CN107426143A - The quick accessing method of user vehicle and device based on Application on Voiceprint Recognition - Google Patents

Abstract

The present invention relates to a kind of quick accessing method of user vehicle based on Application on Voiceprint Recognition and device, by for each information model distribution corresponding to memory cell, and limit the SC service ceiling of each information model, when logining checking, the text information corresponding to voice print database inputted by user, by the range of search of vocal print feature code be locked in corresponding in memory cell, and extract from the memory cell user name corresponding with the vocal print feature code-phase and login password and logined.Can be logined by the voice print database of user, user name and password are manually entered without user, substantially increase user login the convenience of operation with it is intelligent；Also, user profile classification storage substantially reduces the time of vocal print feature code comparison, so that speech recognition can be applied to user and login.

Description

The quick accessing method of user vehicle and device based on Application on Voiceprint Recognition

Technical field

The present invention relates to automobile technical field, more particularly to a kind of quick side of logining of user vehicle based on Application on Voiceprint RecognitionMethod and device.

Background technology

With the continuous development of automotive engineering, present automobile is increasingly to energy-conserving and environment-protective direction and intelligent interconnection directionDevelop, the function in automobile also becomes increasingly complex.And in order to preferably manage these functions, and be easy to interact with driver,The car-mounted terminals such as car running computer would generally be provided with automobile.Information exchange between driver and car-mounted terminal, Ke YitongCross control button input or touch-screen input；And some automobiles can also be controlled by phonetic entry, as Chevrolet automobile is takenThe Anji star system of load.In existing car-mounted terminal, using carry out user's checking is preceding usually required that, only it is verifiedUse can just be logined.

In the prior art, the checking of user is mainly verified by user name with logining password.In some realization sidesIn case, also have by speech recognition to realize the input of control instruction.The scheme of the existing control instruction of present speech recognition is mainFor：Control instruction collection is prestored in systems, when in use, the user speech collected from sound acquisition module, andSystem is digitized processing, extracts the characteristic value of voice, then carry out with the condition code of the voice command concentration of system storageMatching verification, identifies order, and rear and other controllers carry out information interchange and perform action.

During the present invention is realized, inventor has found that there are the following problems in the prior art, existing car-mounted terminalCan only be by verifying that user name is logined with password, car-mounted terminal logins operation inconvenience, and user's use is not convenient enough, inadequate human natureChange.Also, in the method for the Voice command of existing car-mounted terminal, voice control command data are all based on a speech databaseStored and called, cause system huge, renewal speed is slow, and cost is high, and system flexibility is low, and renewal and extension are not easy；Judge that each phonetic order is required for retrieving and calling from whole database, subset of commands corresponding to matching is done check, madeTime into response is relatively long.Because the enrollment of user vehicle is continuously increased, the user data stored is very huge,Time-consuming for existing speech recognition schemes, in a short time according to the pronunciation character of user, can not identify the identity of user,Therefore, when existing speech recognition schemes can not be applied to login in the identification of user.

The content of the invention

For this reason, it may be necessary to a kind of user vehicle verification method using more quick, simplicity and intelligence is provided, it is existing for solvingThere is in technology user login car-mounted terminal and login operation inconvenience, and time-consuming for speech recognition, is not used to user identity identificationTechnical problem.

To achieve the above object, a kind of quick accessing method of the user vehicle based on Application on Voiceprint Recognition is inventor provided, is wrappedInclude following steps：

Default two or more information model, memory cell corresponding to respectively each information model distribution, and set eachThe higher limit that information model is reused；

In user's registration, obtain the user name of user, login password and user according to the progress of a wherein information modelThe voice print database of pronunciation, and from the voice print database extract user vocal print feature code, and by the user name, login it is closeWhat code and vocal print feature code associated stores into the memory cell corresponding to described information template；

When user logins, the voice print database of user is obtained, identify the text information corresponding to user's voice print database, and fromThe vocal print feature code of user is extracted in the voice print database；

The memory cell of storage user profile is determined according to the text information, and extract from the memory cell withUser name corresponding to the vocal print feature code-phase and login password and logined.

Further optimization, the voice print database are obtained by the sound pick-up of automobile mounted terminal；With each information modelCorresponding memory cell is arranged on cloud server；

When user logins, by the text information corresponding to automobile mounted terminal recognition user voice print database, and by instituteState voice print database and text information is sent to cloud server；And

The vocal print feature code of user is extracted from the voice print database by cloud server, and according to received textWord information determines the memory cell of storage user profile, and whether retrieved from memory cell has the vocal print matched with the user specialCode is levied, if so, then the user is registered users, and user name corresponding with the vocal print feature code is extracted and logins passwordLogined；If nothing, refuse the user and login.

Further optimization, the vocal print feature code include acoustic feature and prosodic features.

Further optimization,

It is described that user name corresponding with the vocal print feature code-phase is extracted from the memory cell and logins password progressLogin and specifically include：

The vocal print feature code of the user is compared with the vocal print feature code in storage element, when the vocal print of the user is specialWhen the similar value of sign code and the vocal print feature code in storage element exceedes setting value, it is right to extract vocal print feature code institute in memory cellThe user name answered and password is logined, and using the user name and login password and logined.

Further optimization, in user's registration, the vocal print feature code of the extraction user from the voice print database is specificIncluding step：

The voice print database that user is pronounced using identical information template is obtained more than twice；

Judge in acquired voice print database, whether the similarity of condition code is more than preset value, if so, then vocal print feature codeExtract successfully；If it is not, then vocal print feature code extraction failure.

The present inventor additionally provides a kind of user vehicle based on Application on Voiceprint Recognition of another technical scheme and quickly logins dressPut, including preset unit, registering unit and login unit；

The default unit is used to preset two or more information model, is stored corresponding to respectively each information model distributionUnit, and set the higher limit that each information model is reused；

The registering unit is used in user's registration, obtains the user name of user, logins password and user according to itIn the voice print database that is pronounced of an information model, and extract from the voice print database vocal print feature code of user, and willThe user name, login password and vocal print feature code association store into the memory cell corresponding to described information template；

The unit of logining is used for when user logins, and obtains the voice print database of user, and identification user voice print database institute is rightThe text information answered, and from the voice print database extract user vocal print feature code；And

The memory cell of storage user profile is determined according to the text information, and extract from the memory cell withUser name corresponding to the vocal print feature code-phase and login password and logined.

Further optimization, the voice print database are obtained by the sound pick-up of automobile mounted terminal；With each information modelCorresponding memory cell is arranged on cloud server；

The unit of logining is when user logins checking, by corresponding to automobile mounted terminal recognition user voice print databaseText information, and the voice print database and text information are sent to cloud server；And

The vocal print feature code of user is extracted from the voice print database by cloud server, and according to received textWord information determines the memory cell of storage user profile, and whether retrieved from memory cell has the vocal print matched with the user specialCode is levied, if so, then the user is registered users, and user name corresponding with the vocal print feature code is extracted and logins passwordLogined；If nothing, refuse the user and login.

Further optimization, the vocal print feature code include acoustic feature and prosodic features.

Further optimization,

The unit of logining extracts user name corresponding with the vocal print feature code-phase and logined from the memory cellPassword login specifically including：

The vocal print feature code of the user is compared with the vocal print feature code in storage element, when the vocal print of the user is specialWhen the similar value of sign code and the vocal print feature code in storage element exceedes setting value, it is right to extract vocal print feature code institute in memory cellThe user name answered and password is logined, and using the user name and login password and logined.

Further optimization, the registering unit is in user's registration, the sound that user is extracted from the voice print databaseLine condition code specifically includes：

The voice print database that user is pronounced using identical information template is obtained more than twice；

Judge in acquired voice print database, whether the similarity of condition code is more than preset value, if so, then vocal print feature codeExtract successfully；If it is not, then vocal print feature code extraction failure.

Prior art is different from, above-mentioned technical proposal is by default more than two information models, and is each informationMemory cell corresponding to template distribution, in user's registration, each user is pronounced according to one of information model, and is obtainedTake the user name at family, login password and the vocal print feature code of user, and associated storage is in storage corresponding with information modelIn unit；When user logins checking, identify user input voice print database corresponding to text information and user's vocal printCondition code, the memory cell of storage user profile is determined according to the text information, and is extracted from the memory cellUser name corresponding with the vocal print feature code-phase and login password and logined.Above-mentioned technical proposal is by for each information modelMemory cell corresponding to distribution, and the SC service ceiling of each information model is limited, when logining checking, pass through the sound of user's inputText information corresponding to line data, by the range of search of vocal print feature code be locked in corresponding in memory cell, and from describedUser name corresponding with the vocal print feature code-phase is extracted in memory cell and logins password and is logined.Above-mentioned technical proposal is led toCrossing the voice print database of user can be logined, and be manually entered user name and password without user, substantially increased user and loginThe convenience of operation with it is intelligent；Also, user profile classification storage substantially reduces the time of vocal print feature code comparison, so as toMake speech recognition can be applied to user to login.

Brief description of the drawings

Fig. 1 is that a kind of flow of the quick accessing method of user vehicle based on Application on Voiceprint Recognition described in embodiment is illustratedFigure；

Fig. 2 is a kind of mechanism signal that the user vehicle based on Application on Voiceprint Recognition described in embodiment quickly logins deviceFigure.

Embodiment

To describe the technology contents of technical scheme, construction feature, the objects and the effects in detail, below in conjunction with specific realityApply example and coordinate accompanying drawing to be explained in detail.

Referring to Fig. 1, a kind of quick accessing method of user vehicle based on Application on Voiceprint Recognition of the present embodiment, including following stepSuddenly：

Step 110：Default two or more information model, memory cell corresponding to respectively each information model distribution, andSet the higher limit that each information model is reused；

Step 120：In user's registration, obtain the user name of user, login password and user according to a wherein informationThe voice print database that template is pronounced, and the vocal print feature code of user is extracted from the voice print database, and by the userName, login password and vocal print feature code association store into the memory cell corresponding to described information template；

Step 130：When user logins, the voice print database of user is obtained, identifies the word corresponding to user's voice print databaseInformation, and from the voice print database extract user vocal print feature code；

Step 140：The memory cell of storage user profile is determined according to the text information, and from the memory cellExtract user name corresponding with the vocal print feature code-phase and login password and logined.

By preset more than two information models, and for each information model distribution corresponding to memory cell, withFamily register when, each user is pronounced according to one of information model, and obtain the user name of user, login password andThe vocal print feature code of user, and associated storage is in memory cell corresponding with information model；When user logins checking, identificationThe condition code of text information and user's vocal print corresponding to the voice print database of the input of user, determined according to the text informationStore the memory cell of user profile, and extract from the memory cell user name corresponding with the vocal print feature code-phase andPassword is logined to be logined.Above-mentioned technical proposal is limited each by for memory cell corresponding to the distribution of each information modelThe SC service ceiling of information model, when logining checking, by the text information corresponding to the voice print database of user's input, by vocal printThe range of search of condition code is locked in corresponding memory cell, and is extracted and the vocal print feature code from the memory cellCorresponding user name and login password and logined.Above-mentioned technical proposal can be logined by the voice print database of user,Be manually entered user name and password without user, substantially increase user login the convenience of operation with it is intelligent；Also, userInformation classification storage substantially reduces the time of vocal print feature code comparison, so that speech recognition can be applied to user and login.

Multiple masterplates are preset, such as masterplate " cloud degree automobile changes ordinary ", masterplate " cloud degree pursued vehicle is remarkable ", masterplate " oneRoad safety " etc., in user's registration, according to an a kind of masterplate " cloud degree automobile changes ordinary ", user is pronounced, and is obtainedThe vocal print feature code of user pronunciation, while obtain the user name of user and login password, and by the user name of the user of acquisition, step onEnter the vocal print feature code associated storage of password and user in memory cell corresponding with information model；When user logins checkingWhen, the text information " cloud degree automobile changes ordinary " corresponding to the voice print database of identification user's input, and the spy of user's vocal printCode is levied, judges user to use information masterplate that " cloud degree automobile, which changes, puts down according to text information " cloud degree automobile change ordinary "It is all ", and the vocal print feature for whether having the vocal print feature code-phase of the user identical is retrieved in memory cell corresponding to information masterplateCode, after condition code is coincide, extract user name corresponding to the vocal print feature code and login password and logined.

In the present embodiment, the voice print database of user is obtained for convenience, and the voice print database is by automobile mounted endThe sound pick-up at end obtains；Memory cell corresponding with each information model is arranged on cloud server；When user logins, lead toThe text information corresponding to automobile mounted terminal recognition user voice print database is crossed, and the voice print database and text information are sent outDeliver to cloud server；And the vocal print feature code of user is extracted from the voice print database by cloud server, and according toWhether received text information determines the memory cell of storage user profile, and retrieve and have and the user from memory cellThe vocal print feature code of matching, if so, then the user is registered users, and extract user name corresponding with the vocal print feature codeAnd login password and logined；If nothing, refuse the user and login.By using the sound pick-up on the car-mounted terminal on automobileTo obtain the voice print database of user, and memory cell corresponding with each information module is established on server beyond the clouds, and passed throughThe text information corresponding to the voice print database of user is identified in car-mounted terminal on automobile, and simultaneously by voice print database and wordInformation is sent to cloud server, extracts the vocal print feature code of user from voice print database by cloud server, and according to instituteThe text information received determines Destination Storage Unit, and retrieves whether have the sound matched with the user from Destination Storage UnitLine condition code, if so, then the user is registered users, then extracts user name and login password and logined；If nothing, the useVerify not by the way that refusal is logined at family.User is facilitated to carry out phonetic entry using the sound pick-up of the car-mounted terminal on automobile, so as to obtainThe voice print database at family is taken, and makes full use of Internet resources etc. quickly to help user to be verified using cloud server.

In the present embodiment, in order to increase the accurate checking of vocal print feature code, the vocal print feature code include acoustic feature,Lexical characteristics and prosodic features.By verifying that acoustic feature (cepstrum) in vocal print feature code and prosodic features (utilize n-The fundamental tone and energy " posture " of gram descriptions), and then make it that the checking of vocal print feature code is more accurate.

In the present embodiment, in order to effectively identify vocal print feature code, the vocal print feature code by comparing the user withWhether the vocal print feature code in Destination Storage Unit, which coincide, specifically includes：Pass through the vocal print feature code and target storage list of the userVocal print feature code in member is compared, when the phase of the vocal print feature code and the vocal print feature code in target storage unit of the userExceed setting value like value, then confirm to coincide, then misfitted less than setting value, in the present embodiment, the setting value is 80%.ByIn reasons such as the influences of various environment, the vocal print feature code of user and the vocal print feature code in target storage unit can not 100%It coincide, by the way that the vocal print feature code of user is compared with the vocal print feature code in Destination Storage Unit, when similar value exceedesSetting value, then confirm to coincide, in the present embodiment, by setting similar value as 80%, then efficiently identify vocal print feature code, andReduce the possibility of mistake.In other embodiments, the setting value may be arranged as other values.

In the present embodiment, in order to increase the extraction correctness of vocal print feature code, the registering unit in user's registration,The vocal print feature code that user is extracted from the voice print database specifically includes：User is obtained more than twice uses identical informationThe voice print database that template is pronounced；Judge in acquired voice print database, whether the similarity of condition code is more than preset value, ifIt is that then vocal print feature code extracts successfully；If it is not, then vocal print feature code extraction failure.Phase is used by obtaining user more than twiceThe voice print database that same information masterplate is pronounced, condition code similarity progress is carried out in the voice print database obtained several times according to thisCompare, when condition code similarity exceedes preset value, then vocal print feature code is extracted successfully, is such as not above preset value, then extraction is lostLose, it is necessary to re-start extraction, and then increase the accuracy of vocal print feature code extraction.

Referring to Fig. 2, quickly logined in user vehicle of another embodiment based on Application on Voiceprint Recognition in device, including it is defaultUnit, registering unit and login unit；

The default unit is used to preset two or more information model, is stored corresponding to respectively each information model distributionUnit, and set the higher limit that each information model is reused；

The registering unit is used in user's registration, obtains the user name of user, logins password and user according to itIn the voice print database that is pronounced of an information model, and extract from the voice print database vocal print feature code of user, and willThe user name, login password and vocal print feature code association store into the memory cell corresponding to described information template；

The unit of logining is used for when user logins, and obtains the voice print database of user, and identification user voice print database institute is rightThe text information answered, and from the voice print database extract user vocal print feature code；And

The memory cell of storage user profile is determined according to the text information, and extract from the memory cell withUser name corresponding to the vocal print feature code-phase and login password and logined.

More than two information models are preset by default unit, and it is single for storage corresponding to the distribution of each information modelMember, by registering unit, in registration, each user's user is pronounced according to one of information model, obtains user'sUser name, password and the vocal print feature code of user are logined, and associated storage is in memory cell corresponding with information model；It is logicalCross and login unit, when user logins checking, identify user input voice print database corresponding to text information and userThe condition code of vocal print, the memory cell of storage user profile is determined according to the text information, and is carried from the memory cellTake out user name corresponding with the vocal print feature code-phase and login password and logined.Above-mentioned technical proposal is by for each informationMemory cell corresponding to template distribution, and the SC service ceiling of each information model is limited, when logining checking, inputted by userVoice print database corresponding to text information, by the range of search of vocal print feature code be locked in corresponding in memory cell, and fromUser name corresponding with the vocal print feature code-phase is extracted in the memory cell and logins password and is logined.Above-mentioned technical sideCase can be logined by the voice print database of user, be manually entered user name and password without user, substantially increase userLogin the convenience of operation with it is intelligent；Also, user profile classification storage substantially reduces the time of vocal print feature code comparison,So that speech recognition can be applied to user and login.

In the present embodiment, the voice print database is obtained by the sound pick-up of automobile mounted terminal；With each information mouldMemory cell is arranged on cloud server corresponding to plate；The unit of logining is when user logins checking, by automobile mountedText information corresponding to terminal recognition user's voice print database, and the voice print database and text information are sent to high in the clouds and takenBusiness device；And the vocal print feature code of user is extracted from the voice print database by cloud server, and according to receivedText information determines the memory cell of storage user profile, and retrieves whether have the vocal print matched with the user from memory cellCondition code, if so, then the user is registered users, and extracts user name corresponding with the vocal print feature code and login closeCode is logined；If nothing, refuse the user and login.User is obtained by using the sound pick-up on the car-mounted terminal on automobileVoice print database, and corresponding with each information module memory cell is established on server beyond the clouds, and pass through the car on automobileMounted terminal is identified the text information corresponding to the voice print database of user, and simultaneously by voice print database and text information send toCloud server, the vocal print feature code of user is extracted from voice print database by cloud server, and according to received textWord information determines Destination Storage Unit, and retrieves whether have the vocal print feature code matched with the user from Destination Storage Unit,If so, then the user is registered users, then extracts user name and login password and logined；If nothing, the user's checking is notBy the way that refusal is logined.User is facilitated to carry out phonetic entry using the sound pick-up of the car-mounted terminal on automobile, so as to obtain user'sVoice print database, and make full use of Internet resources etc. quickly to help user to be verified using cloud server.

In the present embodiment, in order to increase the accurate checking of vocal print feature code, the vocal print feature code include acoustic feature,Lexical characteristics and prosodic features.By verifying that acoustic feature (cepstrum) in vocal print feature code and prosodic features (utilize n-The fundamental tone and energy " posture " of gram descriptions), and then make it that the checking of vocal print feature code is more accurate.

In the present embodiment, in order to effectively identify vocal print feature code, the vocal print feature code by comparing the user withWhether the vocal print feature code in Destination Storage Unit, which coincide, specifically includes：Pass through the vocal print feature code and target storage list of the userVocal print feature code in member is compared, when the phase of the vocal print feature code and the vocal print feature code in target storage unit of the userExceed setting value like value, then confirm to coincide, then misfitted less than setting value.The reasons such as the influence due to various environment, user'sVocal print feature code in vocal print feature code and target storage unit 100% can not coincide, by by the vocal print feature code of user withVocal print feature code in Destination Storage Unit is compared, and when similar value exceedes setting value, then confirmation coincide.In the present embodimentIn, by setting similar value as 80%, then vocal print feature code is efficiently identified, and reduce the possibility of mistake.

In the present embodiment, in order to increase the extraction correctness of vocal print feature code, the registering unit in user's registration,The vocal print feature code that user is extracted from the voice print database specifically includes：User is obtained more than twice uses identical informationThe voice print database that template is pronounced；Judge in acquired voice print database, whether the similarity of condition code is more than preset value, ifIt is that then vocal print feature code extracts successfully；If it is not, then vocal print feature code extraction failure.Phase is used by obtaining user more than twiceThe voice print database that same information masterplate is pronounced, condition code similarity progress is carried out in the voice print database obtained several times according to thisCompare, when condition code similarity exceedes preset value, then vocal print feature code is extracted successfully, is such as not above preset value, then extraction is lostLose, it is necessary to re-start extraction, and then increase the accuracy of vocal print feature code extraction.

Although the various embodiments described above are described, those skilled in the art once know basic woundThe property made concept, then other change and modification can be made to these embodiments, so embodiments of the invention are the foregoing is only,Not thereby the scope of patent protection of the present invention, every equivalent structure made using description of the invention and accompanying drawing content are limitedOr equivalent flow conversion, or other related technical areas are directly or indirectly used in, similarly it is included in the patent of the present inventionWithin protection domain.

Claims (10)

1. the quick accessing method of a kind of user vehicle based on Application on Voiceprint Recognition, it is characterised in that comprise the following steps：

Default two or more information model, memory cell corresponding to respectively each information model distribution, and set each informationThe higher limit that template is reused；

In user's registration, the user name of user is obtained, password and user is logined and is pronounced according to a wherein information modelVoice print database, and from the voice print database extract user vocal print feature code, and by the user name, login password withAnd vocal print feature code association store into the memory cell corresponding to described information template；

When user logins, the voice print database of user is obtained, identify the text information corresponding to user's voice print database, and from describedThe vocal print feature code of user is extracted in voice print database；

The memory cell of storage user profile is determined according to the text information, and is extracted and the sound from the memory cellThe corresponding user name of line condition code and login password and logined.

2. the quick accessing method of user vehicle according to claim 1, it is characterised in that the voice print database is to pass through vapourThe sound pick-up of car car-mounted terminal obtains；Memory cell corresponding with each information model is arranged on cloud server；

When user logins, by the text information corresponding to automobile mounted terminal recognition user voice print database, and by the soundLine data and text information are sent to cloud server；And

The vocal print feature code of user is extracted from the voice print database by cloud server, and is believed according to received wordBreath determines the memory cell of storage user profile, and retrieves whether have the vocal print feature matched with the user from memory cellCode, if so, then the user is registered users, and extracts user name corresponding with the vocal print feature code and logins passwordRow is logined；If nothing, refuse the user and login.

3. the quick accessing method of user vehicle according to claim 1, it is characterised in that the vocal print feature code includes soundLearn feature and prosodic features.

4. the quick accessing method of user vehicle according to claim 1, it is characterised in that described from the memory cellExtract user name corresponding with the vocal print feature code-phase and login password and login specifically including：

The vocal print feature code of the user is compared with the vocal print feature code in storage element, when the vocal print feature code of the userWhen exceeding setting value with the similar value of the vocal print feature code in storage element, extract in memory cell corresponding to vocal print feature codeUser name and login password, and using the user name and login password and logined.

5. the quick accessing method of user vehicle according to claim 1, it is characterised in that in user's registration, it is described fromThe vocal print feature code that user is extracted in the voice print database specifically includes step：

The voice print database that user is pronounced using identical information template is obtained more than twice；

Judge in acquired voice print database, whether the similarity of condition code is more than preset value, if so, then vocal print feature code extractsSuccess；If it is not, then vocal print feature code extraction failure.

6. a kind of user vehicle based on Application on Voiceprint Recognition quickly logins device, it is characterised in that including default unit, registering unitAnd login unit；

The default unit is used to preset two or more information model, and storage corresponding to respectively each information model distribution is singleMember, and set the higher limit that each information model is reused；

The registering unit is used in user's registration, obtains the user name of user, logins password and user according to wherein oneThe voice print database that information model is pronounced, and from the voice print database extract user vocal print feature code, and will described inUser name, login password and vocal print feature code association store into the memory cell corresponding to described information template；

The unit of logining is used for when user logins, and obtains the voice print database of user, identifies corresponding to user's voice print databaseText information, and from the voice print database extract user vocal print feature code；And

The memory cell of storage user profile is determined according to the text information, and is extracted and the sound from the memory cellThe corresponding user name of line condition code and login password and logined.

7. user vehicle according to claim 6 quickly logins device, it is characterised in that the voice print database is to pass through vapourThe sound pick-up of car car-mounted terminal obtains；Memory cell corresponding with each information model is arranged on cloud server；

The unit of logining passes through the word corresponding to automobile mounted terminal recognition user voice print database when user logins checkingInformation, and the voice print database and text information are sent to cloud server；And

The vocal print feature code of user is extracted from the voice print database by cloud server, and is believed according to received wordBreath determines the memory cell of storage user profile, and retrieves whether have the vocal print feature matched with the user from memory cellCode, if so, then the user is registered users, and extracts user name corresponding with the vocal print feature code and logins passwordRow is logined；If nothing, refuse the user and login.

8. user vehicle according to claim 6 quickly logins device, it is characterised in that the vocal print feature code includes soundLearn feature and prosodic features.

9. user vehicle according to claim 6 quickly logins device, it is characterised in that the unit of logining is deposited from describedUser name corresponding with the vocal print feature code-phase is extracted in storage unit and logins password and login specifically including：

The vocal print feature code of the user is compared with the vocal print feature code in storage element, when the vocal print feature code of the userWhen exceeding setting value with the similar value of the vocal print feature code in storage element, extract in memory cell corresponding to vocal print feature codeUser name and login password, and using the user name and login password and logined.

10. user vehicle according to claim 6 quickly logins device, it is characterised in that the registering unit is in userDuring registration, the vocal print feature code that user is extracted from the voice print database specifically includes：

The voice print database that user is pronounced using identical information template is obtained more than twice；

Judge in acquired voice print database, whether the similarity of condition code is more than preset value, if so, then vocal print feature code extractsSuccess；If it is not, then vocal print feature code extraction failure.