Voice interactive method and device, vehicle-mounted voice interactive device and storage medium
Technical field
The present embodiments relate to interactive voice technology more particularly to a kind of voices applied to interactive system for vehicle-mounted voice
Exchange method and device, vehicle-mounted voice interactive device and storage medium.
Background technique
With the boundless development of intelligent network connection automobile, application more and more common, people of the voice assistant in automobile
Gradually relied on voice assistant and completed some simple vehicle controls, for example adjusted air-conditioner temperature, voice initiation navigation etc..So
And at present since voice technology ability can't reach complete ideal state, user using voice assistant frequency and
Viscosity is all lower.
In the prior art, frequency and viscosity that user uses voice assistant are improved generally by the following two kinds method: first
Kind, the monitoring of voice assistant is indicated using fixed animated graphics, identification, network request, answers the states such as execution, while passing through text
During word and other figures convey interactive voice, the other information of understanding needed for user;Second, use the shape that personalizes
As, such as the robot animation image or creature animation image, interactive voice is carried out with user, user is made to understand voice assistant in time
To the executive condition of instruction.
In the implementation of the present invention, the discovery prior art has following defects that above-mentioned first method to inventor
Interactive mode is more mechanical, it is difficult to improve frequency and viscosity that user uses voice assistant;The interaction side of above-mentioned second method
Formula, it is lower to the degree that personalizes of user although flexibility ratio increases compared with the interactive mode of first method,
Still it is difficult to using the frequency of voice assistant and viscosity all improve user to certain height.
Summary of the invention
The embodiment of the invention provides a kind of voice interactive method applied to interactive system for vehicle-mounted voice and devices, vehicle-mounted
Interactive voice equipment and storage medium to realize the personalization for improving interactive animation image and the degree that personalizes, and then improve
Frequency of use and viscosity of the user to interactive system for vehicle-mounted voice.
In a first aspect, being applied to interactive system for vehicle-mounted voice, packet the embodiment of the invention provides a kind of voice interactive method
It includes:
According to the numerical value of the facial characteristics parameter of acquired user, the facial shape of interaction corresponding with the user is adjusted
As;
According to interactive face image corresponding with the user adjusted, the required each voice of vehicle-mounted voice interaction is generated
Interaction FA Facial Animation;
Using the corresponding interactive voice FA Facial Animation of the execution state with vehicle-mounted voice interactive instruction, with the user
Carry out animation interactive voice.
Second aspect, the embodiment of the invention provides a kind of voice interaction devices, are set to interactive system for vehicle-mounted voice, packet
It includes:
Face image adjusts module, for the numerical value according to the facial characteristics parameter of acquired user, adjustment with it is described
The corresponding interactive face image of user;
FA Facial Animation generation module, for generating vehicle according to interactive face image corresponding with the user adjusted
Each interactive voice FA Facial Animation needed for carrying interactive voice;
Voice interaction module, for using the interactive voice face corresponding with the execution state of vehicle-mounted voice interactive instruction
Portion's animation carries out animation interactive voice with the user.
The third aspect, the embodiment of the invention provides a kind of vehicle-mounted voice interactive device, the vehicle-mounted voice interactive device
Include:
One or more processors;
Storage device, for storing one or more programs;
Camera, for obtaining the face-image of user;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes vehicle-mounted voice exchange method described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention provides a kind of storage medium comprising computer executable instructions, the meters
Calculation machine executable instruction is handed over when being executed as computer processor for executing vehicle-mounted voice described in any embodiment of that present invention
Mutual method.
The embodiment of the invention provides a kind of voice interactive method applied to interactive system for vehicle-mounted voice and devices, vehicle-mounted
Interactive voice equipment and storage medium, it is corresponding with user by being adjusted according to the numerical value of the facial characteristics parameter by user
Interaction face image, generate the required each interactive voice FA Facial Animation of vehicle-mounted voice interaction, and hand over using each voice generated
Mutual FA Facial Animation and user carry out animation interactive voice, and it is more mechanical, clever to solve vehicle-mounted voice interactive mode in the prior art
Activity is low, it is difficult to improve user using the technological deficiency of the frequency of interactive system for vehicle-mounted voice and viscosity, realize raising interaction
The personalization of animating image and the degree that personalizes, and then improve user to the frequency of use of interactive system for vehicle-mounted voice and glue
Property.
Detailed description of the invention
Fig. 1 is a kind of flow chart for voice interactive method that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow chart of voice interactive method provided by Embodiment 2 of the present invention
Fig. 3 is a kind of flow chart for voice interactive method that the embodiment of the present invention three provides;
Fig. 4 is a kind of structure chart for voice interaction device that the embodiment of the present invention four provides;
Fig. 5 is a kind of structure chart for vehicle-mounted voice interactive device that the embodiment of the present invention five provides.
Specific 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 limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for voice interactive method that the embodiment of the present invention one provides, and the present embodiment is applicable to drive
The case where passenger and interactive system for vehicle-mounted voice on personnel or vehicle carry out interactive voice is sailed, this method can be by interactive voice
Device executes, which can be by software and or hardware realization, which can be integrated in vehicle-mounted voice interactive device.
As shown in Figure 1, this method specifically comprises the following steps:
S101, the numerical value according to the facial characteristics parameter of acquired user adjust the facial shape of interaction corresponding to the user
As.
In the present embodiment, user specifically can be the driver of this vehicle or the passenger of this vehicle, can also be driving for this vehicle
Personage etc. on the objects such as image, the picture that the person of sailing or the passenger of this vehicle are shown.Facial characteristics parameter specifically can be upper lip
Between the distance between the distance between the distance between lower lip, two corners of the mouths, upper lip and nose, the wing of nose and nose away from
From the distance between in the middle part of the distance between the distance between, upper eyelid and palpebra inferior, eyebrows and eyebrows and eyebrow etc..
In the present embodiment, in voice interaction device, it is previously stored the face for carrying out interactive voice with user
Image, or the facial shape for carrying out interactive voice with user can be obtained from corresponding server by wireless network
As.It is understood that different human face's features is different, even there are larger differences sometimes, accordingly, it is difficult to realize
In all existing face images, exist and all more matched face image of the facial characteristics of each user.Therefore, in this implementation
In example, by the numerical value according to the facial characteristics parameter of user, existing face image is modified, so that corresponding with user
Interaction face image be more close to the users real life facial image.
Further, in the present embodiment, it after obtaining the numerical value of facial characteristics parameter of user, can specifically carry out
The following two kinds operation adjusts interactive face image corresponding to the user to realize:
The first, by voice interaction device actively from the existing each facial shape that can be used for carrying out interactive voice with user
As the face image that the facial characteristics parameter of middle selection and user is closer to, as face image to be modified, then,
According to the numerical value of the facial characteristics parameter of acquired user, to this, face image to be modified is modified.
Second, user actively chooses one from the existing each face image that can be used for carrying out interactive voice with user
A face image is as face image to be modified, then, according to the numerical value of the facial characteristics parameter of acquired user, to this
Face image to be modified is modified.
Two kinds of operations as above are of course not solely limited to, two kinds of operations as above are merely illustrative.
Further, in the present embodiment, existing face image is modified, to obtain interaction face corresponding to the user
The method of portion's image specifically can be according to user each facial characteristics parameter numerical value, successively to existing face image into
Row amendment, can also be the numerical value of the facial characteristics parameter according to user, the number with the facial characteristics parameter of existing face image
The numerical value that biggish facial characteristics parameter is differed between value, is modified existing face image, can also be according to user's
The numerical value of each key facial feature parameter, is successively modified existing face image.
S102, according to interactive face image corresponding to the user adjusted, generate the required each language of vehicle-mounted voice interaction
Sound interacts FA Facial Animation.
It is understood that bringing better usage experience to user, generally to keep interactive voice process more lively
The form and user that will use animation carry out interactive voice.Therefore, in the present embodiment, interaction face corresponding to the user is being adjusted
After portion's image, the various dynamic for the interactive voice face in vehicle-mounted voice interactive process of the interaction face image can be generated
It draws.
Illustratively, interactive voice FA Facial Animation may include the smile of interactive face image corresponding to the user, laugh,
It crys, broadcast the corresponding FA Facial Animation of a variety of moods such as road conditions, indignation, helpless, can also include for indicating currently performed
The corresponding interactive face image of voice operating (such as networking, downloading data, adjust the operation such as air-conditioner temperature) FA Facial Animation
Deng.
S103, using the corresponding interactive voice FA Facial Animation of execution state with vehicle-mounted voice interactive instruction, with user into
Action picture interactive voice.
In the present embodiment, after each interactive voice FA Facial Animation of interactive face image corresponding to the user generates,
During executing the vehicle-mounted voice interactive instruction that user sends, the execution shape of meeting real-time display and vehicle-mounted voice interactive instruction
The corresponding interactive voice FA Facial Animation of state.It illustratively, can be with the corresponding interactive voice face of the currently performed operation of real-time display
Portion's animation or the corresponding interactive voice FA Facial Animation of the performance level of real-time display vehicle-mounted voice interactive instruction etc..
The embodiment of the invention provides a kind of voice interactive method applied to interactive system for vehicle-mounted voice, by according to by
The interactive face image corresponding to the user that the numerical value of the facial characteristics parameter of user adjusts generates vehicle-mounted voice interaction institute
Each interactive voice FA Facial Animation needed, and animation interactive voice is carried out using each interactive voice FA Facial Animation and user generated,
It is low to solve vehicle-mounted voice interactive mode more machinery, flexibility ratio in the prior art, it is difficult to improve user and hand over using vehicle-mounted voice
The frequency of mutual system and the technological deficiency of viscosity, realize the personalization for improving interactive animation image and the degree that personalizes, into
And user is improved to the frequency of use and viscosity of interactive system for vehicle-mounted voice.
Embodiment two
Fig. 2 is a kind of flow chart of voice interactive method provided by Embodiment 2 of the present invention.The present embodiment is with above-mentioned implementation
It is optimized based on example, in the present embodiment, gives a kind of acquisition process of numerical value for increasing facial characteristics parameter, specifically
Change the process for carrying out animation interactive voice with user, and embodies the specific embodiment party for adjusting the process of interaction face image
Formula.Same as the previously described embodiments or corresponding term explains that this embodiment is not repeated.
Correspondingly, the method for the present embodiment specifically includes:
S201, this vehicle interactive system for vehicle-mounted voice starting after, obtain the face-image of current driver.
In the present embodiment, step 201 and step 202 are increased, the numerical value of the facial characteristics parameter for obtaining user.
Meanwhile " user " being embodied as to the current driver of this vehicle.
In the present embodiment, interactive system for vehicle-mounted voice is after start-up (either current driver passes through manually
Or vice activation, it is also possible to start automatically when this vehicle starts), internal or external image acquisition equipment (example can be passed through
Such as camera) obtain the face-image of current driver.Specifically, interactive system for vehicle-mounted voice can at interval of one compared with
The short time just obtains the face-image of the current driver of a width, to get required face-image as early as possible.Further,
If the face of current driver is at a distance from image acquisition equipment, angle etc. is improper, image acquisition equipment is difficult to obtain
Required face-image is got, at this point, interactive system for vehicle-mounted voice can be prompted by voice or picture, so that currently
Face is moved to effective images acquisition locations by driver, and is turned to effective image and obtained angle.In general, until
The frontal face images and a side face-image for needing to obtain current driver less, can just accurately determine
The numerical value of the facial characteristics parameter of current driver.
S202, according to the face-image of current driver, obtain the numerical value of the facial characteristics parameter of current driver.
In the present embodiment, the numerical value of the facial characteristics parameter of current driver is worked as by acquired in step 201
The face-image of preceding driver is determined.
S203, the numerical value according to the facial characteristics parameter of acquired current driver, from alternative face image set
In, it chooses and the matched alternative face image of current driver.
In the present embodiment, the face image for being corrected, not current driver choose, vehicle-mounted voice
Numerical value of the interactive system according to the facial characteristics parameter of current driver, automatically from alternative face image set, selection
One and the matched alternative face image of current driver.
Specifically, choosing specifically can be the following two kinds with the method for the matched alternative face image of current driver
Any one of method:
The first chooses the highest facial characteristics ginseng of different degree from all facial characteristics parameters of current driver
Number chooses the values match degree highest with the highest facial characteristics parameter of the different degree then from alternative face image set
Alternative face image, as with the matched alternative face image of current driver.
Second, from all facial characteristics parameters of current driver, choose own value mark corresponding with itself
Quasi- numerical value differs maximum facial characteristics parameter as facial characteristics parameter to be compared, then from alternative face image set
In, choose with the highest face image of values match degree of the facial characteristics parameter to be compared as with current driver
The alternative face image matched.
Two kinds of operations as above are of course not solely limited to, two kinds of operations as above are merely illustrative.
S204, the numerical value according to the facial characteristics parameter of current driver, change the facial characteristics of alternative face image,
Obtain interactive face image corresponding with current driver.
In the present embodiment, after the alternative face image of determination, can't directly using the alternative face image as with
The corresponding interactive face image of current driver, but can be according further to the number of the facial characteristics parameter of current driver
Value, changes the facial characteristics of alternative face image.
Further, the method for changing the facial characteristics of alternative face image specifically can be the every of current driver
The numerical value of one facial characteristics parameter is mapped to alternative face image, can also be and joins the facial characteristics of current driver
In number, own value differs biggish with standard figures, and the numerical value of each facial characteristics parameter is mapped to alternative face image, also
The numerical value that can be the facial characteristics parameter for choosing user, is mapped to alternative face image etc., the present embodiment to this without
Limitation.
S205, according to interactive face image corresponding with current driver adjusted, generate vehicle-mounted voice interaction institute
Each interactive voice FA Facial Animation needed.
S206, the vehicle-mounted voice interactive instruction that current driver sends is received.
S207, vehicle-mounted voice interactive instruction is executed, and shows each execution stage corresponding voice in the process of implementation
Interaction FA Facial Animation, while each execution stage corresponding casting voice is broadcasted, to carry out animation language with current driver
Sound interaction.
In the present embodiment, the vehicle-mounted voice interaction sent by the current driver that step 206 receives is being executed
During instruction, in each execution stage, can all show with the execution content, implementing result, completeness in the stage etc.
The corresponding interactive voice FA Facial Animation of aspect, and while showing interactive voice FA Facial Animation, it can also broadcast and current language
The corresponding casting voice of sound interaction FA Facial Animation, preferably to carry out animation interactive voice with current driver.
The embodiment of the invention provides a kind of voice interactive methods, and this method increase obtaining for the numerical value of facial characteristics parameter
Process is taken, quickly, accurately and efficiently to obtain the numerical value of the facial characteristics parameter of user, embodies and carries out animation with user
The process of interactive voice further improves frequency and viscosity that user uses interactive system for vehicle-mounted voice, embodies further tune
The process of whole interactive face image, so that interactive face image adjusted, is more nearly the face image of user, Jin Erti
High user uses the frequency and viscosity of interactive system for vehicle-mounted voice.
Embodiment three
Fig. 3 is a kind of flow chart for voice interactive method that the embodiment of the present invention three provides.The present embodiment is with above-mentioned implementation
Optimized based on example, in the present embodiment, give a kind of acquisition process for embodying alternative face image, embody with
The obtaining step of the corresponding interactive face image of user, and embody the specific reality of the generating process of interactive voice FA Facial Animation
Apply mode.Same as the previously described embodiments or corresponding term explains that this embodiment is not repeated.
Correspondingly, the method for the present embodiment specifically includes:
S301, this vehicle interactive system for vehicle-mounted voice starting after, obtain the face-image of current driver.
S302, according to the face-image of current driver, obtain the numerical value of the facial characteristics parameter of current driver,
And by the numerical value of the facial characteristics parameter of current driver, the numerical value of the facial characteristics parameter as current driver.
S303, the different degree according to facial characteristics parameter, from big to small, to each facial characteristics parameter of current driver
It is ranked up, and using first facial characteristics parameter in ranking results as current matching facial characteristics parameter.
In the present embodiment, pass through step 303 to step 307 determination and the matched alternative facial shape of current driver
As.
In the present embodiment, different facial characteristics parameters has different different degrees, the higher facial characteristics of different degree
Parameter, the influence to the selection result with the matched alternative face image of current driver are bigger.Firstly, passing through this step
303, the different degree according to facial characteristics parameter is from big to small ranked up each facial characteristics parameter of current driver,
The result of sequence is as the reference sequence that each facial characteristics parameter is compared in step 304 to step 307.
Further, in the present embodiment, a facial characteristics can successively be chosen according to the sequence of different degree from big to small
Parameter, as current matching facial characteristics parameter.
S304, from alternative face image set, choose the numerical value of the current matching facial characteristics parameter of itself, and it is current
The immediate alternative face image of numerical value of the current matching facial characteristics parameter of driver, as current matching face shape
As.
In the present embodiment, it after determining current matching facial characteristics parameter, can obtain in alternative face image set,
The numerical value of the current matching facial characteristics parameter of each alternative face image, and the numerical value of the acquisition is driven with current one by one
The numerical value of the current matching facial characteristics parameter of personnel is compared, finally by the number of the current matching facial characteristics parameter of itself
Value, the immediate alternative face image of numerical value with the current matching facial characteristics parameter of current driver is as current matching
Face image.
Further it should be noted that being generally not in the current matching face of two or more alternative face images
The numerical value of characteristic parameter is identical, and the immediate situation of numerical value with the current matching facial characteristics parameter of current driver.
If there is above situation, next face of current matching facial characteristics parameter can be chosen from the ranking results of step 303
Then portion's characteristic parameter is re-executed the operation of this step, is worked as with final determination as new current matching facial characteristics parameter
Preceding matching face image.
S305, judge current matching face image current matching facial characteristics parameter numerical value, with current driver
The numerical value of current matching facial characteristics parameter whether meet matching rule, if so, 306 are thened follow the steps, if otherwise executing step
Rapid 307.
It in the present embodiment, can't be directly by current matching face after current matching face image has been determined
Image as with the matched alternative face image of current driver.Even if it is understood that current matching face image
The numerical value of current matching facial characteristics parameter is big with the difference of the numerical value of the current matching facial characteristics parameter of current driver
In other alternative face-images, but it is also likely to be present the number of the current matching facial characteristics parameter of current matching face image
Value, the larger situation with the difference of the numerical value of the current matching facial characteristics parameter of current driver.
Therefore, in the present embodiment, by the deterministic process of this step, to the current matching face of current matching face image
The numerical value of portion's characteristic parameter, with the difference of the numerical value of the current matching facial characteristics parameter of current driver larger situation into
Row filtering.
In the present embodiment, matching rule specifically can be the current matching facial characteristics parameter of current matching face image
Numerical value, should be greater than given threshold etc. divided by the quotient of the numerical value of the current matching facial characteristics parameter of current driver.
S306, by current matching face image, as with the matched alternative face image of current driver.
S307, by ranking results, facial characteristics parameter after current matching facial characteristics parameter is worked as new
Preceding matching facial characteristics parameter, and 304 are returned to step, until having traversed all facial characteristics parameters in ranking results.
In the present embodiment, the numerical value of the current matching facial characteristics parameter of current matching face image drives with current
When the numerical value of the current matching facial characteristics parameter of personnel is unsatisfactory for matching rule, then it can be selected from the ranking results of step 303
The facial characteristics parameter after current matching facial characteristics parameter is taken, as new current matching facial characteristics parameter, then, weight
Current matching face image is newly chosen from alternative face image set, that is, returns to step 304.
In the present embodiment, default the setting based on matching rule, can centainly be chosen from alternative face image set
Out with the matched alternative face image of current driver.Therefore, all facial characteristics parameters in ranking results are being traversed
When or before, can centainly be selected and the matched alternative face image of current driver from alternative face image set.
S308, by the numerical value of the facial characteristics parameter of alternative face image, be revised as the facial characteristics of current driver
The numerical value of parameter obtains new interaction corresponding with current driver and moves face image.
In the present embodiment, after the alternative face image of determination, all facial characteristics of the meeting according to current driver
The numerical value of the numerical value of parameter, the facial characteristics parameter to alternative face image being corresponding in turn to is modified, and is ultimately generated new
Face image is moved in interaction corresponding with current driver.
The numerical value of each setting expressive parameter of S309, the current driver of acquisition.
In the present embodiment, the required each interactive voice face of vehicle-mounted voice interaction is generated by step 309 and step 310
Animation.In the present embodiment, interactive voice FA Facial Animation is not that interactive system for vehicle-mounted voice is joined according to the program of itself completely
What number generated, but the numerical generation of each setting expressive parameter according to current driver.
Therefore, in the present embodiment, each setting expressive parameter that this step 309 obtains current driver is first passed through
Numerical value.Wherein, setting expression specifically refers to the required corresponding expression of each interactive voice FA Facial Animation of vehicle-mounted voice interaction.
S310, the numerical value according to each setting expressive parameter and interaction corresponding with current driver adjusted
Face image generates each setting expressive animation of interactive face image corresponding with current driver adjusted, and
Using each setting expressive animation each interactive voice FA Facial Animation required as vehicle-mounted voice interaction.
In the present embodiment, each setting expressive of interactive face image corresponding with current driver adjusted
Animation all maps to adjusted corresponding with current driver particular by by the numerical value of each setting expressive parameter
Interaction face image and obtain.
S311, the vehicle-mounted voice interactive instruction that current driver sends is received.
S312, vehicle-mounted voice interactive instruction is executed, and shows each execution stage corresponding voice in the process of implementation
Interaction FA Facial Animation, while each execution stage corresponding casting voice is broadcasted, to carry out animation language with current driver
Sound interaction.
The embodiment of the invention provides a kind of voice interactive method, this method embodies the acquisition of alternative face image
Journey embodies the obtaining step of interactive face image corresponding to the user, embodies further the life of interactive voice FA Facial Animation
At process
Example IV
Fig. 4 is a kind of structure chart for voice interaction device that the embodiment of the present invention four provides, and the present embodiment is in above-mentioned each reality
On the basis of applying example, the embodiment of " voice interactive method " is provided.Same as the previously described embodiments or corresponding term explanation,
This embodiment is not repeated.
As shown in figure 4, described device includes: face image adjustment module 401, FA Facial Animation generation module 402 and language
Sound interactive module 403, in which:
Face image adjusts module 401, for the numerical value according to the facial characteristics parameter of acquired user, adjustment and uses
The corresponding interactive face image in family;
FA Facial Animation generation module 402, for generating vehicle-mounted according to interactive face image corresponding to the user adjusted
Each interactive voice FA Facial Animation needed for interactive voice;
Voice interaction module 403, for using interactive voice face corresponding with the execution state of vehicle-mounted voice interactive instruction
Portion's animation carries out animation interactive voice with user.
The embodiment of the invention provides a kind of voice interaction device, which adjusts module 401 by face image first
According to the numerical value of the facial characteristics parameter of acquired user, interactive face image corresponding to the user is adjusted, face is then passed through
It is required to generate vehicle-mounted voice interaction according to interactive face image corresponding to the user adjusted for portion's animation producing module 402
Each interactive voice FA Facial Animation uses the execution state pair with vehicle-mounted voice interactive instruction finally by voice interaction module 403
The interactive voice FA Facial Animation answered carries out animation interactive voice with user.
Which solves vehicle-mounted voice interactive mode in the prior art more machinery, flexibility ratio are low, it is difficult to improve user
Using interactive system for vehicle-mounted voice frequency and viscosity technological deficiency, realize improve interactive animation image personalization and
Personalize degree, and then improves user to the frequency of use and viscosity of interactive system for vehicle-mounted voice.
On the basis of the various embodiments described above, can also include:
Face-image obtains module, in the numerical value according to the facial characteristics parameter of acquired user, adjustment and uses
Before the corresponding interactive face image in family, after the interactive system for vehicle-mounted voice starting of this vehicle, obtain current driver's
Face-image;
Facial characteristics parameter acquisition module obtains current driver for the face-image according to current driver
Facial characteristics parameter numerical value, and the facial characteristics by the numerical value of the facial characteristics parameter of current driver, as user
The numerical value of parameter.
On the basis of the various embodiments described above, voice interaction module 403 may include:
Interactive instruction acquiring unit, for receiving the vehicle-mounted voice interactive instruction of user's transmission;
Animation interactive voice unit for executing vehicle-mounted voice interactive instruction, and shows that each is held in the process of implementation
The corresponding interactive voice FA Facial Animation of row order section, while broadcasting each execution stage corresponding casting voice, with user into
Action picture interactive voice.
On the basis of the various embodiments described above, face image adjustment module 401 may include:
Alternative face image selection unit, for the numerical value according to the facial characteristics parameter of acquired user, from alternative
In face image set, choose and the matched alternative face image of user;
Interaction face image determination unit changes alternative facial shape for the numerical value according to the facial characteristics parameter of user
The facial characteristics of elephant obtains interactive face image corresponding to the user.
On the basis of the various embodiments described above, alternative face image selection unit may include:
Sorting subunit from big to small, joins each facial characteristics of user for the different degree according to facial characteristics parameter
Number is ranked up, and using first facial characteristics parameter in ranking results as current matching facial characteristics parameter;
Face image chooses subelement, and the current matching face for from alternative face image set, choosing itself is special
Levy the numerical value of parameter, the immediate alternative face image of numerical value with the current matching facial characteristics parameter of user, as current
Match face image;
Alternative face image determines subelement, if the current matching facial characteristics parameter for current matching face image
Numerical value, the numerical value with the current matching facial characteristics parameter of user meets matching rule, then by current matching face image,
As with the matched alternative face image of user;
Operation subelement is returned, if the numerical value of the current matching facial characteristics parameter for current matching face image,
With the numerical value of the current matching facial characteristics parameter of user, it is unsatisfactory for matching rule, then by ranking results, in current matching face
Facial characteristics parameter after portion's characteristic parameter as new current matching facial characteristics parameter, and returns to execution from alternative face
In portion's image set, the numerical value of the current matching facial characteristics parameter of itself is chosen, is joined with the current matching facial characteristics of user
The immediate alternative face image of several numerical value, as the operation of current matching face image, until having traversed in ranking results
All facial characteristics parameters.
On the basis of the various embodiments described above, interaction face image determination unit specifically can be used for:
By the numerical value of the facial characteristics parameter of alternative face image, it is revised as the numerical value of the facial characteristics parameter of user, is obtained
Face image is moved to new interaction corresponding to the user.
On the basis of the various embodiments described above, FA Facial Animation generation module 402 may include:
Expression parameter acquiring unit, the numerical value of each setting expressive parameter for obtaining user;
Interactive voice FA Facial Animation generation unit, for according to each setting numerical value of expressive parameter and adjusted
Interactive face image corresponding to the user generates each setting expressive of interactive face image corresponding to the user adjusted
Animation, and each interactive voice FA Facial Animation that each setting expressive animation is required as vehicle-mounted voice interaction.
Voice interaction device provided by the embodiment of the present invention can be performed voice provided by any embodiment of the invention and hand over
Mutual method has the corresponding functional module of execution method and beneficial effect.The not technical detail of detailed description in the present embodiment,
It can be found in the voice interactive method that any embodiment of that present invention provides.
Embodiment five
Fig. 5 is a kind of structural schematic diagram for vehicle-mounted voice interactive device that the embodiment of the present invention five provides.Fig. 5 shows suitable
In the block diagram for the exemplary on board interactive voice equipment 12 for being used to realize embodiment of the present invention.The vehicle-mounted voice that Fig. 5 is shown is handed over
Mutual equipment 12 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, vehicle-mounted voice interactive device 12 is showed in the form of universal computing device.Vehicle-mounted voice interactive device
12 component can include but is not limited to: one or more processor or processing unit 16, system storage 28, and connection is not
The bus 18 of homologous ray component (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Vehicle-mounted voice interactive device 12 typically comprises a variety of computer system readable media.These media can be any
The usable medium that can be accessed by vehicle-mounted voice interactive device 12, including volatile and non-volatile media, movably and not
Moveable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Vehicle-mounted voice interactive device 12 may further include other removable
Dynamic/immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for
Read and write immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although not showing in Fig. 5
Out, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to removable
The CD drive of anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases,
Each driver can be connected by one or more data media interfaces with bus 18.System storage 28 may include to
A few program product, the program product have one group of (for example, at least one) program module, these program modules are configured to
Execute the function of various embodiments of the present invention.
Program/utility 40 with one group of (at least one) program module 42 can store and store in such as system
In device 28, such program module 42 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 42
Usually execute the function and/or method in embodiment described in the invention.
Vehicle-mounted voice interactive device 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display
Device 24 etc.) communication, the equipment interacted with the vehicle-mounted voice interactive device 12 communication can be also enabled a user to one or more,
And/or with enable the vehicle-mounted voice interactive device 12 and one or more of the other any equipment for being communicated of calculating equipment
(such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also,
Vehicle-mounted voice interactive device 12 can also by network adapter 20 and one or more network (such as local area network (LAN), extensively
Domain net (WAN) and/or public network, such as internet) communication.As shown, network adapter 20 by bus 18 with it is vehicle-mounted
Other modules of interactive voice equipment 12 communicate.It should be understood that although not shown in the drawings, vehicle-mounted voice interactive device can be combined
12 use other hardware and/or software module, including but not limited to: microcode, device driver, redundant processing unit, outside
Disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize voice interactive method provided by the embodiment of the present invention.Namely: according to the face of acquired user
The numerical value of characteristic parameter adjusts interactive face image corresponding with the user;According to adjusted corresponding with the user
Interaction face image generates the required each interactive voice FA Facial Animation of vehicle-mounted voice interaction;Using with vehicle-mounted voice interactive instruction
The corresponding interactive voice FA Facial Animation of execution state, with the user carry out animation interactive voice.
Camera 17 is used to obtain the face-image of user.
Embodiment six
The embodiment of the present invention six additionally provides a kind of computer readable storage medium, is stored thereon with computer program,
It is characterized in that, the voice interactive method as described in any embodiment of that present invention is realized when which is executed by processor.Namely: root
According to the numerical value of the facial characteristics parameter of acquired user, interactive face image corresponding with the user is adjusted;According to adjustment
Interactive face image corresponding with the user afterwards generates the required each interactive voice FA Facial Animation of vehicle-mounted voice interaction;Make
With the corresponding interactive voice FA Facial Animation of the execution state with vehicle-mounted voice interactive instruction, animation language is carried out with the user
Sound interaction.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.