CN105810200A - Man-machine dialogue apparatus and method based on voiceprint identification - Google Patents
Man-machine dialogue apparatus and method based on voiceprint identification Download PDFInfo
- Publication number
- CN105810200A CN105810200A CN201610078214.XA CN201610078214A CN105810200A CN 105810200 A CN105810200 A CN 105810200A CN 201610078214 A CN201610078214 A CN 201610078214A CN 105810200 A CN105810200 A CN 105810200A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- module
- identification
- application
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000001755 vocal effect Effects 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000001815 facial effect Effects 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 4
- 210000001215 vagina Anatomy 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 9
- 230000003993 interaction Effects 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 4
- 230000036651 mood Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 240000007711 Peperomia pellucida Species 0.000 description 1
- 235000012364 Peperomia pellucida Nutrition 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a man-machine dialogue apparatus and method based on voiceprint identification, for carrying out a user-friendly dialogue with a user. A background server of the apparatus at least comprises a user ID database, a voiceprint feature database and a voice identification database; an information receiving module receives a voice information instruction given by the user and transmits the instruction to an identity identification module; the identity identification module at least comprises a voiceprint identification submodule, and the voiceprint identification submodule is connected with the voiceprint feature database of the background server, for determining user ID according to data stored by the voiceprint feature database and generating user identity feature information; a voice identification module is connected with the voice identification database of the background server, for identifying voice information input b y the user and transmitting the voice information to a control management module; and the control management module, according to the received identified user identity feature information and the voice information identified by the voice identification module, generates a control instruction which is transmitted to an information sending module and is executed by an execution module. According to the invention, identities of speakers in the dialogue are identified by use of a voiceprint identification mode, and the dialogue is carried out in a customized mode according to the identities.
Description
Technical field
The present invention relates to interactive field, particularly relate to a kind of human computer conversation based on Application on Voiceprint Recognition dress
Put and method.
Background technology
Along with the fast development of science and technology, especially extensive in every field of robot and human-computer interaction technology
Application, requires more and more higher for interactive technology.And in human computer conversation, personalized as complete
A kind of means of kind man-machine harmony, also receive the highest concern.In past and existing man-machine interaction
In, it is to consider that people deacclimatizes machine more, this has resulted in the development limitation of interactive, because of
And it should be to allow machine to adapt to people that those skilled in the art have become increasingly aware of development trend.In the art
Briefly being divided into two kinds of understanding modes for " allowing machine adapt to people ", a kind of understanding is that " people " is considered as one
Entirety, and put aside personal characteristics's impact on man-machine interaction；Another kind of then that consideration is different further people
The concrete property impact on man-machine interaction, the personalization under this understanding is referred to as " personalized interaction ", and " individual
Propertyization is coordinated " following man-machine society is of universal significance, it is a core of following man-machine harmony common technology
Part.
In existing robot conversational system, robot for talk with people identification, relatively also in
One blank phase, and fixing account, face recognition or voice that the identification generally used typically uses
Identify, and in actual application scenarios, use fixing account number to know and be not suitable for the dynamic of complexity
State environment, is only suitable only for the simple environment of man-to-man communication；And use the mode of face recognition to need machine
Face-to-face with user, or the camera head of at least machine can photograph the face spoken, and scene
Ask comparison strict；Comparatively speaking, under session context, it is possible to be easy to obtain the voice of interlocutor, the most just
There is the information source differentiating identity, so, utilize speech recognition to have more its broad applicability, but mesh
The speech content being in recognition of speech signals of the application more number of front speech recognition, it is not intended that speak
Whom people is, it only emphasizes general character.
In view of the situation of prior art, it is badly in need of a kind of interactive system in view of hommization existing to solve
Identity recognizing technology in technology is strict to scene requirement and can not be advantageously used the technology of dynamic environment and lacks
Fall into.
Summary of the invention
The present invention seeks to propose a kind of human computer conversation's devices and methods therefor based on Application on Voiceprint Recognition.
The present invention solves technical problem and adopts the following technical scheme that a kind of human computer conversation based on Application on Voiceprint Recognition fills
Putting, carry out hommization dialogue with user, described human computer conversation's device at least includes background server, information
Receiver module, identification module, sound identification module, control management module and information sending module,
Wherein: described background server at least includes that ID data base, vocal print property data base and voice are known
Other data base；Described information receiving module, the voice messaging that reception user sends instructs and is transferred to described
Identification module；Described identification module at least includes Application on Voiceprint Recognition submodule, and described vocal print
Identify that submodule is connected with the vocal print property data base of described background server, according to described vocal print characteristic number
Determine ID according to the data of library storage and generate user identity characteristic information；Described sound identification module with
The speech recognition database of described background server connects, and identifies the voice messaging of user's input and is passed
Deliver to described control management module；Described controls the management module user identity according to the identification received
The voice messaging of characteristic information and described sound identification module identification generates control instruction and is transferred to information transmission
Module；The control instruction received is sent holding to described human computer conversation's device by described information sending module
Row module performs.
Optionally, described Application on Voiceprint Recognition submodule also includes condition adjudgement submodule, becomes in subscriber authentication
During merit, the feature contrast judgement User Status in the vocal print feature according to input with ID data base is raw
Become user identity characteristic information, be sent to described control management module；When subscriber authentication failure,
Directly generate error message to described control management module.
Optionally, described information receiving module also includes that ID receives submodule, is used for receiving user defeated
The account information entered transmission are to the most described identification module；
Described identification module also includes ID identification submodule, receives ID and receives submodule
The account information of the user's input transmitted.
Optionally, described information receiving module also includes that user's facial information receives submodule, is used for gathering
Receive the facial information of user and send to described identification module；
Described identification module also includes face recognition submodule, receives described user's facial information and receives
The facial information for identifying ID that submodule transmits.
Optionally, described sound identification module at least includes text conversion units and grammatical and semantic unit,
The voice messaging of user is converted into text message and sends to described grammer language by described text conversion units
Justice unit, described grammatical and semantic unit divides according to the information of the speech recognition database of described background server
Analysis text message, and the information after analyzing transmits as described control management module.
Optionally, described speech recognition database at least include the training in advance of a kind of language corpus,
Language library and dictionary.
A kind of interactive method based on Application on Voiceprint Recognition, carries out hommization dialogue with user, at least include with
Lower step:
The voice messaging instruction that A, reception user send；
B, to received voice messaging instruction carry out Application on Voiceprint Recognition, determine user identity characteristic information；
C, the voice messaging instruction received is carried out speech recognition, analyze user instruction；
D, generate control instruction according to the voice messaging of user identity characteristic information and speech recognition；
E, perform described user voice messaging instruction.
Optionally, in described step B, described user identity characteristic information includes ID information and use
Family state characteristic information, when subscriber authentication success, performs step D；In subscriber authentication failure
Time, execution step F: generation error information.
Optionally, also include that receiving user inputs accounts information and determine step A1 of ID information.
Optionally, also include gathering user's face information and determining step A2 of ID information.
There is advantages that
1, the present invention have employed sound groove recognition technology in e in identification and carries out identification, can be according to user
Speech waveform in the voice messaging of input reflects the speech parameter of speak human physiology and behavior characteristics, according to number
Information according to storehouse identifies the technology of speaker's identity automatically.
2, the present invention determines User Status based on sound stricture of vagina identification, the action output of the personalized robot coordinated.
3, the present invention is accurately judged to the difference of speaker by vocal print and sorts out, according to the data prestored
Comparison, matching degree is anticipated reaches more than 90%, as emotional exchange class robot, it is already possible in a lot of degree
Meet the requirement of anticipation.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of human computer conversation's device based on Application on Voiceprint Recognition of the present invention；
Fig. 2 is interactive method flow diagram based on Application on Voiceprint Recognition of the present invention.
Detailed description of the invention
Below in conjunction with embodiment and accompanying drawing, technical scheme is further elaborated.The present invention provides one
Plant human computer conversation's device based on Application on Voiceprint Recognition, hommization dialogue can be carried out with user, with reference to shown in Fig. 1
Structured flowchart, at least includes background server at human computer conversation's device of the present invention, information receiving module,
Identification module, sound identification module, control management module and information sending module, wherein: described
Background server at least include ID data base, vocal print property data base and speech recognition database；
Described information receiving module, the voice messaging that reception user sends instructs and is transferred to described identification
Module；Described identification module at least includes Application on Voiceprint Recognition submodule, and described Application on Voiceprint Recognition submodule
It is connected with the vocal print property data base of described background server, according to described vocal print characteristic library storage
Data determine ID and generate user identity characteristic information；Described sound identification module and described backstage
The speech recognition database of server connects, and identifies the voice messaging of user's input and is sent to described
Control management module；Described control management module according to the user identity characteristic information of the identification received with
And the voice messaging of described sound identification module identification generates control instruction information and is transferred to information sending module；
The control instruction received is sent the execution module to described human computer conversation's device by described information sending module
Perform.In the present invention, described Application on Voiceprint Recognition submodule also includes condition adjudgement submodule, at user identity
Feature contrast judgement user when being proved to be successful, in the vocal print feature according to input with ID data base
State generates user identity characteristic information, is sent to described control management module；Lose in subscriber authentication
When losing, directly generate error message to described control management module.
The Application on Voiceprint Recognition used in technical scheme belongs to the one of biological identification technology, is a root
According to speech waveform carries out user's identification, and the different tone tone frequency of same user all can corresponding user not
Same selection, so it is humanized to use vocal print technology to carry out human computer conversation.Sound groove recognition technology in e mainly wraps
Including two parts, i.e. feature detection and pattern match, wherein the task of feature detection is to choose unique performance to speak
Effective and the reliable and stable vocal print feature of people's identity, and the task of pattern match is to when training and identify
Feature mode does similarity coupling, and it with existing speech recognition difference is the most always: Application on Voiceprint Recognition utilization
Be the speaker information in voice signal, and do not consider in voice words the meaning, it emphasizes speaker's
Individual character, and the purpose of speech recognition is to identify the speech content in voice signal, it is not intended that speaker is
Who, it emphasizes general character.It is to say, the data in heretofore described vocal print property data base, permissible
Including realizing user's voice print database under the multiple environment tone and state of training, and in the process of use
In can also retraining storage.Therefore in application process, it is considered that the characteristic of hommization, and not merely
Consider speech content.And about feature detection and the specific algorithm of pattern match and mode, all can adopt
Realize by existing mode.
In the present invention, described information receiving module can also include that ID receives submodule, is used for connecing
Receive the account information of user's input and send to described identification module；Described identification module pair
Should also include ID identification submodule, receive ID and receive the account of user's input that submodule transmits
Information, and according to the ID data base in background server by ID identification user.
In the present invention, described information receiving module also can also include that user's facial information receives submodule,
For gathering the facial information receiving user and sending to described identification module；Described identification
Module also includes face recognition submodule, receive described user's facial information receive submodule transmit for knowing
The facial information of other ID, and according to the ID data base in background server by ID identification
User.The ID data base of the background server of the present invention is actual can be made up of three partial informations, including
The ID account information of user's fixed line, voice print database information and the face feature information of user, application
Time and according to practical situation, user carried out checking and identifies, or use three kinds according to safe class simultaneously
Or one or two kinds of therein carries out subscriber authentication.Use these three identification information specifically than
To process, existing technology can be used to realize, no longer repeat at this.It is emphasized that this
The device of invention, during as carried out authentication only with sound groove recognition technology in e, identification module and voice are known
Other module can receive voice messaging simultaneously, carries out processing and sending the information generated to described control simultaneously
Tubulation reason module, and described control management module is when authentication success, the letter generated according to two modules
Breath generates control instruction.
As it is shown in figure 1, sound identification module of the present invention at least includes text conversion units and grammer
Semantic primitive, the voice messaging of user is converted into text message and sends to institute by described text conversion units
The grammatical and semantic unit stated, described grammatical and semantic unit is according to the voice recognition data of described background server
The information analysis text message in storehouse, and the information after analyzing transmits as described control management module.?
When carrying out speech recognition, first complete the speech processes needed for human computer conversation by speech recognition and synthetic technology,
Complete the conversion between audio frequency input/output and corresponding text, then text is carried out syntactic analysis and language
Justice analyze, and can process the current service request of user, environment describe (such as environment has what object with
And Properties of Objects, the individual characteristics of user and characteristic etc.)；Again through semantic analysis, system generates certain
Internal logic expression formula, syntactic analysis can utilize existing syntactic analysis instrument to complete, and semantic analysis passes through
Realization to existing semantic analysis instrument..These information are stored in domain knowledge base, i.e. with reference to shown in Fig. 1,
In the present invention, described speech recognition database at least include the training in advance of a kind of language corpus,
Language library and dictionary, wherein language library, for storing relevant linguistic knowledge, corpus is used for storing
The linguistic information that training obtains, and dictionary is for storing the linguistic information of magnanimity.
In the present invention, described control management module, generating information command when, can call backstage
Movement knowledge storehouse in server and domain knowledge base (not shown), described movement knowledge stock contains
The knowledge relevant with robot control, other background knowledge of the described relevant application of domain knowledge library storage,
And the acquisition of these knowledge has three kinds of approach: first is and/or to be set from user by natural language human computer conversation
Meter person obtains；Second is to obtain (being mainly used in robot motion's knowledge) by experiment statistics, and the 3rd is design
Person's manual coding.Mainly using the first and second approach, motion planning with heuristic search is
Main, miscellaneous part (robot controls and sensor etc.) uses the robotics of standard.In the present invention,
Can directly use Android program design language is treatment mechanism, completes uniformly to plan required reasoning
And computing function.
It is described further below in conjunction with specific embodiment, applies English with existing conventional human computer conversation
As a example by language study, conventional user mode access is usually input ID account and accesses, and machine is to user's body
After part identifies, start speech input information is identified, i.e. carry out text and change grammatical and semantic analysis again,
Again by controlling management module according to the voice content analyzed by background server gathering information from data base, raw
Become voice messaging, owing to information sending module sends, can be that voice dialogue is sent out by speaker in this application
Go out.This human computer conversation is a kind of universal mode, does not goes to consider the human nature feature of this user.Simple employing
Human computer conversation's process that facial recognition carries out identification is identical with above-mentioned situation, repeats no more.And this
Bright described device, mainly uses audio access, i.e. user directly to carry out with device of the present invention right
Words, after assembly of the invention receives this voice messaging, just use the mode of Application on Voiceprint Recognition to identifying user's
Identity, is specially the feature to user's vocal print and is identified, can judge the ID of user after identification, and
Simultaneously according to the information of ID databases storage, (information here includes user's sound under various regimes
Stricture of vagina inputs, and trains the data of generation) judge the state of user, such as the mood of user, condition with
And the information such as local environment, the voice messaging that user is inputted by sound identification module carries out speech recognition, this language
Sound identification process is consistent with foregoing description, and controls to manage module meeting root after receiving the information of speech recognition
Information and vocal print characteristic jointly generate and perform instruction accordingly, and such as in English study, user is rising
Phonetic entry " what is my agenda today in the case of bed is late？" robot is first according to user
Vocal print feature carry out identification, determine user identity, and judge that user is in hurriedly according to the tone of user
Busy state, is then carrying out speech recognition, it is judged that the voice content that user is inputted, the control of robot
Management module can call the agenda of user in background server, and combines the hasty tone of user simultaneously
Output prompting message or temporal information.In learning process, machine can also according to the vocal print feature of user,
Judging the fluency of user, the voice messaging calling respective horizontal in the data base on backstage is handed over user
Stream, improves the learning interest of user the most to a great extent, also functions to good human computer conversation's efficiency, carry
The learning level of high user.
The most again by the embodiment of an entertainment applications, perform the process of task in explanation assembly of the invention,
Such as user's phonetic entry under happy mood: singing a first pleasing to the ear song, assembly of the invention information receives mould
After block receives this voice messaging, the Application on Voiceprint Recognition submodule of identification module carry out Application on Voiceprint Recognition judgement
The identity of user, after being proved to be successful, then by the vocal print feature of condition adjudgement this user of submodule in vocal print feature
In data base, matching judgment user is in buoyant state, and generates user identity characteristic information and be sent to
Described control management module；After described sound identification module receives voice messaging, transferred to text,
By syntactic analysis, semantic understanding, it is decomposed into JSON format text, forms identification information and send to described
Control management module；After described control management module receives this information, differentiated the use obtained by vocal print
Family identity characteristic information and voice recognition information, match the private information storehouse of user, according to user identity
In characteristic information, the information of user's happiness mood is in the conventional library of user, extracts happy mood and commonly uses
Song shuffle one or by shuffle so that interactive system can meet the happiness of user very well
Good tendency so that it is experience sense is greatly improved.
In the present embodiment, also provide for a kind of interactive method based on Application on Voiceprint Recognition, carry out people with user
Propertyization is talked with, and with reference to shown in Fig. 2, at least comprises the following steps:
The voice messaging instruction that A, reception user send；
B, to received voice messaging instruction carry out Application on Voiceprint Recognition, determine user identity characteristic information；
C, the voice messaging instruction received is carried out speech recognition, analyze user instruction；
D, generate control instruction according to the voice messaging of user identity characteristic information and speech recognition；
E, perform described user voice messaging instruction.
In described step B, described user identity characteristic information includes that ID information and User Status are special
Reference ceases, and when subscriber authentication success, performs step D；When subscriber authentication failure, perform
Step F: generation error information.
Method in the present invention also includes that receiving user inputs accounts information and determine the step of ID information.
Method in the present invention also includes gathering user's face information and determining the step of ID information.
The method step of the present invention is corresponding with assembly of the invention, the concrete application of the present embodiment and the present invention
The step of method describe identical, no longer repeat at this.
In sum, the present invention have employed sound groove recognition technology in e in identification and carries out identification, permissible
The speech waveform in voice messaging according to user's input reflects the voice ginseng of speak human physiology and behavior characteristics
Number, automatically identifies the technology of speaker's identity according to the information of data base.And individual character based on sound stricture of vagina identification
Change the action output of the robot coordinated, utilize mode identification interlocutor's identity of Application on Voiceprint Recognition, and according to this
Identity does the dialogue of personalization.
The sequencing of above example only for ease of describing, does not represent the quality of embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, rather than it is limited
System；Although the present invention being described in detail with reference to previous embodiment, those of ordinary skill in the art
It is understood that the technical scheme described in foregoing embodiments still can be modified by it, or to it
Middle part technical characteristic carries out equivalent；And these amendments or replacement, do not make appropriate technical solution
Essence departs from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. human computer conversation's device based on Application on Voiceprint Recognition, carries out hommization dialogue with user, and its feature exists
Background server is at least included in, described human computer conversation's device, information receiving module, identification module,
Sound identification module, controls management module and information sending module, wherein: described background server is extremely
Include ID data base, vocal print property data base and speech recognition database less；Described information receives
Module, the voice messaging that reception user sends instructs and is transferred to described identification module；Described body
Part identification module at least includes Application on Voiceprint Recognition submodule, and described Application on Voiceprint Recognition submodule takes with described backstage
The vocal print property data base of business device connects, and determines ID according to the data of described vocal print characteristic library storage
And generate user identity characteristic information；The voice of described sound identification module and described background server is known
Other data base connects, and identifies the voice messaging of user's input and is sent to described control management module；
The described management module that controls is according to the user identity characteristic information of the identification received and described speech recognition
The voice messaging of module identification generates control instruction and is transferred to information sending module；Described information sending module
The control instruction received is sent the execution module execution to described human computer conversation's device.
Intelligent apparatus based on Application on Voiceprint Recognition the most according to claim 1, it is characterised in that described sound
Stricture of vagina identification submodule also includes condition adjudgement submodule, when subscriber authentication success, for according to input
Vocal print feature and ID data base in feature contrast judgement User Status generate user identity feature letter
Breath, is sent to described control management module；When subscriber authentication failure, directly generate error message
To described control management module.
Intelligent apparatus based on Application on Voiceprint Recognition the most according to claim 1, it is characterised in that described
Information receiving module also includes that ID receives submodule, for receiving the account information of user's input and sending
To described identification module；
Described identification module also includes ID identification submodule, receives ID and receives submodule
The account information of the user's input transmitted.
Intelligent apparatus based on Application on Voiceprint Recognition the most according to claim 1 and 2, it is characterised in that institute
The information receiving module stated also includes that user's facial information receives submodule, for gathering the face receiving user
Information also sends to described identification module；
Described identification module also includes face recognition submodule, receives described user's facial information and receives
The facial information for identifying ID that submodule transmits.
Intelligent apparatus based on Application on Voiceprint Recognition the most according to claim 1, it is characterised in that described
Sound identification module at least includes text conversion units and grammatical and semantic unit, described text conversion units
The voice messaging of user is converted into text message and sends to described grammatical and semantic unit, described grammer
Semantic primitive is according to the information analysis text message of the speech recognition database of described background server, and will divide
Information after analysis transmits as described control management module.
Intelligent apparatus based on Application on Voiceprint Recognition the most according to claim 5, it is characterised in that described
Speech recognition database at least includes the corpus of the training in advance of a kind of language, language library and dictionary.
7. an interactive method based on Application on Voiceprint Recognition, carries out hommization dialogue with user, and its feature exists
In, at least comprise the following steps:
The voice messaging instruction that A, reception user send；
B, to received voice messaging instruction carry out Application on Voiceprint Recognition, determine user identity characteristic information；
C, the voice messaging instruction received is carried out speech recognition, analyze user instruction；
D, generate control instruction according to the voice messaging of user identity characteristic information and speech recognition；
E, perform described user voice messaging instruction.
Interactive method based on Application on Voiceprint Recognition the most according to claim 7, it is characterised in that
In described step B, described user identity characteristic information includes ID information and User Status characteristic information,
When subscriber authentication success, perform step D；When subscriber authentication failure, perform step F: raw
Become error message.
Interactive method based on Application on Voiceprint Recognition the most according to claim 7, it is characterised in that also
Input accounts information including receiving user and determine step A1 of ID information.
Interactive method based on Application on Voiceprint Recognition the most according to claim 7, it is characterised in that
Also include gathering user's face information and determining step A2 of ID information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610078214.XA CN105810200A (en) | 2016-02-04 | 2016-02-04 | Man-machine dialogue apparatus and method based on voiceprint identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610078214.XA CN105810200A (en) | 2016-02-04 | 2016-02-04 | Man-machine dialogue apparatus and method based on voiceprint identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105810200A true CN105810200A (en) | 2016-07-27 |
Family
ID=56466415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610078214.XA Pending CN105810200A (en) | 2016-02-04 | 2016-02-04 | Man-machine dialogue apparatus and method based on voiceprint identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105810200A (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297790A (en) * | 2016-08-22 | 2017-01-04 | 深圳市锐曼智能装备有限公司 | The voiceprint service system of robot and service control method thereof |
| CN106385658A (en) * | 2016-09-08 | 2017-02-08 | 歌尔科技有限公司 | Smart glasses microphone acoustic performance regulation method and smart glasses |
| CN106782537A (en) * | 2016-12-27 | 2017-05-31 | 深圳前海勇艺达机器人有限公司 | The method and system of weather is inquired about in robot |
| CN106782606A (en) * | 2017-01-17 | 2017-05-31 | 山东南工机器人科技有限公司 | For the communication and interaction systems and its method of work of Dao Jiang robots |
| CN107015781A (en) * | 2017-03-28 | 2017-08-04 | 联想(北京)有限公司 | Audio recognition method and system |
| CN107481720A (en) * | 2017-06-30 | 2017-12-15 | 百度在线网络技术（北京）有限公司 | A kind of explicit method for recognizing sound-groove and device |
| CN108170034A (en) * | 2017-12-29 | 2018-06-15 | 上海器魂智能科技有限公司 | Smart machine control method, device, computer equipment and storage medium |
| CN108326875A (en) * | 2017-01-20 | 2018-07-27 | 松下知识产权经营株式会社 | Communication control method and device, long-range presentation robot and storage medium |
| CN108376546A (en) * | 2017-01-31 | 2018-08-07 | 三星电子株式会社 | Pronunciation inputting method and the electronic equipment for supporting this method and system |
| CN108831470A (en) * | 2018-08-24 | 2018-11-16 | 深圳伊讯科技有限公司 | A kind of method and system by voice control BMS |
| CN108986825A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| WO2019007249A1 (en) * | 2017-07-05 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Interaction method, electronic device, and server |
| CN109213877A (en) * | 2017-06-29 | 2019-01-15 | 永丰商业银行股份有限公司 | A kind of financial services system based on intelligent sound human-computer interaction equipment |
| CN109389983A (en) * | 2017-08-10 | 2019-02-26 | 奥迪股份公司 | For handling the method and switching equipment of the recognition result of automatic online-speech recognition device of mobile terminal device |
| CN109545203A (en) * | 2018-12-14 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Audio recognition method, device, equipment and storage medium |
| CN109671438A (en) * | 2019-01-28 | 2019-04-23 | 武汉恩特拉信息技术有限公司 | It is a kind of to provide the device and method of ancillary service using voice |
| CN109756342A (en) * | 2019-01-16 | 2019-05-14 | 中民乡邻投资控股有限公司 | A kind of the account identity identifying method and device of the dialogue formula based on vocal print |
| CN109887503A (en) * | 2019-01-20 | 2019-06-14 | 北京联合大学 | A kind of man-machine interaction method of intellect service robot |
| WO2019137066A1 (en) * | 2018-01-15 | 2019-07-18 | 格力电器（武汉）有限公司 | Electric appliance control method and device |
| CN110164455A (en) * | 2018-02-14 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Device, method and the storage medium of user identity identification |
| CN110428816A (en) * | 2019-02-26 | 2019-11-08 | 北京蓦然认知科技有限公司 | A kind of method and device voice cell bank training and shared |
| CN110570208A (en) * | 2019-07-29 | 2019-12-13 | 阿里巴巴集团控股有限公司 | Complaint preprocessing method and device |
| CN110619870A (en) * | 2018-06-04 | 2019-12-27 | 佛山市顺德区美的电热电器制造有限公司 | Man-machine conversation method and device, household appliance and computer storage medium |
| CN110868427A (en) * | 2019-12-02 | 2020-03-06 | 浙江理工大学 | Remote voice recognition automatic signing device and recognition method thereof |
| CN110880325A (en) * | 2018-09-05 | 2020-03-13 | 华为技术有限公司 | Identity recognition method and equipment |
| CN110910875A (en) * | 2019-11-13 | 2020-03-24 | 秒针信息技术有限公司 | Member management method and system based on voice recognition |
| CN110970033A (en) * | 2019-12-02 | 2020-04-07 | 浙江理工大学 | Voiceprint recognition automatic signing device and recognition method thereof |
| WO2020077841A1 (en) * | 2018-10-18 | 2020-04-23 | 平安科技（深圳）有限公司 | Voiceprint recognition-based customer service method, device, computer device, and storage medium |
| WO2020087336A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳市大疆创新科技有限公司 | Control method and control device for mobile platform |
| WO2020114384A1 (en) * | 2018-12-06 | 2020-06-11 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| CN111292734A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| CN111429920A (en) * | 2020-03-30 | 2020-07-17 | 北京奇艺世纪科技有限公司 | User distinguishing method, user behavior library determining method, device and equipment |
| CN111462754A (en) * | 2020-04-16 | 2020-07-28 | 深圳航天科创实业有限公司 | Method for establishing dispatching control voice recognition model of power system |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN112069484A (en) * | 2020-11-10 | 2020-12-11 | 中国科学院自动化研究所 | Multi-mode interactive information acquisition method and system |
| CN112599136A (en) * | 2020-12-15 | 2021-04-02 | 江苏惠通集团有限责任公司 | Voice recognition method and device based on voiceprint recognition, storage medium and terminal |
| CN113555010A (en) * | 2021-07-16 | 2021-10-26 | 广州三星通信技术研究有限公司 | Voice processing method and voice processing device |
| CN114339342A (en) * | 2021-12-23 | 2022-04-12 | 歌尔科技有限公司 | Remote controller control method, remote controller, control device and medium |
| CN114422154A (en) * | 2022-03-30 | 2022-04-29 | 深圳市永达电子信息股份有限公司 | Digital certificate management method and device based on voice recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202003365U (en) * | 2010-12-31 | 2011-10-05 | 深圳市丰泰瑞达实业有限公司 | Authentication device based on system on programmable chip (SOPC) |
| CN102496365A (en) * | 2011-11-30 | 2012-06-13 | 上海博泰悦臻电子设备制造有限公司 | User verification method and device |
| CN103219007A (en) * | 2013-03-27 | 2013-07-24 | 谢东来 | Voice recognition method and voice recognition device |
| CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
| CN104778946A (en) * | 2014-01-10 | 2015-07-15 | 中国电信股份有限公司 | Voice control method and system |
| CN105206269A (en) * | 2015-08-14 | 2015-12-30 | 百度在线网络技术（北京）有限公司 | Voice processing method and device |
-
2016
- 2016-02-04 CN CN201610078214.XA patent/CN105810200A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202003365U (en) * | 2010-12-31 | 2011-10-05 | 深圳市丰泰瑞达实业有限公司 | Authentication device based on system on programmable chip (SOPC) |
| CN102496365A (en) * | 2011-11-30 | 2012-06-13 | 上海博泰悦臻电子设备制造有限公司 | User verification method and device |
| CN103219007A (en) * | 2013-03-27 | 2013-07-24 | 谢东来 | Voice recognition method and voice recognition device |
| CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
| CN104778946A (en) * | 2014-01-10 | 2015-07-15 | 中国电信股份有限公司 | Voice control method and system |
| CN105206269A (en) * | 2015-08-14 | 2015-12-30 | 百度在线网络技术（北京）有限公司 | Voice processing method and device |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297790A (en) * | 2016-08-22 | 2017-01-04 | 深圳市锐曼智能装备有限公司 | The voiceprint service system of robot and service control method thereof |
| CN106385658A (en) * | 2016-09-08 | 2017-02-08 | 歌尔科技有限公司 | Smart glasses microphone acoustic performance regulation method and smart glasses |
| CN106385658B (en) * | 2016-09-08 | 2019-05-31 | 歌尔科技有限公司 | The microphone acoustic property regulation method and intelligent glasses of intelligent glasses |
| CN106782537A (en) * | 2016-12-27 | 2017-05-31 | 深圳前海勇艺达机器人有限公司 | The method and system of weather is inquired about in robot |
| CN106782606A (en) * | 2017-01-17 | 2017-05-31 | 山东南工机器人科技有限公司 | For the communication and interaction systems and its method of work of Dao Jiang robots |
| CN108326875A (en) * | 2017-01-20 | 2018-07-27 | 松下知识产权经营株式会社 | Communication control method and device, long-range presentation robot and storage medium |
| CN108376546A (en) * | 2017-01-31 | 2018-08-07 | 三星电子株式会社 | Pronunciation inputting method and the electronic equipment for supporting this method and system |
| CN108376546B (en) * | 2017-01-31 | 2023-06-27 | 三星电子株式会社 | Voice input method, and electronic device and system for supporting the same |
| CN107015781A (en) * | 2017-03-28 | 2017-08-04 | 联想(北京)有限公司 | Audio recognition method and system |
| CN109213877A (en) * | 2017-06-29 | 2019-01-15 | 永丰商业银行股份有限公司 | A kind of financial services system based on intelligent sound human-computer interaction equipment |
| CN107481720B (en) * | 2017-06-30 | 2021-03-19 | 百度在线网络技术（北京）有限公司 | Explicit voiceprint recognition method and device |
| CN107481720A (en) * | 2017-06-30 | 2017-12-15 | 百度在线网络技术（北京）有限公司 | A kind of explicit method for recognizing sound-groove and device |
| WO2019007249A1 (en) * | 2017-07-05 | 2019-01-10 | 阿里巴巴集团控股有限公司 | Interaction method, electronic device, and server |
| CN109215643A (en) * | 2017-07-05 | 2019-01-15 | 阿里巴巴集团控股有限公司 | A kind of exchange method, electronic equipment and server |
| US11238870B2 (en) | 2017-07-05 | 2022-02-01 | Alibaba Group Holding Limited | Interaction method, electronic device, and server |
| CN109215643B (en) * | 2017-07-05 | 2023-10-24 | 阿里巴巴集团控股有限公司 | Interaction method, electronic equipment and server |
| CN109389983A (en) * | 2017-08-10 | 2019-02-26 | 奥迪股份公司 | For handling the method and switching equipment of the recognition result of automatic online-speech recognition device of mobile terminal device |
| CN109389983B (en) * | 2017-08-10 | 2023-07-07 | 奥迪股份公司 | Method for processing recognition results of an automatic online voice recognizer of a mobile terminal and switching device |
| CN108170034A (en) * | 2017-12-29 | 2018-06-15 | 上海器魂智能科技有限公司 | Smart machine control method, device, computer equipment and storage medium |
| WO2019137066A1 (en) * | 2018-01-15 | 2019-07-18 | 格力电器（武汉）有限公司 | Electric appliance control method and device |
| CN110164455A (en) * | 2018-02-14 | 2019-08-23 | 阿里巴巴集团控股有限公司 | Device, method and the storage medium of user identity identification |
| CN110619870A (en) * | 2018-06-04 | 2019-12-27 | 佛山市顺德区美的电热电器制造有限公司 | Man-machine conversation method and device, household appliance and computer storage medium |
| CN110619870B (en) * | 2018-06-04 | 2022-05-06 | 佛山市顺德区美的电热电器制造有限公司 | Man-machine conversation method and device, household appliance and computer storage medium |
| CN108986825A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108831470A (en) * | 2018-08-24 | 2018-11-16 | 深圳伊讯科技有限公司 | A kind of method and system by voice control BMS |
| CN110880325B (en) * | 2018-09-05 | 2022-06-28 | 华为技术有限公司 | Identity recognition method and equipment |
| CN110880325A (en) * | 2018-09-05 | 2020-03-13 | 华为技术有限公司 | Identity recognition method and equipment |
| WO2020077841A1 (en) * | 2018-10-18 | 2020-04-23 | 平安科技（深圳）有限公司 | Voiceprint recognition-based customer service method, device, computer device, and storage medium |
| WO2020087336A1 (en) * | 2018-10-31 | 2020-05-07 | 深圳市大疆创新科技有限公司 | Control method and control device for mobile platform |
| CN111292734B (en) * | 2018-12-06 | 2024-03-08 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| WO2020114384A1 (en) * | 2018-12-06 | 2020-06-11 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| CN111292733A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| CN111292734A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Voice interaction method and device |
| CN109545203A (en) * | 2018-12-14 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Audio recognition method, device, equipment and storage medium |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN109756342A (en) * | 2019-01-16 | 2019-05-14 | 中民乡邻投资控股有限公司 | A kind of the account identity identifying method and device of the dialogue formula based on vocal print |
| CN109887503A (en) * | 2019-01-20 | 2019-06-14 | 北京联合大学 | A kind of man-machine interaction method of intellect service robot |
| CN109671438A (en) * | 2019-01-28 | 2019-04-23 | 武汉恩特拉信息技术有限公司 | It is a kind of to provide the device and method of ancillary service using voice |
| CN110428816B (en) * | 2019-02-26 | 2022-06-03 | 杭州蓦然认知科技有限公司 | Method and device for training and sharing voice cell bank |
| CN110428816A (en) * | 2019-02-26 | 2019-11-08 | 北京蓦然认知科技有限公司 | A kind of method and device voice cell bank training and shared |
| CN110570208A (en) * | 2019-07-29 | 2019-12-13 | 阿里巴巴集团控股有限公司 | Complaint preprocessing method and device |
| CN110910875A (en) * | 2019-11-13 | 2020-03-24 | 秒针信息技术有限公司 | Member management method and system based on voice recognition |
| CN110970033A (en) * | 2019-12-02 | 2020-04-07 | 浙江理工大学 | Voiceprint recognition automatic signing device and recognition method thereof |
| CN110868427A (en) * | 2019-12-02 | 2020-03-06 | 浙江理工大学 | Remote voice recognition automatic signing device and recognition method thereof |
| CN111429920A (en) * | 2020-03-30 | 2020-07-17 | 北京奇艺世纪科技有限公司 | User distinguishing method, user behavior library determining method, device and equipment |
| CN111429920B (en) * | 2020-03-30 | 2024-01-23 | 北京奇艺世纪科技有限公司 | User distinguishing method, user behavior library determining method, device and equipment |
| CN111462754A (en) * | 2020-04-16 | 2020-07-28 | 深圳航天科创实业有限公司 | Method for establishing dispatching control voice recognition model of power system |
| CN112069484A (en) * | 2020-11-10 | 2020-12-11 | 中国科学院自动化研究所 | Multi-mode interactive information acquisition method and system |
| CN112599136A (en) * | 2020-12-15 | 2021-04-02 | 江苏惠通集团有限责任公司 | Voice recognition method and device based on voiceprint recognition, storage medium and terminal |
| CN113555010A (en) * | 2021-07-16 | 2021-10-26 | 广州三星通信技术研究有限公司 | Voice processing method and voice processing device |
| CN114339342A (en) * | 2021-12-23 | 2022-04-12 | 歌尔科技有限公司 | Remote controller control method, remote controller, control device and medium |
| CN114422154A (en) * | 2022-03-30 | 2022-04-29 | 深圳市永达电子信息股份有限公司 | Digital certificate management method and device based on voice recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105810200A (en) | Man-machine dialogue apparatus and method based on voiceprint identification | |
| CN110209791B (en) | Multi-round dialogue intelligent voice interaction system and device | |
| US10600414B1 (en) | Voice control of remote device | |
| CN108000526B (en) | Dialogue interaction method and system for intelligent robot | |
| WO2021051506A1 (en) | Voice interaction method and apparatus, computer device and storage medium | |
| Anguera et al. | Speaker diarization: A review of recent research | |
| CN107818798A (en) | Customer service quality evaluating method, device, equipment and storage medium | |
| CN105843381B (en) | Data processing method for realizing multi-modal interaction and multi-modal interaction system | |
| CN103458056B (en) | Speech intention judging system based on automatic classification technology for automatic outbound system | |
| JP2019528512A (en) | Human-machine interaction method and apparatus based on artificial intelligence | |
| CN104538043A (en) | Real-time emotion reminder for call | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN109101663A (en) | A kind of robot conversational system Internet-based | |
| CN112131359A (en) | Intention identification method based on graphical arrangement intelligent strategy and electronic equipment | |
| KR20220140599A (en) | Synthetic speech audio data generated on behalf of a human participant in a conversation | |
| CN110019691A (en) | Conversation message treating method and apparatus | |
| CN114821744A (en) | Expression recognition-based virtual character driving method, device and equipment | |
| CN115293132A (en) | Conversation processing method and device of virtual scene, electronic equipment and storage medium | |
| CN111128175B (en) | Spoken language dialogue management method and system | |
| CN209328511U (en) | A kind of portable AI interactive voice control system | |
| CN112349266A (en) | Voice editing method and related equipment | |
| CN109830232A (en) | Man-machine interaction method, device and storage medium | |
| KR20210124050A (en) | Automatic interpretation server and method thereof | |
| CN112309396A (en) | AI virtual robot state dynamic setting system | |
| KR20210123545A (en) | Method and apparatus for conversation service based on user feedback |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |
|
| RJ01 | Rejection of invention patent application after publication |