional category;When receiving the speech data with emotional culture, characteristic parameter is extracted to it, so
Match afterwards with the acoustic model under each mood classification, finally obtain the emotion information of the voice.
The virtual portrait emotional facial expressions, action model storehouse are mainly established corresponding to all kinds of emotions by 3D modeling software
The 3D person models for the action that expression and the mood habituation of some exaggerations are made.
Simply illustrate principle of the present utility model and most preferred embodiment described in above-described embodiment and specification, do not taking off
On the premise of the spirit and scope of the utility model, the utility model also has various changes and modifications, these changes and improvements
Both fall within claimed the scope of the utility model.
Claims (6)
- A kind of 1. voice interactive system with emotive function based on reality environment, it is characterised in that:Moved including voice Dynamic terminal, virtual environment terminal, external server, the external server respectively with voice mobile terminal, virtual environment terminal Communication connection, the voice mobile terminal are connected with virtual environment terminal called;The voice mobile terminal includes processor, and what is be connected with processor is used to gather the voice signal of user, and to collection The voice acquisition module that is pre-processed of voice signal;It is connected to the voice signal of pretreatment being converted into the sound identification module of text message with processor;What is be connected with processor is used to extract the speech emotional characteristic parameter extraction of the parameter with affective characteristics in text message Module;What is be connected with processor is used to store voice recognition data, the voice control command data from external server loading renewal Storehouse and the memory module of speech emotional database;What is be connected with processor is used to be connected with virtual environment terminal called, so as to the control command that will identify that or speech exchange Information is sent to virtual environment terminal, and is connected for being communicated with external server, so that will be corresponding in external server Packet loads renewal to the wireless communication module in memory module;The voice acquisition module is connected with sound identification module respectively, the connection of speech emotional characteristic parameter extraction module;The memory module is connected with sound identification module and speech emotional characteristic parameter extraction module respectively;The virtual environment terminal includes being used to store the virtual portrait emotional facial expressions from external server loading renewal and action Model library, the memory cell of intonation and word speed database corresponding to speech emotional;There is intonation and the word of word speed or the voice playing module of sentence for playing in the speech exchange information received,For showing the emotional facial expressions of virtual portrait and the display module of action in speech exchange information,For being connected with voice communication of mobile terminal, and communicate and connect with external server, so as to by phase in external server It is communication module into memory cell that the packet answered, which loads renewal,.
- 2. a kind of voice interactive system with emotive function based on reality environment according to claim 1, its It is characterised by:Described voice acquisition module is mainly microphone.
- 3. a kind of voice interactive system with emotive function based on reality environment according to claim 1, its It is characterised by:Described sound identification module includes speech feature extraction unit, phonetic feature comparing unit, comparative result output Unit, the speech feature extraction unit are connected with phonetic feature comparing unit, and the phonetic feature comparing unit is tied compared with Fruit output unit connects.
- 4. a kind of voice interactive system with emotive function based on reality environment according to claim 1, its It is characterised by:The speech emotional characteristic parameter extraction module includes affective feature extraction unit, affective characteristics comparing unit, feelings Feel feature output unit, the affective feature extraction unit is connected with affective characteristics comparing unit, and the affective characteristics is more single Member is connected with affective characteristics output unit.
- 5. a kind of voice interactive system with emotive function based on reality environment according to claim 1, its It is characterised by:The voice playing module includes intonation matching unit, voice playing unit, the intonation matching unit and language Sound broadcast unit connects.
- 6. a kind of voice interactive system with emotive function based on reality environment according to claim 1, its It is characterised by:The display module includes action matching unit, display unit, and the action matching unit connects with display unit Connect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720170435.XU CN206711600U (en) | 2017-02-24 | 2017-02-24 | The voice interactive system with emotive function based on reality environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720170435.XU CN206711600U (en) | 2017-02-24 | 2017-02-24 | The voice interactive system with emotive function based on reality environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN206711600U true CN206711600U (en) | 2017-12-05 |
Family
ID=60469149
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201720170435.XU Active CN206711600U (en) | 2017-02-24 | 2017-02-24 | The voice interactive system with emotive function based on reality environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN206711600U (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107018611A (en) * | 2017-04-23 | 2017-08-04 | 黄石德龙自动化科技有限公司 | A kind of wisdom lamp control system and control method based on speech recognition and emotion |
CN108159687A (en) * | 2017-12-19 | 2018-06-15 | 芋头科技(杭州)有限公司 | A kind of automated induction systems and intelligent sound box equipment based on more people's interactive processes |
CN108247633A (en) * | 2017-12-27 | 2018-07-06 | 珠海格力节能环保制冷技术研究中心有限公司 | The control method and system of robot |
CN108986803A (en) * | 2018-06-26 | 2018-12-11 | 北京小米移动软件有限公司 | Scenery control method and device, electronic equipment, readable storage medium storing program for executing |
CN109961152A (en) * | 2019-03-14 | 2019-07-02 | 广州多益网络股份有限公司 | Personalized interactive method, system, terminal device and the storage medium of virtual idol |
CN110488975A (en) * | 2019-08-19 | 2019-11-22 | 深圳市仝智科技有限公司 | A kind of data processing method and relevant apparatus based on artificial intelligence |
-
2017
- 2017-02-24 CN CN201720170435.XU patent/CN206711600U/en active Active
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107018611A (en) * | 2017-04-23 | 2017-08-04 | 黄石德龙自动化科技有限公司 | A kind of wisdom lamp control system and control method based on speech recognition and emotion |
CN108159687A (en) * | 2017-12-19 | 2018-06-15 | 芋头科技(杭州)有限公司 | A kind of automated induction systems and intelligent sound box equipment based on more people's interactive processes |
CN108159687B (en) * | 2017-12-19 | 2021-06-04 | 芋头科技(杭州)有限公司 | Automatic guidance system and intelligent sound box equipment based on multi-person interaction process |
CN108247633A (en) * | 2017-12-27 | 2018-07-06 | 珠海格力节能环保制冷技术研究中心有限公司 | The control method and system of robot |
CN108247633B (en) * | 2017-12-27 | 2021-09-03 | 珠海格力节能环保制冷技术研究中心有限公司 | Robot control method and system |
CN108986803A (en) * | 2018-06-26 | 2018-12-11 | 北京小米移动软件有限公司 | Scenery control method and device, electronic equipment, readable storage medium storing program for executing |
CN109961152A (en) * | 2019-03-14 | 2019-07-02 | 广州多益网络股份有限公司 | Personalized interactive method, system, terminal device and the storage medium of virtual idol |
CN110488975A (en) * | 2019-08-19 | 2019-11-22 | 深圳市仝智科技有限公司 | A kind of data processing method and relevant apparatus based on artificial intelligence |
CN110488975B (en) * | 2019-08-19 | 2021-04-13 | 深圳市仝智科技有限公司 | Data processing method based on artificial intelligence and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106710590A (en) | Voice interaction system with emotional function based on virtual reality environment and method | |
CN206711600U (en) | The voice interactive system with emotive function based on reality environment | |
CN110427472A (en) | The matched method, apparatus of intelligent customer service, terminal device and storage medium | |
CN110647636B (en) | Interaction method, interaction device, terminal equipment and storage medium | |
CN111833418B (en) | Animation interaction method, device, equipment and storage medium | |
CN110400251A (en) | Method for processing video frequency, device, terminal device and storage medium | |
CN104461525B (en) | A kind of intelligent consulting platform generation system that can customize | |
CN110413841A (en) | Polymorphic exchange method, device, system, electronic equipment and storage medium | |
CN110286756A (en) | Method for processing video frequency, device, system, terminal device and storage medium | |
CN107797663A (en) | Multi-modal interaction processing method and system based on visual human | |
CN107294837A (en) | Engaged in the dialogue interactive method and system using virtual robot | |
CN106200886A (en) | A kind of intelligent movable toy manipulated alternately based on language and toy using method | |
CN109522835A (en) | Children's book based on intelligent robot is read and exchange method and system | |
CN107831905A (en) | A kind of virtual image exchange method and system based on line holographic projections equipment | |
CN204650422U (en) | A kind of intelligent movable toy manipulated alternately based on language | |
CN104317389B (en) | Method and device for identifying character role through action | |
CN106528859A (en) | Data pushing system and method | |
CN108345385A (en) | Virtual accompany runs the method and device that personage establishes and interacts | |
CN109324688A (en) | Exchange method and system based on visual human's behavioral standard | |
CN108416420A (en) | Limbs exchange method based on visual human and system | |
CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
CN107784355A (en) | The multi-modal interaction data processing method of visual human and system | |
CN109343695A (en) | Exchange method and system based on visual human's behavioral standard | |
WO2022089224A1 (en) | Video communication method and apparatus, electronic device, computer readable storage medium, and computer program product | |
CN108052250A (en) | Virtual idol deductive data processing method and system based on multi-modal interaction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |