CN107393538A - Robot interactive method and system - Google Patents
Robot interactive method and system Download PDFInfo
- Publication number
- CN107393538A CN107393538A CN201710616317.1A CN201710616317A CN107393538A CN 107393538 A CN107393538 A CN 107393538A CN 201710616317 A CN201710616317 A CN 201710616317A CN 107393538 A CN107393538 A CN 107393538A
- Authority
- CN
- China
- Prior art keywords
- speech waveform
- user
- waveform
- voice messaging
- speech
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/04—Training, enrolment or model building
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
Abstract
The embodiment of the invention discloses a kind of robot interactive method and system, methods described includes:Obtain the first speech waveform figure of user;The first response message according to corresponding to the first speech waveform figure is replied as target response information, solve the problems, such as that robot answer speed is excessively slow in the prior art, the sound characteristic of user is familiar with by image training robot to improve the answer speed of robot.
Description
Technical field
The present embodiments relate to robotic technology field, more particularly to a kind of robot interactive method and system.
Background technology
Robot (Robot) is the automatic machine system for performing work.It can both receive mankind commander, can run again
The program of advance layout, can also be according to the principle guiding principle action formulated with artificial intelligence technology, for assisting or substituting the mankind
Work.
At present, with the fast development of science and technology, robot can with speech recognition, can also face recognition, therefore machine
Device people can realize to be interacted and behavior interaction with the normal of the mankind.Our mother tongue is Chinese, as English is for our footpath between fields
Raw degree is the same, and the language of user is also very strange for robot.For example, when we and the foreigner link up, first the foreigner
English Translation into Chinese, after understanding the meaning of the foreigner, then the information of response sorted out come by the Chinese of arrangement with Chinese
Translate into English and carry out response.The communication of robot and user are also such.
After robot hears the voice messaging of user, word is converted speech information into, should by text search matching
Text information is answered, then response text information is converted into voice messaging and carries out response, so cumbersome answering causes machine
The answer speed of people is excessively slow.
The content of the invention
The embodiment of the present invention provides a kind of robot interactive method and system, can improve robot response in the prior art
Slow-footed problem.
In a first aspect, the embodiments of the invention provide a kind of robot interactive method, including:
Obtain the first speech waveform figure of user;
The first response message according to corresponding to the first speech waveform figure is replied as target response information.
Further, the first speech waveform figure for obtaining user includes:
Receive the first voice messaging of the user;
First voice messaging is converted into the first speech waveform data, and by the first speech waveform data
Be converted to the first speech waveform figure.
Further, before the first speech waveform figure of the acquisition user, in addition to:
Set preset times threshold value;
When the number for obtaining the first speech waveform figure reaches the preset times threshold value, first response is established
Information and the matching relationship of the first speech waveform figure.
Further, in addition to:
According to vocal print feature, the vocal print feature identical voice messaging and speech waveform figure are stored to same vocal print and believed
Cease storehouse;
Obtain the second speech waveform figure and the second voice messaging of the user;
Vocal print feature identification is carried out to the second voice messaging of user, and matches corresponding voiceprint storehouse;
Based on the voiceprint storehouse, second response message corresponding with the second speech waveform figure is obtained as mesh
Mark response message is replied.
Further, the speech waveform figure includes waveform, frequency and amplitude;
Set the first error range and the second error range;
Under the conditions of same waveform, by the frequency in the first error range simultaneously and the amplitude in the second error range
Speech waveform figure be set as same speech waveform figure.
Second aspect, the embodiment of the present invention additionally provide a kind of robot interactive system, including:
First speech waveform figure acquisition module, for obtaining the first speech waveform figure of user;
First replies module, should as target for the first response message according to corresponding to the first speech waveform figure
Information is answered to be replied.
Further, the first speech waveform figure acquisition module is specifically used for:
Receive the first voice messaging of the user;
First voice messaging is converted into the first speech waveform data, and by the first speech waveform data
Be converted to the first speech waveform figure.
Further, in addition to:
Threshold setting module, for before the first speech waveform figure of the acquisition user, setting preset times threshold value;
When the number for obtaining the first speech waveform figure reaches the preset times threshold value, first response message and institute are established
State the matching relationship of the first speech waveform figure.
Further, in addition to:
Second replies module, for according to vocal print feature, by the vocal print feature identical voice messaging and speech waveform
Figure is stored to same voiceprint storehouse;Obtain the second speech waveform figure and the second voice messaging of the user;To the of user
Two voice messagings carry out vocal print feature identification, and match corresponding voiceprint storehouse;Based on the voiceprint storehouse, obtain
Second response message corresponding with the second speech waveform figure is replied as target response information.
Further, the speech waveform figure includes waveform, frequency and amplitude;
Set the first error range and the second error range;
Under the conditions of same waveform, by the frequency in the first error range simultaneously and the amplitude in the second error range
Speech waveform figure be set as same speech waveform figure.
The embodiments of the invention provide a kind of robot interactive method and system, by the first speech waveform for obtaining user
Figure;The first response message according to corresponding to the first speech waveform figure is replied as target response information, is solved
The problem of robot answer speed is excessively slow in the prior art, the sound characteristic of user is familiar with by image training robot to improve machine
The answer speed of device people.
Brief description of the drawings
Fig. 1 is a kind of flow chart of robot interactive method in the embodiment of the present invention one;
Fig. 2 is a kind of structural representation of robot interactive system in the embodiment of the present invention two.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart for robot interactive method that the embodiment of the present invention one provides, and the present embodiment is applicable to
The situation of various robot interactives, this method can be performed by robot interactive system provided in an embodiment of the present invention.Such as Fig. 1
It is shown, specifically include:
S110, the first speech waveform figure for obtaining user.
Because the memory capacity of robot is limited, and the number of data storage have impact on the speed of service of robot, therefore,
Robot is connected with robot server, the data storage of Large Copacity and complex calculation are transferred to robot server
End, is handled by server, while robot original running status is not influenceed, can realize the storage of more data with
Processing.
First speech waveform figure is to react individual subscriber tone color and the oscillogram of voice messaging.Personal tone color on user
Feature, it by comparing the additional small vibration of waveform, on the tone height of user, can compare the density degree of waveform,
And on the loudness size of user, the amplitude of waveform can be compared.Therefore, every voice messaging that robot obtains user has
Its specific speech waveform figure, and the speech waveform figure of the every voice messaging obtained is different.By obtain user first
Speech waveform figure, it can determine the oscillogram feature of user's current speech.
Exemplary, the first speech waveform figure for obtaining user includes:Receive the first voice messaging of the user;
First voice messaging is converted into the first speech waveform data, and the first speech waveform data are converted into institute
State the first speech waveform figure.
Wherein, the first voice messaging is that robot carries out exchanging caused interactive information, the first speech waveform with user
Data are the data of the first voice messaging sound characteristic of record, can be obtained instead by carrying out processing to the first speech waveform data
Answer the first speech waveform figure of the first voice messaging feature.
Specifically, when the first voice messaging can be robot and user's face-to-face exchange, the user speech information of reception,
Can also be the user speech information that robot is received with user by communication apparatus such as mobile phones.Robot is by the first of reception
Voice messaging is uploaded to robot server, and upload mode can be uploaded by bluetooth or wireless network.Robot takes
After business device receives the first voice messaging, text conversion will not be carried out to the first voice messaging, but pass through sound processing techniques
First voice messaging is converted into the first speech waveform data, then the first speech waveform data are converted into oscillogram.
It should be noted that the first voice messaging, which is converted to the first speech waveform data, passes through the first voice that will receive
Information is converted to data signal, then converts digital signals into waveform electronic signal by digital analog converter, will be on
All waveform electronic signals of one voice messaging are handled to form the first speech waveform figure.
S120, the first response message according to corresponding to the first speech waveform figure are answered as target response information
It is multiple.
Wherein, the first response message is that can be directed to the information that the first voice messaging received make response, Ke Yiwei
Text message, or voice messaging.It is text message by the first response message when the first response message is text message
Afterwards, then using the first response message as target response information replied.
It should be noted that robot server establishes speech waveform database for the response mode of the present embodiment.Its
In, a large amount of speech waveform figures are not only stored in speech waveform database, also stored for of speech waveform figure and response message
With relation.After server gets the first response waveform figure of user, will be matched in speech waveform database with this first
The first response message that response waveform figure matches, and carry out response using the first response message as target reply message.
Wherein, the data preserved in speech waveform database can be robot server obtain on video display information,
Obtained such as the dialog information processing in TV play, can also be according in daily life, the dialogue between robot and user is believed
Breath and the dialog information between user and other users are handled and obtained.
For example, when if the first speech waveform figure is two-dimentional sinusoidal waveform figure, same person is obtained due to tone difference of speaking
The oscillogram taken also will not be the same, such as following formula Fs1And F (t)2(t) used for the user that robot server is got respectively
The formula of " coming to play with me " that the happy tone and the tone of indignation are said corresponding speech waveform figure is:
F1(t)=sin (kt)+A1sin (2kt)+A2sin (3kt)+
F2(t)=sin (kt)+B1sin (2kt)+B2sin (3kt)+
Above-mentioned formula F1And F (t)2(t) difference of the reaction in two-dimentional sinusoidal waveform figure can be the size of amplitude.Therefore,
The different tone that robot can identify user by recording speech waveform figure to be used for, enter so as to more match suitable voice messaging
Row response.
The embodiments of the invention provide a kind of robot interactive method, by the first speech waveform figure for obtaining user;Root
Replied according to the first response message corresponding to the first speech waveform figure as target response information, solve existing skill
The problem of Shu Zhong robots answer speed is excessively slow, improve the answer speed of robot.
Exemplary, before the first speech waveform figure of the acquisition user, in addition to:Set preset times threshold value;
When the number for obtaining the first speech waveform figure reaches the preset times threshold value, first response message and institute are established
State the matching relationship of the first speech waveform figure.
Wherein, preset times threshold value, which is used to determine whether to establish the first response message with the first speech waveform figure, matches pass
The basis for estimation of system.Preset times threshold value can be set according to the default parameters of robot or according to user spy
Sign, the dynamic value set by user.For example, when preset times threshold value be 10 times when, only robot obtain the first language
When the number of sound oscillogram reaches 10, the matching relationship of the first response message and the first speech waveform figure is just established.
The method of setting preset times threshold value avoids rarely needed interactive information and takes depositing for speech waveform database
Store up space the problem of, contribute to save speech waveform database memory space, so as to be advantageous to the Rapid matching of robot with
Response.
Exemplary, the method that the present embodiment provides also includes:According to vocal print feature, by the vocal print feature identical language
Message ceases to be stored to same voiceprint storehouse with speech waveform figure;Obtain the second speech waveform figure and the second voice of the user
Information;Vocal print feature identification is carried out to the second voice messaging of user, and matches corresponding voiceprint storehouse;Based on described
Voiceprint storehouse, obtain second response message corresponding with the second speech waveform figure and answered as target response information
It is multiple.
In real life, language when everyone speaks, the characteristics of having oneself., can be only between the people being very familiar with
Listening and mutually it is discernable, here it is the variant characteristic of everyone vocal print feature.Wherein, vocal print is electricity consumption acoustic instrument
The sound wave spectrum of the carrying verbal information of display.Vocal print not only has specificity, and has the characteristics of relative stability.Adult with
Afterwards, the sound of people can keep for a long time stablize relatively it is constant.No matter talker is deliberately to imitate other people sound and the tone, or whisper in sb.'s ear
Softly talk, even if imitating remarkably true to life, its vocal print but differs all the time.Therefore, can be by vocal print feature, to user's
Speech waveform database carries out personalized storage, establishes the voiceprint storehouse of user.
Wherein, voiceprint storehouse is based on the basis of speech waveform database, to speech waveform database root according to vocal print
Feature is further classified so that robot can carry out separate storage to the sound of different user.If for example, receive
User A voice messaging, then response message is matched in user A voiceprint storehouse, if receiving user B voice messaging,
Then response message is matched in user B voiceprint storehouse.
Specifically, after robot server receives the voice messaging of user second, can be to the second voice messaging carry out sound
The identification of line feature, according to vocal print feature, vocal print feature identical voice messaging and speech waveform figure are stored to same vocal print
Information bank.When obtaining the second speech waveform figure and the second voice messaging of user, first the second voice messaging of user is carried out
Vocal print feature identifies, matches corresponding voiceprint storehouse, then based on the voiceprint storehouse, obtain and the second speech waveform
Scheme the second corresponding response message to be replied as target response information.
It should be noted that vocal print feature identical voice messaging and speech waveform figure are stored to same voiceprint
Storehouse, the same voiceprint storehouse also need to consider the vocal print feature that be under any scene state of user, for example, flu, cough with
And also stored in the lump to the same vocal print for belonging to the user with speech waveform figure containing the voice messaging when material object in mouth
Information bank.
It should be noted that the extraction of vocal print feature can utilize the method for mathematical modeling to establish vocal print automatic identification mould
Type, wherein vocal print automatic identification model can contemplate acoustic feature (cepstrum), lexical characteristics, prosodic features and languages, side
Accent information etc. of making peace various features factor.
Exemplary, the speech waveform figure includes waveform, frequency and amplitude;Set the first error range and the second error
Scope;Under the conditions of same waveform, by the frequency in the first error range simultaneously and the amplitude in the second error range
Speech waveform figure is set as same speech waveform figure.
Wherein, the waveform in everyone speech waveform figure is changeless.The user obtained due to robot server
Speech waveform figure under varying environment is possible to can be different, therefore allow the frequency in speech waveform figure to exist with amplitude and miss
Poor scope, that is, frequency is allowed the first error range to be present, amplitude has the second error range, will be in the first error range simultaneously
Interior frequency and the speech waveform figure of the amplitude in the second error range are set as same speech waveform figure, contribute to the service of saving
The memory space of device, improve the speed of service.
The present embodiment is categorized as different vocal print letters to speech waveform database by being extracted to the vocal print feature of user
Storehouse is ceased, after the vocal print feature by identifying user, response message can be matched in the voiceprint storehouse of the user, due to reducing
The matching operation amount of database, therefore improve the answer speed of robot.
Embodiment two
Fig. 2 is a kind of structural representation for robot interactive system that the embodiment of the present invention two provides, and the present embodiment can fit
Situation for the interaction of various robots.As shown in Fig. 2 specifically include:First speech waveform figure acquisition module 21 and first
Reply module 22.
First speech waveform figure acquisition module 21, for obtaining the first speech waveform figure of user;
First replies module 22, for the first response message according to corresponding to the first speech waveform figure as target
Response message is replied.
On the basis of above-described embodiment, the first speech waveform figure acquisition module 21 is specifically used for:Receive the user
The first voice messaging;First voice messaging is converted into the first speech waveform data, and by first voice
Wave data is converted to the first speech waveform figure.
On the basis of above-described embodiment, in addition to:Threshold setting module 23.
Threshold setting module 23, for before the first speech waveform figure of the acquisition user, setting preset times threshold
Value;When the number for obtaining the first speech waveform figure reaches the preset times threshold value, first response message is established
With the matching relationship of the first speech waveform figure.
On the basis of above-described embodiment, in addition to:Second replies module 24.
Second replies module 24, for according to vocal print feature, by the vocal print feature identical voice messaging and speech wave
Shape figure is stored to same voiceprint storehouse;Obtain the second speech waveform figure and the second voice messaging of the user;To user's
Second voice messaging carries out vocal print feature identification, and matches corresponding voiceprint storehouse;Based on the voiceprint storehouse, obtain
Second response message corresponding with the second speech waveform figure is taken to be replied as target response information.
On the basis of above-described embodiment, the speech waveform figure includes waveform, frequency and amplitude;Set the first error range
With the second error range;Under the conditions of same waveform, by the frequency in the first error range simultaneously and the second error range
The speech waveform figure of interior amplitude is set as same speech waveform figure.
The embodiments of the invention provide a kind of robot interactive system, by the first speech waveform figure for obtaining user;Root
Replied according to the first response message corresponding to the first speech waveform figure as target response information, solve existing skill
The problem of Shu Zhong robots answer speed is excessively slow, improve the answer speed of robot.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
- A kind of 1. robot interactive method, it is characterised in that including:Obtain the first speech waveform figure of user;The first response message according to corresponding to the first speech waveform figure is replied as target response information.
- 2. according to the method for claim 1, it is characterised in that the first speech waveform figure for obtaining user includes:Receive the first voice messaging of the user;First voice messaging is converted into the first speech waveform data, and by the first speech waveform data conversion For the first speech waveform figure.
- 3. according to the method for claim 1, it is characterised in that before the first speech waveform figure of the acquisition user, Also include:Set preset times threshold value;When the number for obtaining the first speech waveform figure reaches the preset times threshold value, first response message is established With the matching relationship of the first speech waveform figure.
- 4. according to the method for claim 1, it is characterised in that also include:According to vocal print feature, the vocal print feature identical voice messaging and speech waveform figure are stored to same voiceprint Storehouse;Obtain the second speech waveform figure and the second voice messaging of the user;Vocal print feature identification is carried out to the second voice messaging of user, and matches corresponding voiceprint storehouse;Based on the voiceprint storehouse, obtaining second response message corresponding with the second speech waveform figure should as target Information is answered to be replied.
- 5. according to the method for claim 4, it is characterised in that the speech waveform figure includes waveform, frequency and amplitude;Set the first error range and the second error range;Under the conditions of same waveform, by the frequency in the first error range simultaneously and the language of the amplitude in the second error range Sound oscillogram is set as same speech waveform figure.
- A kind of 6. robot interactive system, it is characterised in that including:First speech waveform figure acquisition module, for obtaining the first speech waveform figure of user;First replies module, believes for the first response message according to corresponding to the first speech waveform figure as target response Breath is replied.
- 7. system according to claim 6, it is characterised in that the first speech waveform figure acquisition module is specifically used for:Receive the first voice messaging of the user;First voice messaging is converted into the first speech waveform data, and by the first speech waveform data conversion For the first speech waveform figure.
- 8. system according to claim 6, it is characterised in that also include:Threshold setting module, for before the first speech waveform figure of the acquisition user, setting preset times threshold value;In obtaining When taking the number of the first speech waveform figure to reach the preset times threshold value, first response message and described the are established The matching relationship of one speech waveform figure.
- 9. system according to claim 6, it is characterised in that also include:Second replies module, for according to vocal print feature, the vocal print feature identical voice messaging to be deposited with speech waveform figure Store up to same voiceprint storehouse;Obtain the second speech waveform figure and the second voice messaging of the user;To the second language of user Message breath carries out vocal print feature identification, and matches corresponding voiceprint storehouse;Based on the voiceprint storehouse, acquisition and institute The second corresponding response message of the second speech waveform figure is stated to be replied as target response information.
- 10. system according to claim 9, it is characterised in that the speech waveform figure includes waveform, frequency and amplitude;Set the first error range and the second error range;Under the conditions of same waveform, by the frequency in the first error range simultaneously and the language of the amplitude in the second error range Sound oscillogram is set as same speech waveform figure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710616317.1A CN107393538A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710616317.1A CN107393538A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107393538A true CN107393538A (en) | 2017-11-24 |
Family
ID=60341121
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710616317.1A Pending CN107393538A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107393538A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111933138A (en) * | 2020-08-20 | 2020-11-13 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
WO2023109415A1 (en) * | 2021-12-16 | 2023-06-22 | 广州城市理工学院 | Holographic interactive system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1760973A (en) * | 2004-10-12 | 2006-04-19 | 上海海事大学 | Method of speech recognition based on qualitative mapping |
CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技(深圳)有限公司 | Chinese auto-answer method and system |
KR20140073889A (en) * | 2012-12-07 | 2014-06-17 | 현대자동차주식회사 | An call word buffering and filling interface for interactive voice recognition |
CN106547813A (en) * | 2016-09-22 | 2017-03-29 | 苏州小璐机器人有限公司 | A kind of method of hoisting machine people voice response ability |
CN106653016A (en) * | 2016-10-28 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and intelligent interaction device |
CN206224438U (en) * | 2016-06-14 | 2017-06-06 | 深圳市三诺声智联股份有限公司 | A kind of intelligent electronic pet voice interactive system |
-
2017
- 2017-07-26 CN CN201710616317.1A patent/CN107393538A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1760973A (en) * | 2004-10-12 | 2006-04-19 | 上海海事大学 | Method of speech recognition based on qualitative mapping |
CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技(深圳)有限公司 | Chinese auto-answer method and system |
CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
KR20140073889A (en) * | 2012-12-07 | 2014-06-17 | 현대자동차주식회사 | An call word buffering and filling interface for interactive voice recognition |
CN206224438U (en) * | 2016-06-14 | 2017-06-06 | 深圳市三诺声智联股份有限公司 | A kind of intelligent electronic pet voice interactive system |
CN106547813A (en) * | 2016-09-22 | 2017-03-29 | 苏州小璐机器人有限公司 | A kind of method of hoisting machine people voice response ability |
CN106653016A (en) * | 2016-10-28 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and intelligent interaction device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111933138A (en) * | 2020-08-20 | 2020-11-13 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
CN111933138B (en) * | 2020-08-20 | 2022-10-21 | Oppo(重庆)智能科技有限公司 | Voice control method, device, terminal and storage medium |
WO2023109415A1 (en) * | 2021-12-16 | 2023-06-22 | 广州城市理工学院 | Holographic interactive system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10438586B2 (en) | Voice dialog device and voice dialog method | |
CN109767765A (en) | Talk about art matching process and device, storage medium, computer equipment | |
CN101981614B (en) | Medium processing server device and medium processing method | |
EP3611724A1 (en) | Voice response method and device, and smart device | |
CN107992195A (en) | A kind of processing method of the content of courses, device, server and storage medium | |
CN110021308A (en) | Voice mood recognition methods, device, computer equipment and storage medium | |
CN103546503B (en) | Voice-based cloud social intercourse system, method and cloud analysis server | |
CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
CN110600014B (en) | Model training method and device, storage medium and electronic equipment | |
CN106294854A (en) | A kind of man-machine interaction method for intelligent robot and device | |
US20130253932A1 (en) | Conversation supporting device, conversation supporting method and conversation supporting program | |
CN110176237A (en) | A kind of audio recognition method and device | |
CN109101663A (en) | A kind of robot conversational system Internet-based | |
CN110933225B (en) | Call information acquisition method and device, storage medium and electronic equipment | |
CN107733722A (en) | Method and apparatus for configuring voice service | |
CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
GB2516942A (en) | Text to Speech Conversion | |
CN108470188A (en) | Exchange method based on image analysis and electronic equipment | |
CN108305618A (en) | Voice obtains and searching method, smart pen, search terminal and storage medium | |
CN108122555A (en) | The means of communication, speech recognition apparatus and terminal device | |
CN110570847A (en) | Man-machine interaction system and method for multi-person scene | |
CN115982400A (en) | Multi-mode-based emotion image generation method and server | |
CN107393538A (en) | Robot interactive method and system | |
CN108364638A (en) | A kind of voice data processing method, device, electronic equipment and storage medium | |
CN108766416A (en) | Audio recognition method and Related product |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171124 |