CN110111794A - Starting method, apparatus, computer equipment and the storage medium of application program - Google Patents
Starting method, apparatus, computer equipment and the storage medium of application program Download PDFInfo
- Publication number
- CN110111794A CN110111794A CN201910305309.4A CN201910305309A CN110111794A CN 110111794 A CN110111794 A CN 110111794A CN 201910305309 A CN201910305309 A CN 201910305309A CN 110111794 A CN110111794 A CN 110111794A
- Authority
- CN
- China
- Prior art keywords
- request
- voice
- application
- vocal print
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000001755 vocal effect Effects 0.000 claims abstract description 155
- 238000001228 spectrum Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 17
- 239000007858 starting material Substances 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000000977 initiatory effect Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 abstract description 12
- 230000006870 function Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
- G06F21/12—Protecting executable software
- G06F21/121—Restricting unauthorised execution of programs
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of starting methods of application program, device, computer equipment and storage medium, this method comprises: when receiving opening request, voice is requested by acquisition, and denoising is carried out to request voice, obtain voice to be identified, Application on Voiceprint Recognition is carried out to voice to be identified, obtain request vocal print, and judge to request whether to match between vocal print and legal vocal print, if, speech recognition then is carried out to voice to be identified, obtain request text, if request text matches with default starting text, then starting request is sent to start destination application to server, it realizes through vocal print verification in such a way that voice content verification combines, when verification passes through for vocal print verification and voice content verification, just starting belongs to the destination application of privacy application, to improve the safety of starting privacy application, raising pair The safety of the privacy information of the legitimate user of destination application.
Description
Technical field
The present invention relates to field of speech recognition more particularly to starting method, apparatus, the computer equipments of a kind of application program
And storage medium.
Background technique
Currently, user is increasingly not intended in the smart machine of oneself as user increasingly payes attention to individual privacy
Some application programs comprising individual privacy are started by other users, it will usually hide by way of by this kind of application program into
Row is hidden.
But in conventional methods where, usually according to the normal flow of starting application program, other users can also be easy to
Found in smart machine and open this kind of hiding application program individual subscriber privacy is caused to be leaked, cause starting to be applied
The safety of program is low.
Therefore, a kind of starting method for finding safe application program becomes asking for those skilled in the art's urgent need to resolve
Topic.
Summary of the invention
The embodiment of the present invention provides starting method, apparatus, computer equipment and the storage medium of a kind of application program, with solution
The safety of certainly currently active application program is low, can not effective protection privacy of user the problem of.
A kind of starting method of application program, comprising:
If the opening for destination application for receiving requesting party's initiation is requested, the destination application is obtained
Application attribute, if the application attribute is privacy application, acquisition is used to open the request of the destination application
The request voice of side；
Denoising is carried out to the request voice using preset speech de-noising method, obtains voice to be identified；
Application on Voiceprint Recognition is carried out to the voice to be identified using preset Application on Voiceprint Recognition model, obtains the request voice pair
The request vocal print answered；
Judge the request vocal print and prestore for start between the legal vocal print of the destination application whether
Match；
When the request vocal print and the legal voice print matching, using preset speech recognition tools to described to be identified
Voice carries out speech recognition, obtains the corresponding request text of the request voice；
If the request text default starting text corresponding with the destination application matches, start the mesh
Mark application program.
A kind of starter of application program, comprising:
Request receiving module is opened, if the opening for destination application for receiving requesting party's initiation is requested,
The application attribute of the destination application is then obtained, if the application attribute is privacy application, acquisition is used to open described
The request voice of the requesting party of destination application；
Speech de-noising module is obtained for carrying out denoising to the request voice using preset speech de-noising method
To voice to be identified；
Voiceprint identification module, for carrying out Application on Voiceprint Recognition to the voice to be identified using preset Application on Voiceprint Recognition model,
Obtain the corresponding request vocal print of the request voice；
Voice print matching module, for judging the request vocal print and prestoring for starting the conjunction of the destination application
Whether matched between method vocal print；
Speech recognition module, for being known using preset voice when the request vocal print and the legal voice print matching
Other tool carries out speech recognition to the voice to be identified, obtains the corresponding request text of the request voice；
Application program launching module, if for the request text default starting text corresponding with the destination application
Originally match, then start the destination application.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize the starting method of above-mentioned application program when executing the computer program
The step of.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the step of starting method of above-mentioned application program when being executed by processor.
In the starting method, apparatus of above-mentioned application program, computer equipment and storage medium, when client receives request
When requesting the opening for the destination application for belonging to privacy application of Fang Faqi, by acquiring the request voice of requesting party, and
Denoising is carried out to request voice, obtains voice to be identified, Application on Voiceprint Recognition is carried out to voice to be identified, obtains request vocal print,
And judge to request whether to match between vocal print and legal vocal print, when requesting vocal print and legal voice print matching, just to language to be identified
Sound carries out speech recognition, obtains request text, starts destination application, effective protection mesh so as to avoid other illegal users
The privacy information of the legitimate user of application program is marked, if request text matches with default starting text, to target application journey
The server of sequence sends starting request to start destination application, realizes and is mutually tied by vocal print verification and voice content verification
The mode of conjunction, when vocal print verification and voice content verification verify when passing through, just starting belongs to the target application journey of privacy application
Sequence improves the privacy information to the legitimate user of destination application to improve the safety for starting this kind of privacy application
Safety.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of the starting method of application program in one embodiment of the invention；
Fig. 2 is a flow chart of the starting method of application program in one embodiment of the invention；
Fig. 3 is a flow chart of step S60 in the starting method of application program in one embodiment of the invention；
Fig. 4 is a flow chart of step S20 in the starting method of application program in one embodiment of the invention；
Fig. 5 is a flow chart of step S30 in the starting method of application program in one embodiment of the invention；
Fig. 6 is a flow chart of step S40 in the starting method of application program in one embodiment of the invention；
Fig. 7 is a schematic diagram of the starter of application program in one embodiment of the invention；
Fig. 8 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
The starting method of application program provided by the present application, can be using in the application environment such as Fig. 1, which includes
Server-side and client, wherein client is communicated by cable network or wireless network with server-side.Wherein, client
It can be, but not limited to various personal computers, laptop, smart phone, tablet computer and portable wearable device.Clothes
Business end can be realized with the server-side cluster of the either multiple server-side compositions of independent server-side.Client is asked for receiving
Voice is sought, and carries out vocal print and voice content identification, the starting request that server-side is used to receive and customer in response end is sent, and it is right
Starting request carries out legitimacy verifies.
In one embodiment, it as shown in Fig. 2, providing a kind of starting method of application program, applies in Fig. 1 in this way
Client, for be illustrated, include the following steps:
If S10, the opening for destination application for receiving requesting party's initiation are requested, destination application is obtained
Application attribute, if application attribute be privacy application, acquisition be used to open destination application requesting party request voice.
In the present embodiment, requesting party is the natural person that destination application is opened in request, for example requesting party is to be
" Zhang San ".Destination application is the application program being successfully mounted in client.
Opening request is to be used to open the request of destination application, and opening request can be for destination application
The suspension button of clicking operation or the acquisition system to triggering collection request voice.
Specifically, if the opening for destination application that client receives requesting party's initiation is requested, obtaining should
The application attribute of destination application, the application attribute is for identifying whether the destination application belongs to privacy application.It can be with
Understand, the user of client can preset the application attribute of destination application, such as by by target application journey
Sequence is hidden, then the application attribute of the destination application is arranged to privacy application.
If the application attribute of destination application is privacy application, acquisition is used to open the request of the destination application
The request voice of side；If the application attribute is not privacy application, the requesting party for being used to open the destination application is not acquired
Request voice, while to the server-side of the destination application send for the destination application starting request so that
The server-side is obtained the starting is requested to carry out legitimacy verifies.
Preferably, which is the voice for requesting the opening destination application.
For example, requesting party clicks the button of a suspension, at this time Huawei's awn of wheat on the desktop of 5 smart phone of Huawei's awn of wheat
5 smart phones are received requests for the opening that destination application is " wechat ", then obtains the application attribute for being somebody's turn to do " wechat ", if
The application attribute is privacy application, then acquisition is used to open the request voice of the requesting party of " wechat ", for example request voice can
Think " Li Si opens wechat ", if the application attribute is not privacy application, does not acquire the requesting party for being used to open " wechat "
Request voice, while to the server-side of " wechat " send for " wechat " starting request so that the server-side opens this
Dynamic request carries out legitimacy verifies.
It should be noted that client can be smart phone or tablet computer, client, destination application, application
The particular content of attribute and request voice, can be set, herein with no restrictions according to practical application.
S20, denoising is carried out to request voice using preset speech de-noising method, obtains voice to be identified.
In the present embodiment, preset speech de-noising method can be the denoising methods such as filtering method or dividing method.
Specifically, there are noise or noises etc., such as request language for the request voice for the requesting party that usual client receives
There are noises for sound, so needing to carry out denoising to request voice using preset speech de-noising method, to obtain smooth
Pure voice to be identified, for example preemphasis processing is carried out to request voice using preemphasis filter, thus after obtaining filtering
Smooth voice to be identified.
It should be noted that the particular content of preset speech de-noising method, can be set according to practical application, this
Place is with no restrictions.
S30, Application on Voiceprint Recognition is carried out to voice to be identified using preset Application on Voiceprint Recognition model, it is corresponding obtains request voice
Request vocal print.
In the present embodiment, request vocal print be requesting party sound vocal print, wherein the request vocal print unique identification this ask
The sound for the side of asking, vocal print refer to the sound wave spectrum for the carrying verbal information that electricity consumption acoustic instrument is shown.
Specifically, Application on Voiceprint Recognition is carried out to voice to be identified using preset Application on Voiceprint Recognition model, obtains request voice pair
The request vocal print answered, for example Application on Voiceprint Recognition is carried out to voice to be identified using PLDA model, obtain the corresponding request of request voice
Vocal print, wherein the full name in English of PLDA is Probabilistic Linear Discriminant Analysis, refers to one kind
Channel compensation algorithm.
It should be noted that the particular content of preset Application on Voiceprint Recognition model, can be set according to practical application, this
Place is with no restrictions.
S40, judge to request whether to match between vocal print and the legal vocal print for starting destination application prestored.
In the present embodiment, legal vocal print is the vocal print for the sound that unique identification is used to start the destination application,
In, everyone vocal print is all different namely everyone sound is all different, it can thus be understood that only legitimate user
Sound could start the destination application, and legitimate user usually can be set to the user for possessing the client.It is understood that
, legal vocal print is pre-existing to be stored in voice print database, in the state that can be called at any time.
Specifically, the storage road for starting the legal vocal print of the destination application is obtained first in voice print database
Then diameter extracts the legal vocal print, the request sound of the requesting party identified in last judgment step S30 according to the store path
Whether matched between line and the legal vocal print extracted namely judgment step S30 in the request vocal print of requesting party that identifies with
It is whether consistent between the legal vocal print extracted.
For example, it is assumed that the voice print database is MySQL database, for starting the legal vocal print of the destination application
Store path be " C: Program Files MySQL MySQL Server 5.0 data ", then first in the MySQL data
In library obtain " C: Program Files MySQL MySQL Server5.0 data ", then according to should " C: Program
Files MySQL MySQL Server 5.0 data " extract the legal vocal print, identified in last judgment step S30 should
Whether matched between the request vocal print of requesting party and the legal vocal print extracted.
It should be noted that the voice print database can be SQL database or oracle database etc., the voice print database
Particular content, can be set according to practical application, herein with no restrictions.
S50, when requesting vocal print and when legal voice print matching, carried out using preset speech recognition tools to voice to be identified
Speech recognition obtains the corresponding request text of request voice.
Specifically, when the legal vocal print got in the request vocal print of the requesting party identified in step S30 and step S40
When matching, namely when the legal vocal print got in the request vocal print and step S40 of the requesting party identified in step S30 is consistent
When, speech recognition is carried out to voice to be identified using preset speech recognition tools, obtains the corresponding request text of request voice,
For example fly identification facility to voice to be identified progress speech recognition using interrogating, obtain the corresponding request text of request voice.Wherein,
Interrogate the tool for speech recognition for flying that identification facility is the research and development of a Iflytek limited liability company.
It should be noted that the particular content of preset speech recognition tools, can be set according to practical application, this
Place is with no restrictions.
Further, when the legal sound got in the request vocal print of the requesting party identified in step S30 and step S40
When line mismatches, that is, when the legal sound got in the request vocal print and step S40 of the requesting party identified in step S30
When line is inconsistent, client does not send the starting request for the destination application to the server of the destination application,
Client exports the miscue information that the requesting party is illegal user simultaneously, wherein starting request is client to the target
The request for being used to start the destination application that the server of application program is sent, illegal user, which refers to, is not belonging to legitimate user
Natural person, miscue information can for " hello, it is non-I operate, please re-enter " etc..
It should be noted that the particular content of miscue information, can be set according to practical application, not done herein
Limitation.
If S60, request text default starting text corresponding with destination application match, start target application journey
Sequence.
In the present embodiment, presetting starting text is to pre-set for starting the corresponding text of the destination application
This, for example default starting text is " Zhang San opens wechat ".
Specifically, if request text default starting text phase corresponding with the destination application obtained in step S50
Matching, that is, if request text default starting text corresponding with the destination application obtained in step S50 is consistent,
Then client terminal start-up destination application.
Further, if request text default starting text corresponding with the destination application obtained in step S50
It mismatches, that is, if request text default starting text corresponding with the destination application obtained in step S50 is mutually different
Cause, then client output is about content miscue information, content miscue information can for " content that you input is wrong,
Please re-enter " etc..
It should be noted that the particular content of the content miscue information, can be set according to practical application, this
Place is with no restrictions.
In the corresponding embodiment of Fig. 2, S10 to step S60, is initiated when client receives requesting party through the above steps
When requesting the opening for the destination application for belonging to privacy application, by acquiring the request voice of requesting party, and to request
Voice carries out denoising, obtains voice to be identified, carries out Application on Voiceprint Recognition to voice to be identified, obtains request vocal print, and judge
Whether match between request vocal print and legal vocal print, when requesting vocal print and legal voice print matching, just voice to be identified is carried out
Speech recognition, obtains request text, starts destination application, effective protection target application so as to avoid other illegal users
The privacy information of the legitimate user of program, if request text matches with default starting text, to the clothes of destination application
Device transmission starting request be engaged in start destination application, realizes and the side combined is verified with voice content by vocal print verification
Formula, when vocal print verification and voice content verification verify when passing through, just starting belongs to the destination application of privacy application, thus
The safety for starting this kind of privacy application is improved, the safety of the privacy information to the legitimate user of destination application is improved
Property.
In one embodiment, the title and target keywords that starting text includes destination application are preset, wherein
Target keywords are the keyword for starting destination application.
Further, as shown in figure 3, step S60, even request text default starting text corresponding with destination application
Originally match, start destination application, specifically comprise the following steps:
S601, the title that destination application is inquired in request text whether there is.
Specifically, the title that the destination application is inquired in the request text that step S60 is identified whether there is,
Such as, it is assumed that the request text that step S60 is identified is " Li Ming please opens wechat at once ", the title of the destination application
For " wechat ", then inquiry " wechat " whether there is in " Li Ming please opens wechat " at once.
S602, when request text in inquire the title of destination application in the presence of, request text in inquire mesh
Mark keyword whether there is.
Specifically, in the presence of inquiring the title of the destination application in the request text that step S50 is identified,
Target keywords are inquired in the request text that step S50 is identified whether there is, wherein target keywords are for starting this
Destination application and the keyword being specially arranged, such as " name+movement ", " name+movement " can be " Zhang San's starting " etc..
In the absence of inquiring the title of the destination application in the request text that step S50 is identified, the request text is determined
Default starting text corresponding with the destination application does not match that.
It should be noted that the particular content of target keywords, can be set according to practical application, not limited herein
System.
S603, in the presence of inquiring target keywords in requesting text, determine request text and default starting text
Match, and starts destination application.
Specifically, in the presence of inquiring the target keywords in the request text identified in step S50, determining should
Request text default starting text corresponding with the destination application matches, and starts destination application, when in step
In the absence of inquiring the target keywords in the request text that S50 is identified, request text and the target application journey are determined
The corresponding default starting text of sequence does not match that, does not start destination application.
Further, within a preset time period, user is possible to forget the name for the destination application itself hidden
Claim, client inquiry desktop keyword can also whether there is in request text, and desktop keyword is to be used to open hidden table
Face and the keyword being specially arranged, such as desktop keyword can be " please open hiding desktop ".It is inquired when in request text
To in the presence of desktop keyword, open the hiding desktop where the destination application, and show this hide desktop, so as to with
Family, which can understand, is intuitive to see the destination application itself hidden, and then user can be answered using the target is clicked manually
Just start the destination application when client receives clicking operation of the user to the destination application with program,
In the presence of inquiring desktop keyword in requesting text, the hiding desktop where the destination application is not opened, and defeated
The prompt information that desktop opens failure is hidden out.
It should be noted that when requesting text default starting text corresponding with the destination application to match, it can
To start the destination application, while the hiding desktop where the destination application, preset period can also be opened
The particular content that the prompt information of failure is opened with hiding desktop, can be set, herein with no restrictions according to practical application.
In the corresponding embodiment of Fig. 3, S601 to step S603, inquires mesh in request text first through the above steps
The title of mark application program whether there is, if the title for inquiring destination application in request text exists, just carry out
The operation that inquiry target keywords whether there is in request text, if inquiring the title of destination application not in request text
In the presence of then can directly determining that the request text is not matched that with default starting text, so that saving execution should be in request text
The step of middle inquiry target keywords whether there is, improves the efficiency for determining matching result, only when in request text
When the title and target keywords for inquiring destination application all exist simultaneously, the request text and default starting text are just determined
Match, to ensure that the accuracy of matching result.
In one embodiment, as shown in figure 4, step S20, that is, use preset speech de-noising method to request voice
Denoising is carried out, voice to be identified is obtained, specifically comprises the following steps:
S201, preemphasis processing is carried out to request voice using preset preemphasis tool, the request after obtaining preemphasis
Voice.
In the present embodiment, preemphasis processing is a kind of signal compensated in transmitting terminal to input signal high fdrequency component
Processing mode.
Specifically, because the mean power for the request voice signal that client receives is radiated by glottal excitation and mouth and nose etc.
Aspect influences, and causes the high fdrequency component for requesting voice insufficient, in order to enhance the high-frequency signal of the request voice, needs using default
Preemphasis tool preemphasis processing, request voice after obtaining high-resolution preemphasis are carried out to request voice, for example adopt
Preemphasis processing is carried out to request voice with FIB preemphasis filter, the request voice after obtaining high-resolution preemphasis,
In, FIB preemphasis filter is the filter in MATLAB, and the full name in English of MATLAB is matrix laboratory, is referred to
The business mathematics software that MathWorks company, the U.S. produces, MathWorks are that technology advanced in the world calculates and based on model
The software developer and supplier of design.
It should be noted that the particular content of preset preemphasis tool, can be set, herein according to practical application
With no restrictions.
S202, scaling down processing is carried out to the request voice after preemphasis using preset dividing method, after being divided
Request voice.
Specifically, it is generally the case that request voice caused due to the concussion that is motivated by external cycles signal it is unstable,
For example there are aliasing signals for request voice, in order to eliminate the unstable property of the request voice, so needing using preset point
Frequency method carries out scaling down processing to the request voice after preemphasis, so that the request voice after the frequency dividing of short-term stationarity is obtained, than
Scaling down processing is such as carried out to the request voice after preemphasis using blind source separation method, the request after obtaining the frequency dividing of short-term stationarity
Voice, wherein blind source separation method, refers in the case where the theoretical model of signal and source signal can not accurately be known, how from mixed
The method of each source signal is repeatedly isolated in signal.
It should be noted that the particular content of preset dividing method, can be set, herein not according to practical application
It is limited.
S203, windowing process is carried out to the request voice after frequency dividing using preset adding window wscript.exe, after obtaining adding window
Request voice.
Specifically, it is generally the case that the request voice after frequency dividing is the voice of each short section, leads to the request voice
Discontinuously, it in order to guarantee the continuity of the request voice, needs using preset adding window wscript.exe to the request language after frequency dividing
Sound carries out windowing process, the request voice after obtaining continuous adding window, for example uses Hamming Window adding window wscript.exe
Windowing process is carried out to the request voice after frequency dividing, obtains continuous steady request voice, wherein Hamming Window, in
Literary fame is known as hamming window, refers to one of MATLAB adding window tool, the content and step of the MATLAB in this step S203
The content of MATLAB in S201 is consistent, no longer illustrates herein.
S204, silent cent is carried out from place to the request voice after adding window from wscript.exe using preset silent cent
Reason, obtains voice to be identified.
Specifically, usually request voice can be divided into activation phase and quiet period two states, do not transmit and appoint in quiet period
What voice signal is needed using preset silent cent to reject the signal of extra quiet period from request voice from foot
This tool carries out silent sound separating treatment to the request voice after adding window, obtains the voice to be identified for only existing the activation phase, such as
Silent sound separating treatment is carried out to the request voice after adding window using FFMPEG detection audio mute wscript.exe, is only existed
The voice to be identified of activation phase.
It should be noted that preset particular content of the silence cent from wscript.exe, can carry out according to practical application
Setting, herein with no restrictions.
In the corresponding embodiment of Fig. 4, S201 to step S204, pre-processes request voice through the above steps,
Namely preemphasis processing, scaling down processing, windowing process and silent sound separating treatment are carried out to request voice, to ensure that request
High-frequency signal in voice is compensated, and eliminates the uneven stability of request voice, and quiet period extra in voice is requested in removal
Signal, thus guarantee obtained voice to be identified can clearly differentiate with continuous voice, improve the robust of voice to be identified
Property.
In one embodiment, as shown in figure 5, step S30, that is, use preset Application on Voiceprint Recognition model to language to be identified
Sound carries out Application on Voiceprint Recognition, obtains the corresponding request vocal print of request voice, specifically comprises the following steps:
S301, Fast Fourier Transform (FFT) processing is carried out to voice to be identified, obtains the corresponding energy frequency spectrum of request voice.
In the present embodiment, Fast Fourier Transform (FFT) processing is that computer is utilized to calculate discrete Fourier transform (DFT)
Efficiently, the general designation of quick calculation method.
Specifically, objective because the transformation of voice signal in the time domain is difficult to find out the characteristic of signal under normal conditions
Family end needs the voice to be identified obtained to denoising in step S20 to carry out Fast Fourier Transform (FFT) processing, obtains the request
The corresponding energy frequency spectrum of voice, so as to observe the different Energy distribution of the request voice.
S302, energy frequency spectrum is filtered using preset filtering tool, it is corresponding smooth obtains request voice
Frequency spectrum.
Specifically, because there is the high-frequency signal of interference, the height of the interference in the energy frequency spectrum that step S301 is handled
Frequency signal will affect the observation of energy frequency spectrum, so need to be filtered energy frequency spectrum using preset filtering tool,
The corresponding smooth spectrum of request voice is obtained, improves the flatness of energy frequency spectrum, for example use triangle bandpass filter pair
Energy frequency spectrum is filtered, and obtains the corresponding smooth spectrum of request voice, wherein triangle bandpass filter is MATLAB
One of filter, the content of the MATLAB in this step S302 is consistent with the content of MATLAB in step S201, herein
No longer illustrate.
It should be noted that the particular content of preset filtering tool, can be set, herein not according to practical application
It is limited.
S303, cepstrum is carried out to smooth spectrum using preset cepstrum tool, it is corresponding obtains request voice
Request vocal print.
It specifically, is formant by observing the peak value that the energy frequency spectrum is known that in frequency spectrum, which carries
The identification attribute of request sound namely the peak value of the energy frequency spectrum of the requesting party are the request vocal print of the requesting party, in order to mention
The request vocal print is taken out, needs to carry out cepstrum to smooth spectrum using preset cepstrum tool, be asked to obtain this
The corresponding request vocal print of voice is sought, for example, carrying out cepstrum to smooth spectrum using the cepstrum module in MATLAB, is obtained
To the corresponding request vocal print of request voice, wherein the content of the MATLAB in this step S303 and the MATLAB in step S201
Content it is consistent, no longer illustrate herein.
It should be noted that the particular content of preset cepstrum tool, can be set according to practical application, this
Place is with no restrictions.
In the corresponding embodiment of Fig. 5, S301 to step S303, the request voice in time domain is converted through the above steps
For the energy frequency spectrum on clearly intuitive frequency domain, then believed using the high frequency interfered in preset filtering tool removal energy frequency spectrum
Number, ensure that energy frequency spectrum be it is smooth, be distributed so as to the different-energy of more intuitively energy frequency spectrum, it is last because pre-
If cepstrum tool play the role of rapidly and accurately extract vocal print, thus using preset cepstrum tool to smooth frequency
Spectrum carries out cepstrum, can rapidly and accurately obtain the corresponding request vocal print of request voice, therefore improve and extract request sound
The efficiency and accuracy rate of line.
In one embodiment, as shown in fig. 6, step S40, i.e. judgement request vocal print are used to start target with what is prestored
Whether match, specifically comprises the following steps: between the legal vocal print of application program
S401, the vocal print similarity value using cosine similarity algorithm, between computation requests vocal print and legal vocal print.
Specifically, using cosine similarity algorithm, calculate the request vocal print identified in step S30 and the legal vocal print it
Between vocal print similarity value, such as the vocal print similarity value can be 0.8.
Further, request vocal print and legal vocal print are input in following formula, obtain vocal print similarity value:
Wherein, w is vocal print similarity value, xkFor k-th of component for requesting vocal print, ykFor k-th of component of legal vocal print, n
For the quantity for requesting vocal print.
The request vocal print identified in step S30 and the legal vocal print are input in above-mentioned formula, thus automatic quick
Ground calculates vocal print similarity value, improves the efficiency for calculating vocal print similarity value.
If S402, vocal print similarity value are greater than or equal to preset similarity threshold, it is determined that request vocal print and legal sound
Line matching.
Specifically, if the vocal print similarity value being calculated in step S401 is greater than or equal to preset similarity threshold,
Then client determines that the request vocal print matches with the legal vocal print, for example continues to be illustrated in step S401, it is assumed that pre-
If similarity threshold be 0.6, it is clear that 0.8 be greater than 0.6, then client determines that the request vocal print matches with the legal vocal print.
It should be noted that the particular content of preset similarity threshold, can be set, herein according to practical application
With no restrictions.
If S403, vocal print similarity value are less than preset similarity threshold, it is determined that request vocal print and legal vocal print are not
Match.
Specifically, if the vocal print similarity value being calculated in step S401 is less than preset similarity threshold, client
It holds and determines that the request vocal print is not matched that with the legal vocal print, for example continue to be illustrated in step S401, it is assumed that is preset
Similarity threshold is 0.85, it is clear that 0.8 less than 0.85, then client determines that the request vocal print is not matched that with the legal vocal print.
In the corresponding embodiment of Fig. 6, S401 to step S403 through the above steps, because cosine similarity algorithm has
The function of similarity value is accurately calculated, so using cosine similarity algorithm, between computation requests vocal print and legal vocal print
Vocal print similarity value, ensure that calculate vocal print similarity value accuracy, then according to vocal print similarity value and preset phase
It compares like degree threshold value, quickly determines out whether request vocal print matches with legal vocal print automatically, realize matching knot
Fruit automatically analyzes, and improves the efficiency of determining matching result.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of starter of application program, the starter of the application program and above-mentioned reality are provided
The starting method for applying application program in example corresponds.As shown in fig. 7, the starter of the application program includes opening request to connect
It receives module 701, speech de-noising module 702, voiceprint identification module 703, voice print matching module 704, speech recognition module 705 and answers
With program starting module 706.Detailed description are as follows for each functional module:
Request receiving module 701 is opened, if the opening for destination application for receiving requesting party's initiation is asked
It asks, then obtains the application attribute of destination application, if application attribute is privacy application, acquisition is used to open target application journey
The request voice of the requesting party of sequence；
Speech de-noising module 702 is obtained for carrying out denoising to request voice using preset speech de-noising method
Voice to be identified；
Voiceprint identification module 703 is obtained for carrying out Application on Voiceprint Recognition to voice to be identified using preset Application on Voiceprint Recognition model
To the corresponding request vocal print of request voice；
Voice print matching module 704 is requested vocal print and is prestored for starting the legal sound of destination application for judging
Whether matched between line；
Speech recognition module 705 is used for when requesting vocal print and legal voice print matching, using preset speech recognition tools
Speech recognition is carried out to voice to be identified, obtains the corresponding request text of request voice；
Application program launching module 706, if for requesting text default starting text phase corresponding with destination application
Matching, then start destination application.
Further, which includes:
Name query submodule 7061, the title for inquiring destination application in request text whether there is；
Keyword query submodule 7062, for existing when the title for inquiring destination application in request text
When, inquiry target keywords whether there is in request text；
Text matches determining submodule 7063, in the presence of inquire target keywords in requesting text, really
Surely request text matches with default starting text, and starts destination application.
Further, which includes:
Voice preemphasis submodule 7021, for being carried out at preemphasis using preset preemphasis tool to request voice
Reason, the request voice after obtaining preemphasis；
Voice divides submodule 7022, for being divided using preset dividing method to the request voice after preemphasis
Processing, the request voice after being divided；
Voice adding window submodule 7023, for being added using preset adding window wscript.exe to the request voice after frequency dividing
Window processing, the request voice after obtaining adding window；
Speech Separation submodule 7024, for using preset silent cent from wscript.exe to the request voice after adding window
Silent sound separating treatment is carried out, voice to be identified is obtained.
Further, which includes:
Phonetic modification submodule 7031 obtains request language for carrying out Fast Fourier Transform (FFT) processing to voice to be identified
The corresponding energy frequency spectrum of sound；
Voice filter submodule 7032 is obtained for being filtered using preset filtering tool to energy frequency spectrum
Request the corresponding smooth spectrum of voice；
Voice scramble submodule 7033, for carrying out cepstrum to smooth spectrum using preset cepstrum tool,
Obtain the corresponding request vocal print of request voice.
Further, which includes:
Similarity calculation submodule 7041, for using cosine similarity algorithm, computation requests vocal print and legal vocal print it
Between vocal print similarity value；
Voice print matching determines submodule 7042, if being greater than or equal to preset similarity threshold for vocal print similarity value,
Then determine request vocal print and legal voice print matching；
Vocal print, which mismatches, determines submodule 7043, if being less than preset similarity threshold for vocal print similarity value, really
Surely request vocal print and legal vocal print mismatch.
Further, which includes:
It is similar to obtain vocal print for vocal print and legal vocal print will to be requested to be input in following formula for input submodule 70411
Angle value:
Wherein, w is vocal print similarity value, xkFor k-th of component for requesting vocal print, ykFor k-th of component of legal vocal print, n
For the quantity for requesting vocal print.
The specific of starter about application program limits the starting method that may refer to above for application program
Restriction, details are not described herein.Modules in the starter of above-mentioned application program can be fully or partially through software, hard
Part and combinations thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment,
It can also be stored in a software form in the memory in computer equipment, execute the above modules in order to which processor calls
Corresponding operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 8.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external service end by network connection.When the computer program is executed by processor with
Realize a kind of starting method of application program.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize above-described embodiment application program when executing computer program
The step of starting method, such as step S10 shown in Fig. 2 to step S80.Alternatively, processor is realized when executing computer program
The function of each module/unit of the starter of application program in above-described embodiment, such as module 701 shown in Fig. 7 is to module 708
Function.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
The starting method that application program in above method embodiment is realized when machine program is executed by processor, alternatively, the computer program
The function of each module/unit in the starter of application program in above-mentioned apparatus embodiment is realized when being executed by processor.To keep away
Exempt to repeat, which is not described herein again.Those of ordinary skill in the art will appreciate that realizing the whole in above-described embodiment method or portion
Split flow is relevant hardware can be instructed to complete by computer program, and the computer program can be stored in one
In non-volatile computer read/write memory medium, the computer program is when being executed, it may include such as the implementation of above-mentioned each method
The process of example.Wherein, to memory, storage, database or other media used in each embodiment provided herein
Any reference, may each comprise non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory
(ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.It is volatile
Property memory may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM
It is available in many forms, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus
(Rambus) direct RAM (RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram
(RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of starting method of application program, which is characterized in that the starting method of the application program includes:
If the opening for destination application for receiving requesting party's initiation is requested, answering for the destination application is obtained
With attribute, if the application attribute is privacy application, acquisition is used to open the requesting party's of the destination application
Request voice；
Denoising is carried out to the request voice using preset speech de-noising method, obtains voice to be identified；
Application on Voiceprint Recognition is carried out to the voice to be identified using preset Application on Voiceprint Recognition model, it is corresponding to obtain the request voice
Request vocal print；
Judge whether match between the request vocal print and the legal vocal print for starting the destination application prestored；
When the request vocal print and the legal voice print matching, using preset speech recognition tools to the voice to be identified
Speech recognition is carried out, the corresponding request text of the request voice is obtained；
If the request text default starting text corresponding with the destination application matches, starts the target and answer
Use program.
2. the starting method of application program as described in claim 1, which is characterized in that the default starting text includes described
The title and target keywords of destination application, wherein the target keywords are for starting the destination application
Keyword start if the request text default starting text corresponding with the destination application matches
The destination application includes:
Inquire it is described request text in whether include the destination application title；
When including the title of the destination application in the request text, inquire in the request text whether include
The target keywords；
In the presence of inquiring the target keywords in the request text, determine that the request text is opened with described preset
Dynamic text matches, and starts the destination application.
3. the starting method of application program as described in claim 1, which is characterized in that described to use preset speech de-noising side
Method carries out denoising to the request voice, and obtaining voice to be identified includes:
Preemphasis processing is carried out to the request voice using preset preemphasis tool, the request voice after obtaining preemphasis；
Scaling down processing is carried out to the request voice after the preemphasis using preset dividing method, the request language after being divided
Sound；
Windowing process is carried out to the request voice after the frequency dividing using preset adding window wscript.exe, the request after obtaining adding window
Voice；
Silent sound separating treatment is carried out to the request voice after the adding window from wscript.exe using preset silent cent, is obtained
The voice to be identified.
4. the starting method of application program as described in claim 1, which is characterized in that described to use preset Application on Voiceprint Recognition mould
Type carries out Application on Voiceprint Recognition to the voice to be identified, and obtaining the corresponding request vocal print of the request voice includes:
Fast Fourier Transform (FFT) processing is carried out to the voice to be identified, obtains the corresponding energy frequency spectrum of the request voice；
The energy frequency spectrum is filtered using preset filtering tool, obtains the corresponding smooth frequency of the request voice
Spectrum；
Cepstrum is carried out to the smooth spectrum using preset cepstrum tool, obtains that the request voice is corresponding to ask
Seek vocal print.
5. such as the starting method of the described in any item application programs of Claims 1-4, which is characterized in that asked described in the judgement
It asks whether to match between vocal print and the legal vocal print for starting the destination application prestored and includes:
Using cosine similarity algorithm, the vocal print similarity value between the request vocal print and the legal vocal print is calculated；
If the vocal print similarity value be greater than or equal to preset similarity threshold, it is determined that the request vocal print with it is described legal
Voice print matching；
If the vocal print similarity value is less than preset similarity threshold, it is determined that the request vocal print and the legal vocal print are not
Matching.
6. the starting method of application program as described in claim 5, which is characterized in that described to be calculated using cosine similarity
Method, the vocal print similarity value calculated between the request vocal print and the legal vocal print include:
The request vocal print and the legal vocal print are input in following formula, vocal print similarity value is obtained:
Wherein, w is the vocal print similarity value, xkFor k-th of component of the request vocal print, ykFor the kth of the legal vocal print
A component, n are the quantity of the request vocal print.
7. a kind of starter of application program, which is characterized in that the starter of the application program includes:
Request receiving module is opened, if the opening for destination application for receiving requesting party's initiation is requested, is obtained
The application attribute of the destination application is taken, if the application attribute is privacy application, acquisition is used to open the target
The request voice of the requesting party of application program；
Speech de-noising module, for using preset speech de-noising method to the request voice progress denoising, obtain to
Identify voice；
Voiceprint identification module is obtained for carrying out Application on Voiceprint Recognition to the voice to be identified using preset Application on Voiceprint Recognition model
The corresponding request vocal print of the request voice；
Voice print matching module, for judging the request vocal print and prestoring for starting the legal sound of the destination application
Whether matched between line；
Speech recognition module is used for when the request vocal print and the legal voice print matching, using preset speech recognition work
Tool carries out speech recognition to the voice to be identified, obtains the corresponding request text of the request voice；
Application program launching module, if being used for the request text default starting text phase corresponding with the destination application
Matching, then start the destination application.
8. the starter of program the use as claimed in claim 7, which is characterized in that default starting text includes target application
The title and target keywords of program, wherein target keywords are the keyword for starting destination application, application program
Starting module includes:
Name query submodule, for inquire it is described request text in whether include the destination application title；
Keyword query submodule, for inquiring when including the title of the destination application in the request text
It whether include the target keywords in the request text；
Text matches determining submodule, in the presence of inquire the target keywords in the request text, really
The fixed request text matches with the default starting text, and starts the destination application.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The starting method of application program described in any one of 5.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the starting of application program of the realization as described in any one of claims 1 to 5 when the computer program is executed by processor
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305309.4A CN110111794A (en) | 2019-04-16 | 2019-04-16 | Starting method, apparatus, computer equipment and the storage medium of application program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910305309.4A CN110111794A (en) | 2019-04-16 | 2019-04-16 | Starting method, apparatus, computer equipment and the storage medium of application program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110111794A true CN110111794A (en) | 2019-08-09 |
Family
ID=67485509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910305309.4A Pending CN110111794A (en) | 2019-04-16 | 2019-04-16 | Starting method, apparatus, computer equipment and the storage medium of application program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110111794A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112530424A (en) * | 2020-11-23 | 2021-03-19 | 北京小米移动软件有限公司 | Voice processing method and device, electronic equipment and storage medium |
| CN112866938A (en) * | 2020-12-31 | 2021-05-28 | 深圳市康冠商用科技有限公司 | Method and device for opening application program by using wireless equipment, intelligent equipment and storage medium |
| CN113033191A (en) * | 2021-03-30 | 2021-06-25 | 上海思必驰信息科技有限公司 | Voice data processing method, electronic device and computer readable storage medium |
| WO2022262592A1 (en) * | 2021-06-18 | 2022-12-22 | 华为技术有限公司 | Access control method and related apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6107935A (en) * | 1998-02-11 | 2000-08-22 | International Business Machines Corporation | Systems and methods for access filtering employing relaxed recognition constraints |
| CN103391201A (en) * | 2013-08-05 | 2013-11-13 | 公安部第三研究所 | System and method for realizing smart card authentication based on voiceprint recognition |
| CN104937603A (en) * | 2013-01-10 | 2015-09-23 | 日本电气株式会社 | Terminal, unlocking method, and program |
| CN109150538A (en) * | 2018-07-16 | 2019-01-04 | 广州大学 | A kind of fingerprint merges identity identifying method with vocal print |
| CN109192213A (en) * | 2018-08-21 | 2019-01-11 | 平安科技（深圳）有限公司 | The real-time transfer method of court's trial voice, device, computer equipment and storage medium |
| CN109256138A (en) * | 2018-08-13 | 2019-01-22 | 平安科技（深圳）有限公司 | Auth method, terminal device and computer readable storage medium |
| CN109616124A (en) * | 2019-01-25 | 2019-04-12 | 厦门快商通信息咨询有限公司 | Lightweight method for recognizing sound-groove and system based on ivector |
-
2019
- 2019-04-16 CN CN201910305309.4A patent/CN110111794A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6107935A (en) * | 1998-02-11 | 2000-08-22 | International Business Machines Corporation | Systems and methods for access filtering employing relaxed recognition constraints |
| CN104937603A (en) * | 2013-01-10 | 2015-09-23 | 日本电气株式会社 | Terminal, unlocking method, and program |
| CN103391201A (en) * | 2013-08-05 | 2013-11-13 | 公安部第三研究所 | System and method for realizing smart card authentication based on voiceprint recognition |
| CN109150538A (en) * | 2018-07-16 | 2019-01-04 | 广州大学 | A kind of fingerprint merges identity identifying method with vocal print |
| CN109256138A (en) * | 2018-08-13 | 2019-01-22 | 平安科技（深圳）有限公司 | Auth method, terminal device and computer readable storage medium |
| CN109192213A (en) * | 2018-08-21 | 2019-01-11 | 平安科技（深圳）有限公司 | The real-time transfer method of court's trial voice, device, computer equipment and storage medium |
| CN109616124A (en) * | 2019-01-25 | 2019-04-12 | 厦门快商通信息咨询有限公司 | Lightweight method for recognizing sound-groove and system based on ivector |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112530424A (en) * | 2020-11-23 | 2021-03-19 | 北京小米移动软件有限公司 | Voice processing method and device, electronic equipment and storage medium |
| CN112866938A (en) * | 2020-12-31 | 2021-05-28 | 深圳市康冠商用科技有限公司 | Method and device for opening application program by using wireless equipment, intelligent equipment and storage medium |
| CN112866938B (en) * | 2020-12-31 | 2023-06-06 | 深圳市康冠商用科技有限公司 | Method and device for opening application program by using wireless device, intelligent device and storage medium |
| CN113033191A (en) * | 2021-03-30 | 2021-06-25 | 上海思必驰信息科技有限公司 | Voice data processing method, electronic device and computer readable storage medium |
| WO2022262592A1 (en) * | 2021-06-18 | 2022-12-22 | 华为技术有限公司 | Access control method and related apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111794A (en) | Starting method, apparatus, computer equipment and the storage medium of application program | |
| CN110770736B (en) | Exporting dialog-driven applications to a digital communication platform | |
| US11682380B2 (en) | Systems and methods for crowdsourced actions and commands | |
| US9424836B2 (en) | Privacy-sensitive speech model creation via aggregation of multiple user models | |
| US9361878B2 (en) | Computer-readable medium, system and method of providing domain-specific information | |
| US11386886B2 (en) | Adjusting speech recognition using contextual information | |
| WO2020181824A1 (en) | Voiceprint recognition method, apparatus and device, and computer-readable storage medium | |
| WO2018149077A1 (en) | Voiceprint recognition method, device, storage medium, and background server | |
| CN103366740B (en) | Voice command identification method and device | |
| WO2019019256A1 (en) | Electronic apparatus, identity verification method and system, and computer-readable storage medium | |
| US20110320202A1 (en) | Location verification system using sound templates | |
| US11741944B2 (en) | Speech personalization and federated training using real world noise | |
| CN109801635A (en) | A kind of vocal print feature extracting method and device based on attention mechanism | |
| US10535352B2 (en) | Automated cognitive recording and organization of speech as structured text | |
| CN105489221A (en) | Voice recognition method and device | |
| CN103187053A (en) | Input method and electronic equipment | |
| CN109801634A (en) | A kind of fusion method and device of vocal print feature | |
| WO2019232826A1 (en) | I-vector extraction method, speaker recognition method and apparatus, device, and medium | |
| CN102063904A (en) | Melody extraction method and melody recognition system for audio files | |
| CN111640411B (en) | Audio synthesis method, device and computer readable storage medium | |
| KR20150041592A (en) | Method for updating contact information in callee electronic device, and the electronic device | |
| US10224029B2 (en) | Method for using voiceprint identification to operate voice recognition and electronic device thereof | |
| JP2005522720A (en) | Distributed automatic speech recognition method and distributed automatic speech recognition system | |
| Singh et al. | Countermeasures to replay attacks: A review | |
| CN109087647A (en) | Application on Voiceprint Recognition processing method, device, electronic equipment and storage medium |
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 |