CN108231082A - A kind of update method and device of self study Application on Voiceprint Recognition - Google Patents
A kind of update method and device of self study Application on Voiceprint Recognition Download PDFInfo
- Publication number
- CN108231082A CN108231082A CN201711477151.6A CN201711477151A CN108231082A CN 108231082 A CN108231082 A CN 108231082A CN 201711477151 A CN201711477151 A CN 201711477151A CN 108231082 A CN108231082 A CN 108231082A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- print feature
- verified
- voice
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
Abstract
The invention discloses a kind of update methods and device of self study Application on Voiceprint Recognition.In the present invention when user selects to verify, it receives voice to be verified and extracts vocal print feature to be verified, judge that vocal print feature to be verified meets the requirement of preset vocal print evaluation criteria with the time newest matching value for merging vocal print feature, voice print verification passes through, after judging that vocal print feature to be verified meets fusion conditions, using vocal print feature to be verified as material vocal print feature, it is the verification operation that user initiates to ensure the material vocal print feature for meeting fusion conditions, access time newest material vocal print feature is merged to obtain new fusion vocal print feature, access time, newest material vocal print feature obtained new fusion vocal print feature in whole process, access time newest fusion vocal print feature verifies vocal print feature to be verified simultaneously, solves the technical issues of current sound groove recognition technology in e can reduce accuracy because of vocal print drift.
Description
Technical field
The present invention relates to sound groove recognition technology in e field more particularly to a kind of update methods and dress of self study Application on Voiceprint Recognition
It puts.
Background technology
With the development of living things feature recognition, Application on Voiceprint Recognition because of its preferable convenience, stability and higher safety,
There is larger application prospect in fields such as bank, smart home, mobile payments.Application on Voiceprint Recognition, user preset according to system
Rule, register a certain amount of voice, when user need verification when again record verification voice submit to system carry out identity knowledge
Not.
Existing sound groove recognition technology in e is all to carry out disposable registration to vocal print to be used for a long time.But with the change of time
The sound for changing people also has certain variation, and this phenomenon is referred to as vocal print drift, and vocal print drift can influence identification just
True rate.
Therefore, the technical issues of current sound groove recognition technology in e can reduce accuracy because of vocal print drift is resulted in.
Invention content
An embodiment of the present invention provides a kind of update methods and device of self study Application on Voiceprint Recognition, solve current vocal print
The technical issues of identification technology can reduce accuracy because of vocal print drift.
The present invention provides a kind of update method of self study Application on Voiceprint Recognition, including：
S1, verification instruction and voice to be verified are received, vocal print is carried out to the voice to be verified according to the verification instruction
Feature extraction obtains vocal print feature to be verified, and by the time newest first in the vocal print feature to be verified and user's vocal print library
The fusion vocal print feature of preset comparison quantity carries out similarity and compares to obtain the matching value of the first preset comparison quantity；
S2, judge whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, voice print verification passes through simultaneously
The vocal print feature to be verified is added in into self study observation vocal print feature library；
S3, judge the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if
It is no, add in user's vocal print library using the vocal print feature to be verified as new material vocal print feature；
The material vocal print feature of the preset fusion quantity of time newest first merge in S4, selection user's vocal print library
To new fusion vocal print feature.
Preferably, step S2 is specifically included：
Judge whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, voice print verification by and will
The vocal print feature to be verified adds in self study observation vocal print feature library, if it is not, then voice print verification does not pass through.
Preferably, step S3 is specifically included：
Judge the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if it is not,
User's vocal print library is added in using the vocal print feature to be verified as new material vocal print feature, if so, the self study is observed
The vocal print feature to be verified in vocal print feature library removes.
Preferably, step S1 is specifically included：
S11, verification instruction and voice to be verified are received；
Whether S12, the detection voice to be verified meet the requirement of preset voice quality standard, if so, performing step
S13, if it is not, then voice print verification does not pass through；
S13, the voice progress vocal print feature to be verified is extracted to obtain vocal print feature to be verified, and will be described to be verified
Vocal print feature is compared with the vocal print feature progress similarity that merges of the preset comparison quantity of time newest first in user's vocal print library
Obtain the matching value of the first preset comparison quantity.
Preferably, it is further included before step S11：
S01, register instruction is received；
S02, registration voice is received；
Whether S03, the detection registration voice meet preset voice quality standard, if so, step S04 is performed, if it is not,
User is then prompted to continue input registration voice and return to step S02；
The registration vocal print feature of S04, the extraction registration voice, and the registration vocal print feature is added in into user's vocal print
Library；
S05, judge whether the quantity that vocal print feature is registered in user's vocal print library is equal to the second preset fusion quantity, if
It is then to perform step S06, if it is not, user is then prompted to continue input registration voice and return to step S02；
S06, the preset registration vocal print feature for merging quantity of selection second are merged to obtain preset fusion vocal print spy
Sign.
The present invention provides a kind of updating device of self study Application on Voiceprint Recognition, including：
First comparison unit, for receiving verification instruction and voice to be verified, according to the verification instruction to described to be tested
Card voice carries out vocal print feature and extracts to obtain vocal print feature to be verified, and by the vocal print feature to be verified and user's vocal print library
The fusion vocal print feature of first preset comparison quantity carries out similarity and compares to obtain the matching value of the first preset comparison quantity；
First judging unit, for judging whether the matching value meets the requirement of preset vocal print evaluation criteria, if so,
Voice print verification adds in self study observation vocal print feature library by and by the vocal print feature to be verified；
Whether second judgment unit is cancelled or is reported to the verification instruction for judging to receive in preset time
Feedback command, if it is not, adding in user's vocal print library using the vocal print feature to be verified as new material vocal print feature；
First integrated unit, for choosing the material vocal print feature of time newest second preset quantity in user's vocal print library
It is merged to obtain new fusion vocal print feature.
Preferably, the first judging unit specifically includes：
Whether the matching value for judging the first preset comparison quantity meets the requirement of preset vocal print evaluation criteria, if so,
Then voice print verification adds in self study observation vocal print feature library by and by the vocal print feature to be verified, if it is not, then voice print verification
Do not pass through.
Preferably, second judgment unit specifically includes：
For judging the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if
It is no, user's vocal print library is added in using the vocal print feature to be verified as new material vocal print feature, if so, the self study is seen
The vocal print feature to be verified examined in vocal print feature library removes.
Preferably, the first comparison unit specifically includes：
First receiving subelement, for receiving verification instruction and voice to be verified；
First detection sub-unit, for detecting the requirement whether voice to be verified meets preset voice quality standard,
If so, the first contrast subunit of triggering, if it is not, then voice print verification does not pass through；
First contrast subunit is extracted to obtain vocal print spy to be verified for carrying out the voice to be verified vocal print feature
Sign, and by the preset comparison quantity of the vocal print feature to be verified and time newest first in user's vocal print library to merge vocal print special
Sign carries out similarity and compares to obtain the matching value of the first preset comparison quantity.
Preferably, further include voice registering unit；
Second receiving subelement, for receiving register instruction；
Third receiving subelement registers voice for receiving；
Second detection sub-unit, for detecting whether the registration voice meets preset voice quality standard, if so, touching
Hair the first extraction subelement, if it is not, user is then prompted to re-enter registration voice and triggers third receiving subelement；
First extraction subelement, for extracting the registration vocal print feature of the registration voice, and the registration vocal print is special
Sign adds in user's vocal print library；
Third judgment sub-unit, for judging whether the quantity that vocal print feature is registered in user's vocal print library is equal to second
Preset fusion quantity, if so, triggering the second fusion subelement, if it is not, user is then prompted to continue input registration voice and is triggered
Third receiving subelement；
Second fusion subelement, the registration vocal print feature for choosing the second preset fusion quantity are merged to obtain
Preset fusion vocal print feature.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages：
The present invention provides a kind of update method of self study Application on Voiceprint Recognition, including：S1：Receive verification instruction and it is to be verified
Voice carries out the voice to be verified according to the verification instruction vocal print feature and extracts to obtain vocal print feature to be verified, and will
The vocal print feature to be verified is carried out with the vocal print feature that merges of the preset comparison quantity of time newest first in user's vocal print library
Similarity compares to obtain the matching value of the first preset comparison quantity；S2：Judge whether the matching value meets preset vocal print assessment
The requirement of standard, if so, voice print verification adds in self study observation vocal print feature library by and by the vocal print feature to be verified；
S3：Judge the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if it is not, by described in
Vocal print feature to be verified adds in user's vocal print library as new material vocal print feature；S4：It is newest to choose the time in user's vocal print library
First it is preset fusion quantity vocal print feature merged to obtain new fusion vocal print feature.
In the present invention when user selects to verify, receive voice to be verified and extract vocal print feature to be verified, judge to be tested
When card vocal print feature meets the requirement of preset vocal print evaluation criteria with the time newest matching value for merging vocal print feature, vocal print is tested
Card passes through, and vocal print feature to be verified is added in self study observation vocal print feature library, judges not received in preset time to verification
After instructing the feedback command for being cancelled or being reported, vocal print feature to be verified is added in into user's vocal print library, it is ensured that meet fusion item
The material vocal print feature of part is the verification operation that user initiates, and it is special to choose time newest material vocal print in user's vocal print library
Sign is merged to obtain new fusion vocal print feature, and access time newest material vocal print feature obtains new melt in whole process
Vocal print feature is closed, while access time newest fusion vocal print feature verifies vocal print feature to be verified, realizes fusion sound
The update of line feature so that merge vocal print feature match always with user voice, and solving current sound groove recognition technology in e can be because of
The technical issues of vocal print drifts about and reduces accuracy.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow of one embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention
Schematic diagram；
Fig. 2 is a kind of stream of another embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention
Journey schematic diagram；
Fig. 3 is a kind of structure of one embodiment of the updating device of self study Application on Voiceprint Recognition provided in an embodiment of the present invention
Schematic diagram.
Specific embodiment
An embodiment of the present invention provides a kind of update methods and device of self study Application on Voiceprint Recognition, solve vocal print drift shadow
The technical issues of ringing identification accuracy.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, a kind of one embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention,
Including：
Step 101：Verification instruction and voice to be verified are received, vocal print feature is carried out to voice to be verified according to verification instruction
Extraction obtains vocal print feature to be verified, and by the newest first preset comparison of time in vocal print feature to be verified and user's vocal print library
The fusion vocal print feature of quantity carries out similarity and compares to obtain the matching value of the first preset comparison quantity；
It should be noted that user needs to click verification option during verification, after receiving verification instruction and voice to be verified,
Vocal print feature is carried out to voice to be verified to extract to obtain vocal print feature to be verified, will be treated using similarity algorithm according to verification instruction
Verification vocal print feature carries out similarity with the vocal print feature that merges of the preset comparison quantity of time newest first in user's vocal print library
It compares and obtains the matching value of the first preset comparison quantity；
Feature extraction algorithm includes：MFCC algorithms, FBank algorithms and D-vector algorithms etc.；
Similarity algorithm includes：SVM algorithm, Cosine Distance (CDS) algorithm, LDA algorithm and PLDA algorithms etc.；
Suitable vocal print feature and similarity algorithm is selected to be merged and calculated in actual application as needed.
Step 102：Judge whether the matching value of the first preset comparison quantity meets the requirement of preset vocal print evaluation criteria, if
It is that then voice print verification adds in self study observation vocal print feature library by and by vocal print feature to be verified；
It should be noted that judging whether the matching value of the first preset comparison quantity meets wanting for preset vocal print evaluation criteria
It asks, if so, illustrating that the corresponding verification voice of vocal print to be verified is the sound of user, voice print verification is by and by vocal print to be verified
Feature adds in self study observation vocal print feature library；
Preset vocal print evaluation criteria includes：First it is preset comparison quantity matching value average value be more than preset threshold value,
The matching value of 90% the first preset quantity is more than preset threshold value or the matching value of maximum is more than preset threshold value；
Different preset vocal print evaluation criterias can be selected to carry out assessment verification in actual application as needed.
Step 103：Judge the feedback command that verification instruction is cancelled or reported whether is received in preset time, if
It is no, add in user's vocal print library using vocal print feature to be verified as new material vocal print feature；
It should be noted that vocal print feature to be verified is added in after self study observation vocal print feature library, to vocal print to be verified
Feature is observed, and judges the feedback command that verification instruction is cancelled or reported whether is received in preset time, if it is not,
It is the verification operation that user initiates then to illustrate the corresponding verification operation of vocal print feature for meeting condition for study, by sound to be verified
Line feature adds in user's vocal print library as new material vocal print feature；
To meet condition for study vocal print feature to be verified observe ensure be user initiation verification operation, ensure that
The safety and reliability of material vocal print feature if other people are by the vocal print feature of certain means acquisition user, then succeeds
The verification of user mobile phone, the operation that user in time reports this verification after finding, it is ensured that user's vocal print are passed through
The safety and reliability in library.
Step 104：The material vocal print feature for choosing the preset fusion quantity of time newest first in user's vocal print library carries out
Fusion obtains new fusion vocal print feature.
It should be noted that after vocal print feature to be verified adds in user's vocal print library as new material vocal print feature, choosing
The vocal print feature of time upper newest first preset fusion quantity is taken to be merged to obtain new fusion vocal print feature, realizes fusion
The high matching of vocal print feature and user voice；
Vocal print feature blending algorithm includes：Gmm-ubm algorithms, DNN i-vector algorithms and JFA algorithms etc.；
Different vocal print feature blending algorithms can be selected in actual application according to different needs and vocal print feature.
In the present embodiment, when user selects to verify, receive voice to be verified and extract vocal print feature to be verified, judge to treat
When verification vocal print feature meets the requirement of preset vocal print evaluation criteria with the time newest matching value for merging vocal print feature, vocal print
It is verified, vocal print feature to be verified is added in into self study observation vocal print feature library, judges not receiving to testing in preset time
After the feedback command that card instruction is cancelled or reported, vocal print feature to be verified is added in into user's vocal print library, it is ensured that meet fusion
The material vocal print feature of condition is the verification operation that user initiates, and chooses time newest material vocal print in user's vocal print library
Feature is merged to obtain new fusion vocal print feature, and access time newest material vocal print feature obtains new in whole process
Vocal print feature is merged, while access time newest fusion vocal print feature verifies vocal print feature to be verified, realizes fusion
The update of vocal print feature so that merge vocal print feature match always with user voice, solve current sound groove recognition technology in e understand because
The technical issues of reducing accuracy for vocal print drift.
It is above a kind of one embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention, below
For a kind of another embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention.
Referring to Fig. 2, a kind of another implementation of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention
Example, including：
Step 201：Receive register instruction；
It should be noted that when user needs registration, registration option is clicked, register instruction is received and receives register instruction
Into register flow path.
Step 202：Receive registration voice；
It should be noted that registration voice can be by the recording of the sound pick-up outfits such as microphone scene or one section
The speech audio recorded.
Step 203：Whether detection registration voice meets preset voice quality standard, if so, step 204 is performed, if it is not,
Then perform step 205；
It should be noted that whether detection registration voice meets preset voice quality standard, if so, step 204 is performed,
If it is not, then perform step 205；
Preset voice quality standard includes：Preset signal-to-noise ratio standard, preset volume standard and preset effective time standard etc.；
Different preset vocal print evaluation criterias can be selected to carry out assessment verification in actual application as needed.
Step 204：The registration vocal print feature of extraction registration voice, and registration vocal print feature is added in into user's vocal print library；
It should be noted that after detection registration voice meets preset voice quality standard, the registration sound of extraction registration voice
Registration vocal print feature is added in user's vocal print library by line feature；
Feature extraction algorithm includes：MFCC algorithms, FBank algorithms and D-vector algorithms etc..
Step 205：Prompting user continues input registration voice and return to step 202；
It should be noted that when detection registration voice is unsatisfactory for preset voice quality standard, user is prompted to continue input note
Volume voice and return to step 202 continue registration operation.
Step 206：Judge whether the quantity that vocal print feature is registered in user's vocal print library is equal to the second preset fusion quantity, if
It is then to perform step 207, if it is not, then performing step 205；
It should be noted that whether the quantity for judging to register vocal print feature in user's vocal print library meets the second preset fusion number
Amount if so, illustrating that the quantity for registering vocal print feature has met the second preset fusion quantity, performs step 207, if it is not, then holding
Row step 205.
Step 207：The registration vocal print feature for choosing the second preset fusion quantity is merged to obtain preset fusion vocal print spy
Sign；
It should be noted that the registration vocal print feature for choosing the second preset fusion quantity merges to obtain preset fusion vocal print spy
Sign；
Vocal print feature blending algorithm includes：Gmm-ubm algorithms, DNN i-vector algorithms and JFA algorithms etc.；
Different vocal print feature blending algorithms can be selected in actual application according to different needs and vocal print feature.
Step 208：Receive verification instruction and voice to be verified；
It should be noted that user is needed after clicking verification option during verification, verification instruction and voice to be verified are received；
Verification voice can be by the recording of the sound pick-up outfits such as microphone scene or one section of language recorded
Sound audio.
Step 209：Whether meet the requirement of preset voice quality standard according to verification command detection voice to be verified, if
It is then to perform step 210, if it is not, then performing step 211；
It should be noted that whether wanting for preset voice quality standard is met according to verification command detection voice to be verified
It asks, if so, step 210 is performed, if it is not, then performing step 211；
Preset voice quality standard includes：Preset signal-to-noise ratio standard, preset volume standard and preset effective time standard；
Different preset vocal print evaluation criterias can be selected to carry out assessment verification in actual application as needed.
Step 210：Vocal print feature is carried out to voice to be verified and extracts to obtain vocal print feature to be verified, and by vocal print to be verified
Feature compares to obtain with the vocal print feature progress similarity that merges of the preset comparison quantity of time newest first in user's vocal print library
The matching value of first preset comparison quantity；
It should be noted that meet the requirement of preset voice quality standard according to verification command detection voice to be verified, it is right
Voice to be verified carries out vocal print feature and extracts after obtaining vocal print feature to be verified, using similarity algorithm by vocal print feature to be verified
It compares to obtain first with the vocal print feature progress similarity that merges of the preset comparison quantity of time newest first in user's vocal print library
The matching value of preset comparison quantity；
Feature extraction algorithm includes：MFCC algorithms, FBank algorithms and D-vector algorithms etc.；
Similarity algorithm includes：SVM algorithm, Cosine Distance (CDS) algorithm, LDA algorithm and PLDA algorithms etc.；
Suitable vocal print feature and similarity algorithm is selected to be merged and calculated in actual application as needed.
Step 211：Prompting user's voice print verification does not pass through；
It should be noted that the requirement of preset voice quality standard is not met according to verification command detection voice to be verified
When, user's voice print verification is prompted not pass through.
Step 212：Judge whether the matching value of the first preset comparison quantity meets the requirement of preset vocal print evaluation criteria, if
It is then to perform step 213, if it is not, then performing step 211；
It should be noted that it should be noted that judge whether the matching value of the first preset comparison quantity meets preset sound
The requirement of line evaluation criteria if so, illustrating that the corresponding verification voice of vocal print to be verified is the sound of user, performs step 213,
If it is not, then illustrate voice to be verified be possible to be not user sound, voice print verification do not pass through；
Preset vocal print evaluation criteria includes：First it is preset comparison quantity matching value average value be more than preset threshold value,
The matching value of 90% the first preset quantity is more than preset threshold value or the matching value of maximum is more than preset threshold value；
Different preset vocal print evaluation criterias can be selected to carry out assessment verification in actual application as needed.
Step 213：Voice print verification adds in self study observation vocal print feature library by and by vocal print feature to be verified；
It should be noted that voice print verification by while vocal print feature to be verified can be added in self study to observe vocal print special
Levy library.
Step 214：Judge the feedback command that verification instruction is cancelled or reported whether is received in preset time, if
It is no, then step 215 is performed, if so, performing step 216；
It should be noted that judge that the feedback that verification instruction is cancelled or reported whether is received in preset time to be referred to
It enables, if it is not, step 215 is then performed, if so, performing step 216.
Step 215：User's vocal print library is added in using vocal print feature to be verified as new material vocal print feature；
It should be noted that judge not receiving the feedback command that verification instruction is cancelled or reported in preset time
Afterwards, it is the verification operation that user initiates to illustrate the corresponding verification operation of vocal print feature for meeting condition for study, will be to be verified
Vocal print feature adds in user's vocal print library as new material vocal print feature.
Step 216：Vocal print feature to be verified in self study observation vocal print feature library is removed；
It should be noted that judge to have received the feedback command that verification instruction is cancelled or reported in preset time
Afterwards, it is not the verification operation that user initiates to illustrate the corresponding verification operation of vocal print feature for meeting condition for study, will be learnt by oneself
The vocal print feature to be verified practised in observation vocal print feature library removes；
To meet condition for study vocal print feature to be verified observe ensure be user initiation verification operation, ensure that
The safety and reliability of material vocal print feature.
Step 217：The material vocal print feature for choosing the preset fusion quantity of time newest first in user's vocal print library carries out
Fusion obtains new fusion vocal print feature.
It should be noted that after vocal print feature to be verified adds in user's vocal print library as new material vocal print feature, choosing
The vocal print feature of time upper newest first preset fusion quantity is taken to be merged to obtain new fusion vocal print feature, realizes fusion
The high matching of vocal print feature and user voice；
Vocal print feature blending algorithm includes：Gmm-ubm algorithms, DNN i-vector algorithms and JFA algorithms etc.；
Different vocal print feature blending algorithms can be selected in actual application according to different needs and vocal print feature.
In the present embodiment, when user selects to verify, receive voice to be verified and extract vocal print feature to be verified, judge to treat
When verification vocal print feature meets the requirement of preset vocal print evaluation criteria with the time newest matching value for merging vocal print feature, vocal print
It is verified, vocal print feature to be verified is added in into self study observation vocal print feature library, judges not receiving to testing in preset time
After the feedback command that card instruction is cancelled or reported, vocal print feature to be verified is added in into user's vocal print library, it is ensured that meet fusion
The material vocal print feature of condition is the verification operation that user initiates, and chooses time newest material vocal print in user's vocal print library
Feature is merged to obtain new fusion vocal print feature, and access time newest material vocal print feature obtains new in whole process
Vocal print feature is merged, while access time newest fusion vocal print feature verifies vocal print feature to be verified solve and work as
The technical issues of preceding sound groove recognition technology in e can reduce accuracy because of vocal print drift.
It is above a kind of another embodiment of the update method of self study Application on Voiceprint Recognition provided in an embodiment of the present invention, with
It is a kind of one embodiment of the updating device of self study Application on Voiceprint Recognition provided in an embodiment of the present invention down.
First comparison unit 301, for receiving verification instruction and voice to be verified, according to verification instruction to voice to be verified
It carries out vocal print feature and extracts to obtain vocal print feature to be verified, and is preset right by the first of vocal print feature to be verified and user's vocal print library
Fusion vocal print feature progress similarity than quantity compares to obtain the matching value of the first preset comparison quantity；
Whether the first judging unit 302, the matching value for judging the first preset comparison quantity meet preset vocal print assessment
The requirement of standard, if so, voice print verification adds in self study observation vocal print feature library by and by vocal print feature to be verified；
Whether second judgment unit 303 is cancelled or is reported to verification instruction for judging to receive in preset time
Feedback command, if it is not, adding in user's vocal print library using vocal print feature to be verified as new material vocal print feature；
First integrated unit 304, for choosing the material vocal print of time newest second preset quantity in user's vocal print library
Feature is merged to obtain new fusion vocal print feature.
Further, the first judging unit 302 specifically includes：
Whether the matching value for judging the first preset comparison quantity meets the requirement of preset vocal print evaluation criteria, if so,
Then voice print verification adds in self study observation vocal print feature library by and by vocal print feature to be verified, if it is not, then voice print verification is obstructed
It crosses.
Further, second judgment unit 303 specifically includes：
For judging the feedback command that verification instruction is cancelled or reported whether is received in preset time, if it is not,
User's vocal print library is added in using vocal print feature to be verified as new material vocal print feature, if so, self study is observed vocal print feature
Vocal print feature to be verified in library removes.
Further, first comparison Unit 301 specifically include：
First receiving subelement 3011, for receiving verification instruction and voice to be verified；
First detection sub-unit 3012, for detecting the requirement whether voice to be verified meets preset voice quality standard,
If so, the first contrast subunit 3013 of triggering, if it is not, then voice print verification does not pass through；
First contrast subunit 3013 is extracted to obtain vocal print spy to be verified for carrying out voice to be verified vocal print feature
Sign, and by vocal print feature to be verified and the time newest first in user's vocal print library it is preset compare quantity merge vocal print feature into
Row similarity compares to obtain the matching value of the first preset comparison quantity.
Further, voice registering unit 300 is further included；
Second receiving subelement 3001, for receiving register instruction；
Third receiving subelement 3002 registers voice for receiving；
Second detection sub-unit 3003, for detecting whether registration voice meets preset voice quality standard, if so, touching
Hair the first extraction subelement, if it is not, user is then prompted to re-enter registration voice and triggers third receiving subelement 3002；
First extraction subelement 3004 for extracting the registration vocal print feature of registration voice, and registration vocal print feature is added
Access customer vocal print library；
Third judgment sub-unit 3005, for judging whether the quantity that vocal print feature is registered in user's vocal print library is equal to second
Preset fusion quantity, if so, triggering the second fusion subelement, if it is not, user is then prompted to re-enter registration voice and is triggered
Third receiving subelement 3002；
Second fusion subelement 3006, the registration vocal print feature for choosing the second preset fusion quantity merge to obtain preset
Merge vocal print feature.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those of ordinary skill in the art that：It still can be to preceding
The technical solution recorded in each embodiment is stated to modify or carry out equivalent replacement to which part technical characteristic；And these
Modification is replaced, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and module can refer to the corresponding process in preceding method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the division of module,
Only a kind of division of logic function, can there is an other dividing mode in actual implementation, such as multiple module or components can be with
With reference to or be desirably integrated into another system or some features can be ignored or does not perform.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of device or module or
Communication connection can be electrical, machinery or other forms.
The module illustrated as separating component may or may not be physically separate, be shown as module
Component may or may not be physical module, you can be located at a place or can also be distributed to multiple networks
In module.Some or all of module therein can be selected according to the actual needs to realize the purpose of this embodiment scheme.
In addition, each function module in each embodiment of the present invention can be integrated in a processing module, it can also
That modules are individually physically present, can also two or more modules be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.
If integrated module realized in the form of software function module and be independent product sale or in use, can
To be stored in a computer read/write memory medium.Based on such understanding, technical scheme of the present invention substantially or
Saying all or part of the part contribute to the prior art or the technical solution can be embodied in the form of software product
Out, which is stored in a storage medium, is used including some instructions so that a computer equipment
(can be personal computer, server or the network equipment etc.) performs all or part of each embodiment method of the present invention
Step.And aforementioned storage medium includes：It is USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic disc or CD
Matter.
Claims (10)
1. a kind of update method of self study Application on Voiceprint Recognition, which is characterized in that including：
S1, verification instruction and voice to be verified are received, vocal print feature is carried out to the voice to be verified according to the verification instruction
Extraction obtains vocal print feature to be verified, and the vocal print feature to be verified and time newest first in user's vocal print library is preset
The fusion vocal print feature of comparison quantity carries out similarity and compares to obtain the matching value of the first preset comparison quantity；
S2, judge whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, voice print verification is by and by institute
It states vocal print feature to be verified and adds in self study observation vocal print feature library；
S3, judge the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if it is not, will
The vocal print feature to be verified adds in user's vocal print library as new material vocal print feature；
The material vocal print feature of the preset fusion quantity of time newest first is merged to obtain new in S4, selection user's vocal print library
Fusion vocal print feature.
2. the update method of a kind of self study Application on Voiceprint Recognition according to claim 1, which is characterized in that step S2 is specifically wrapped
It includes：
Judge whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, voice print verification by and will described in
Vocal print feature to be verified adds in self study observation vocal print feature library, if it is not, then voice print verification does not pass through.
3. the update method of a kind of self study Application on Voiceprint Recognition according to claim 1, which is characterized in that step S3 is specifically wrapped
It includes：
Judge the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if it is not, by institute
It states vocal print feature to be verified and adds in user's vocal print library as new material vocal print feature, if so, the self study is observed vocal print
The vocal print feature to be verified in feature database removes.
4. the update method of a kind of self study Application on Voiceprint Recognition according to claim 1, which is characterized in that step S1 is specifically wrapped
It includes：
S11, verification instruction and voice to be verified are received；
Whether S12, the detection voice to be verified meet the requirement of preset voice quality standard, if so, step S13 is performed,
If it is not, then voice print verification does not pass through；
S13, it vocal print feature is carried out to the voice to be verified extracts to obtain vocal print feature to be verified, and by the vocal print to be verified
Feature compares to obtain with the vocal print feature progress similarity that merges of the preset comparison quantity of time newest first in user's vocal print library
The matching value of first preset comparison quantity.
5. the update method of a kind of self study Application on Voiceprint Recognition according to claim 4, which is characterized in that before step S11
It further includes：
S01, register instruction is received；
S02, registration voice is received；
Whether S03, the detection registration voice meet preset voice quality standard, if so, step S04 is performed, if it is not, then carrying
Show that user continues input registration voice and return to step S02；
The registration vocal print feature of S04, the extraction registration voice, and the registration vocal print feature is added in into user's vocal print library；
S05, judge whether the quantity that vocal print feature is registered in user's vocal print library is equal to the second preset fusion quantity, if so,
Step S06 is then performed, if it is not, user is then prompted to continue input registration voice and return to step S02；
S06, the preset registration vocal print feature for merging quantity of selection second are merged to obtain preset fusion vocal print feature.
6. a kind of updating device of self study Application on Voiceprint Recognition, which is characterized in that including：
First comparison unit, for receiving verification instruction and voice to be verified, according to the verification instruction to the language to be verified
Sound carries out vocal print feature and extracts to obtain vocal print feature to be verified, and by the first of the vocal print feature to be verified and user's vocal print library
The fusion vocal print feature of preset comparison quantity carries out similarity and compares to obtain the matching value of the first preset comparison quantity；
First judging unit, for judging whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, sound
Line is verified and the vocal print feature to be verified is added in self study observation vocal print feature library；
Second judgment unit, for judge whether to receive in preset time to it is described verification instruction cancelled or reported it is anti-
Feedback instruction, if it is not, adding in user's vocal print library using the vocal print feature to be verified as new material vocal print feature；
First integrated unit, for choosing the material vocal print feature of the preset fusion quantity of time newest first in user's vocal print library
It is merged to obtain new fusion vocal print feature.
A kind of 7. updating device of self study Application on Voiceprint Recognition according to claim 6, which is characterized in that the first judging unit
It specifically includes：
For judging whether the matching value meets the requirement of preset vocal print evaluation criteria, if so, voice print verification by and will
The vocal print feature to be verified adds in self study observation vocal print feature library, if it is not, then voice print verification does not pass through.
A kind of 8. updating device of self study Application on Voiceprint Recognition according to claim 6, which is characterized in that second judgment unit
It specifically includes：
For judging the feedback command that the verification instruction is cancelled or reported whether is received in preset time, if it is not,
User's vocal print library is added in using the vocal print feature to be verified as new material vocal print feature, if so, the self study is observed
The vocal print feature to be verified in vocal print feature library removes.
A kind of 9. updating device of self study Application on Voiceprint Recognition according to claim 6, which is characterized in that the first comparison unit
It specifically includes：
First receiving subelement, for receiving verification instruction and voice to be verified；
First detection sub-unit, for detecting the requirement whether voice to be verified meets preset voice quality standard, if so,
The first contrast subunit is then triggered, if it is not, then voice print verification does not pass through；
First contrast subunit is extracted to obtain vocal print feature to be verified for carrying out vocal print feature to the voice to be verified, and
By the vocal print feature to be verified and time newest first in user's vocal print library preset comparison quantity merge vocal print feature into
Row similarity compares to obtain the matching value of the first preset comparison quantity.
10. the updating device of a kind of self study Application on Voiceprint Recognition according to claim 6, which is characterized in that further include voice
Registering unit：
Second receiving subelement, for receiving register instruction；
Third receiving subelement registers voice for receiving；
Second detection sub-unit, for detecting whether the registration voice meets preset voice quality standard, if so, triggering the
One extraction subelement, if it is not, user is then prompted to re-enter registration voice and triggers third receiving subelement；
First extraction subelement for extracting the registration vocal print feature of the registration voice, and the registration vocal print feature is added
Access customer vocal print library；
Third judgment sub-unit, for judging it is preset whether the quantity that vocal print feature is registered in user's vocal print library is equal to second
Quantity is merged, if so, triggering the second fusion subelement, if it is not, user is then prompted to continue input registration voice and triggers third
Receiving subelement；
Second fusion subelement, the registration vocal print feature for choosing the second preset fusion quantity are merged to obtain preset
Merge vocal print feature.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711477151.6A CN108231082A (en) | 2017-12-29 | 2017-12-29 | A kind of update method and device of self study Application on Voiceprint Recognition |
| PCT/CN2018/077535 WO2019127897A1 (en) | 2017-12-29 | 2018-02-28 | Updating method and device for self-learning voiceprint recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711477151.6A CN108231082A (en) | 2017-12-29 | 2017-12-29 | A kind of update method and device of self study Application on Voiceprint Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108231082A true CN108231082A (en) | 2018-06-29 |
Family
ID=62647095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711477151.6A Pending CN108231082A (en) | 2017-12-29 | 2017-12-29 | A kind of update method and device of self study Application on Voiceprint Recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108231082A (en) |
| WO (1) | WO2019127897A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448731A (en) * | 2018-11-20 | 2019-03-08 | 北京网众共创科技有限公司 | Comparison method and device, storage medium, the electronic device of voiceprint |
| CN110491373A (en) * | 2019-08-19 | 2019-11-22 | Oppo广东移动通信有限公司 | Model training method, device, storage medium and electronic equipment |
| CN110600029A (en) * | 2019-09-17 | 2019-12-20 | 苏州思必驰信息科技有限公司 | User-defined awakening method and device for intelligent voice equipment |
| CN110660398A (en) * | 2019-09-19 | 2020-01-07 | 北京三快在线科技有限公司 | Voiceprint feature updating method and device, computer equipment and storage medium |
| WO2020019176A1 (en) * | 2018-07-24 | 2020-01-30 | 华为技术有限公司 | Method for updating wake-up voice of voice assistant by terminal, and terminal |
| CN111063360A (en) * | 2020-01-21 | 2020-04-24 | 北京爱数智慧科技有限公司 | Voiceprint library generation method and device |
| CN111091837A (en) * | 2019-12-27 | 2020-05-01 | 中国人民解放军陆军工程大学 | Time-varying voiceprint authentication method and system based on online learning |
| CN111428576A (en) * | 2020-03-02 | 2020-07-17 | 广州微盾科技股份有限公司 | Characteristic information learning method, electronic device, and storage medium |
| CN112331210A (en) * | 2021-01-05 | 2021-02-05 | 太极计算机股份有限公司 | Speech recognition device |
| CN113327618A (en) * | 2021-05-17 | 2021-08-31 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
| CN113327617A (en) * | 2021-05-17 | 2021-08-31 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
| WO2022236827A1 (en) * | 2021-05-14 | 2022-11-17 | 华为技术有限公司 | Voiceprint management method and apparatus |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113257266B (en) * | 2021-05-21 | 2021-12-24 | 特斯联科技集团有限公司 | Complex environment access control method and device based on voiceprint multi-feature fusion |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130060569A1 (en) * | 2005-07-27 | 2013-03-07 | International Business Machines Corporation | Voice authentication system and method using a removable voice id card |
| WO2014123631A1 (en) * | 2013-02-05 | 2014-08-14 | Visa International Service Association | Speaker verification |
| CN104183240A (en) * | 2014-08-19 | 2014-12-03 | 中国联合网络通信集团有限公司 | Vocal print feature fusion method and device |
| WO2015033121A1 (en) * | 2013-09-05 | 2015-03-12 | Barclays Bank Plc | Biometric verification using predicted signatures |
| CN104424277A (en) * | 2013-08-29 | 2015-03-18 | 深圳市腾讯计算机系统有限公司 | Processing method and device for report information |
| CN104616110A (en) * | 2015-02-10 | 2015-05-13 | 五八同城信息技术有限公司 | Information processing method and device |
| CN105096121A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voiceprint authentication method and device |
| CN106228387A (en) * | 2015-09-16 | 2016-12-14 | 颜陈煜 | The system and method for information accurate transfer is realized based on information retrieval and messages application |
| CN106469553A (en) * | 2015-08-13 | 2017-03-01 | 中兴通讯股份有限公司 | Audio recognition method and device |
| CN106506524A (en) * | 2016-11-30 | 2017-03-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for verifying user |
| CN106506563A (en) * | 2016-12-30 | 2017-03-15 | 中国建设银行股份有限公司 | account setup method, device and bank service system |
| US20170140760A1 (en) * | 2015-11-18 | 2017-05-18 | Uniphore Software Systems | Adaptive voice authentication system and method |
| CN106782564A (en) * | 2016-11-18 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for processing speech data |
| CN106782565A (en) * | 2016-11-29 | 2017-05-31 | 重庆重智机器人研究院有限公司 | A kind of vocal print feature recognition methods and system |
| CN107180632A (en) * | 2017-06-19 | 2017-09-19 | 微鲸科技有限公司 | Sound control method, device and readable storage medium storing program for executing |
| CN107424614A (en) * | 2017-07-17 | 2017-12-01 | 广东讯飞启明科技发展有限公司 | A kind of sound-groove model update method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107331400A (en) * | 2017-08-25 | 2017-11-07 | 百度在线网络技术（北京）有限公司 | A kind of Application on Voiceprint Recognition performance improvement method, device, terminal and storage medium |
-
2017
- 2017-12-29 CN CN201711477151.6A patent/CN108231082A/en active Pending
-
2018
- 2018-02-28 WO PCT/CN2018/077535 patent/WO2019127897A1/en active Application Filing
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130060569A1 (en) * | 2005-07-27 | 2013-03-07 | International Business Machines Corporation | Voice authentication system and method using a removable voice id card |
| WO2014123631A1 (en) * | 2013-02-05 | 2014-08-14 | Visa International Service Association | Speaker verification |
| CN104424277A (en) * | 2013-08-29 | 2015-03-18 | 深圳市腾讯计算机系统有限公司 | Processing method and device for report information |
| WO2015033121A1 (en) * | 2013-09-05 | 2015-03-12 | Barclays Bank Plc | Biometric verification using predicted signatures |
| CN104183240A (en) * | 2014-08-19 | 2014-12-03 | 中国联合网络通信集团有限公司 | Vocal print feature fusion method and device |
| CN104616110A (en) * | 2015-02-10 | 2015-05-13 | 五八同城信息技术有限公司 | Information processing method and device |
| CN105096121A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voiceprint authentication method and device |
| CN106469553A (en) * | 2015-08-13 | 2017-03-01 | 中兴通讯股份有限公司 | Audio recognition method and device |
| CN106228387A (en) * | 2015-09-16 | 2016-12-14 | 颜陈煜 | The system and method for information accurate transfer is realized based on information retrieval and messages application |
| US20170140760A1 (en) * | 2015-11-18 | 2017-05-18 | Uniphore Software Systems | Adaptive voice authentication system and method |
| CN106782564A (en) * | 2016-11-18 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for processing speech data |
| CN106782565A (en) * | 2016-11-29 | 2017-05-31 | 重庆重智机器人研究院有限公司 | A kind of vocal print feature recognition methods and system |
| CN106506524A (en) * | 2016-11-30 | 2017-03-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for verifying user |
| CN106506563A (en) * | 2016-12-30 | 2017-03-15 | 中国建设银行股份有限公司 | account setup method, device and bank service system |
| CN107180632A (en) * | 2017-06-19 | 2017-09-19 | 微鲸科技有限公司 | Sound control method, device and readable storage medium storing program for executing |
| CN107424614A (en) * | 2017-07-17 | 2017-12-01 | 广东讯飞启明科技发展有限公司 | A kind of sound-groove model update method |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020019176A1 (en) * | 2018-07-24 | 2020-01-30 | 华为技术有限公司 | Method for updating wake-up voice of voice assistant by terminal, and terminal |
| CN109448731A (en) * | 2018-11-20 | 2019-03-08 | 北京网众共创科技有限公司 | Comparison method and device, storage medium, the electronic device of voiceprint |
| CN110491373A (en) * | 2019-08-19 | 2019-11-22 | Oppo广东移动通信有限公司 | Model training method, device, storage medium and electronic equipment |
| CN110600029A (en) * | 2019-09-17 | 2019-12-20 | 苏州思必驰信息科技有限公司 | User-defined awakening method and device for intelligent voice equipment |
| CN110660398A (en) * | 2019-09-19 | 2020-01-07 | 北京三快在线科技有限公司 | Voiceprint feature updating method and device, computer equipment and storage medium |
| CN110660398B (en) * | 2019-09-19 | 2020-11-20 | 北京三快在线科技有限公司 | Voiceprint feature updating method and device, computer equipment and storage medium |
| CN111091837A (en) * | 2019-12-27 | 2020-05-01 | 中国人民解放军陆军工程大学 | Time-varying voiceprint authentication method and system based on online learning |
| CN111063360A (en) * | 2020-01-21 | 2020-04-24 | 北京爱数智慧科技有限公司 | Voiceprint library generation method and device |
| CN111063360B (en) * | 2020-01-21 | 2022-08-19 | 北京爱数智慧科技有限公司 | Voiceprint library generation method and device |
| CN111428576A (en) * | 2020-03-02 | 2020-07-17 | 广州微盾科技股份有限公司 | Characteristic information learning method, electronic device, and storage medium |
| CN112331210A (en) * | 2021-01-05 | 2021-02-05 | 太极计算机股份有限公司 | Speech recognition device |
| CN112331210B (en) * | 2021-01-05 | 2021-05-18 | 太极计算机股份有限公司 | Speech recognition device |
| WO2022236827A1 (en) * | 2021-05-14 | 2022-11-17 | 华为技术有限公司 | Voiceprint management method and apparatus |
| CN113327618A (en) * | 2021-05-17 | 2021-08-31 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
| CN113327617A (en) * | 2021-05-17 | 2021-08-31 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019127897A1 (en) | 2019-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108231082A (en) | A kind of update method and device of self study Application on Voiceprint Recognition | |
| US10593334B2 (en) | Method and apparatus for generating voiceprint information comprised of reference pieces each used for authentication | |
| CN107093066B (en) | Service implementation method and device | |
| US11449848B2 (en) | Offline transaction implementation method and apparatus | |
| JP6141388B2 (en) | Voiceprint authentication method and apparatus | |
| WO2017215558A1 (en) | Voiceprint recognition method and device | |
| CN107404381A (en) | A kind of identity identifying method and device | |
| US8886635B2 (en) | Apparatus and method for recognizing content using audio signal | |
| CN104505090B (en) | The audio recognition method and device of sensitive word | |
| CN109450850A (en) | Auth method, device, computer equipment and storage medium | |
| CN110533288A (en) | Business handling process detection method, device, computer equipment and storage medium | |
| Buriro et al. | Itsme: Multi-modal and unobtrusive behavioural user authentication for smartphones | |
| CN107886958A (en) | A kind of express delivery cabinet pickup method and device based on vocal print | |
| CN111898108A (en) | Identity authentication method and device, terminal and server | |
| CN109214820B (en) | Merchant money collection system and method based on audio and video combination | |
| CN109299594B (en) | Identity verification method and device | |
| US8983207B1 (en) | Mitigating replay attacks using multiple-image authentication | |
| EP3582127B1 (en) | Feature information-based user authentication method and device | |
| CN109887187A (en) | A kind of pickup processing method, device, equipment and storage medium | |
| CN108735222B (en) | A kind of vocal print identification method and system based on Application on Voiceprint Recognition | |
| CN111445252A (en) | Method, device and equipment for establishing biological feature library | |
| CN111160928A (en) | Identity verification method and device | |
| CN104486306B (en) | Identity authentication method is carried out based on finger hand vein recognition and cloud service | |
| Beton et al. | Biometric secret path for mobile user authentication: A preliminary study | |
| KR101805437B1 (en) | Speaker verification method using background speaker data and speaker verification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |