CN108418788A - A kind of method of speech verification, server and system - Google Patents
A kind of method of speech verification, server and system Download PDFInfo
- Publication number
- CN108418788A CN108418788A CN201810015295.8A CN201810015295A CN108418788A CN 108418788 A CN108418788 A CN 108418788A CN 201810015295 A CN201810015295 A CN 201810015295A CN 108418788 A CN108418788 A CN 108418788A
- Authority
- CN
- China
- Prior art keywords
- verification
- audio file
- response
- validation
- audio
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
- G11B27/19—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier
- G11B27/28—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier by using information signals recorded by the same method as the main recording
- G11B27/30—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier by using information signals recorded by the same method as the main recording on the same track as the main recording
- G11B27/3027—Indexing; Addressing; Timing or synchronising; Measuring tape travel by using information detectable on the record carrier by using information signals recorded by the same method as the main recording on the same track as the main recording used signal is digitally coded
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention provides a kind of method of speech verification, server and system, this method is applied to server, including：It is sent to client by the verification audio file comprising at least two tracks and for the validation problem of the verification audio file, so as to verify audio file described in the client terminal playing, and exports the validation problem；Receive the response for the validation problem that the client is sent；According to the verification audio file and the response, it is determined whether pass through verification.The present invention provides a kind of method of speech verification, server and systems, can improve the safety of verification process.
Description
Technical field
The present invention relates to technical field of voice recognition, more particularly to a kind of method of speech verification, server and system.
Background technology
People or computer to distinguish user during business processing, generally by the form of identifying code come
Verification.
In the prior art, verification process is realized generally by the mode of word.Verification is shown on the interface of verification
Problem, user input answer according to validation problem.But computer can easily capture the word on interface, and then really
Make answer.Therefore, the safety of existing verification process is relatively low.
Invention content
An embodiment of the present invention provides a kind of method of speech verification, server and systems, can improve verification process
Safety.
In a first aspect, an embodiment of the present invention provides a kind of method of speech verification, it is applied to server, including：
It is sent by the verification audio file comprising at least two tracks and for the validation problem of the verification audio file
To client, so as to verify audio file described in the client terminal playing, and the validation problem is exported；
Receive the response for the validation problem that the client is sent；
According to the verification audio file and the response, it is determined whether pass through verification.
Further,
This method further comprises：
At least one first problem is pre-set, corresponding at least two first sound is set for each first problem
The information of each first audio file is arranged in frequency file；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to before client, is further comprised：
The validation problem is determined from least one first problem；
From corresponding described at least two first audio file of the validation problem, at least two first objects are determined
Audio file；
According at least two targets, first audio file, the verification audio file is generated, wherein each described
The first audio file of target corresponds to a track of the verification audio file；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
According to the information of at least two first objects audio file, determine the validation problem for described at least
First Validation Answer Key of two first object audio files；
Judge whether the response is consistent with first Validation Answer Key, if it is, determine through verification, otherwise,
Determination does not pass through verification.
Further,
This method further comprises：
Pre-set it is at least one include at least two tracks the second audio file；
Pre-set the corresponding Second Problem of each second audio file and answer；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to before client, is further comprised：
The verification audio file is determined from least one second audio file；
Determine the corresponding validation problem of the verification audio file and the second Validation Answer Key；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
Judge whether the response is consistent with second Validation Answer Key, if it is, determine through verification, otherwise,
Determination does not pass through verification.
Further,
This method further comprises：
Pre-set verification time length；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to after client, is further comprised：
Start timing；
Judge whether to receive the response in the verification time length, if it is, executing described in the basis
Verify audio file and the response, it is determined whether by verification, otherwise, it determines not terminating current process by verification.
Further,
Described according to the verification audio file and the response, it is determined whether after verification, further wrap
It includes：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man.
Further,
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
Second aspect, an embodiment of the present invention provides a kind of servers of speech verification, including：
Transmission unit, for will include at least two tracks verification audio file and be directed to the verification audio file
Validation problem be sent to client, so as to verify audio described in the client terminal playing, and export the validation problem；
Receiving unit, the response for receiving the validation problem that the client is sent；
Authentication unit, for according to the verification audio file and the response, it is determined whether pass through verification.
Further,
The server further comprises：
First storage unit, for preserving at least one first problem, each first problem corresponding at least two
First audio file, the information of each first audio file；
Further comprise：
Generation unit, for determining the validation problem from least one first problem, from the validation problem
In corresponding described at least two first audio files, at least two first object audio files are determined, according to described at least two
The first audio file of a target generates the verification audio file, wherein each the first audio file of the target corresponds to institute
State a track of verification audio file；
The authentication unit determines the verification for the information according at least two first objects audio file
Problem is directed to the first Validation Answer Key of at least two first objects audio file, judges described whether respond with described the
One Validation Answer Key is consistent, if it is, determining by verification, otherwise, it determines not passing through verification.
Further,
The server further comprises：
Second storage unit, for it is at least one include at least two tracks the second audio file, each described second
The corresponding Second Problem of audio file and answer；
Further comprise：
Determination unit determines institute for determining the verification audio file from least one second audio file
State the corresponding validation problem of verification audio file and the second Validation Answer Key；
The authentication unit, for judging whether the response is consistent with second Validation Answer Key, if it is,
It determines by verification, otherwise, it determines not passing through verification.
Further,
The server further comprises：
Setting unit, for verification time length to be arranged；
Further comprise：
Timing unit judges whether to receive the response in the verification time length, such as starting timing
Fruit is then to execute the triggering authentication unit, otherwise, it determines not passing through verification.
Further,
Described according to the verification audio file and the response, it is determined whether after verification, further wrap
It includes：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man.
Further,
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
The third aspect, an embodiment of the present invention provides a kind of systems of speech verification, including：
Any server at least one client and second aspect；
The client is tested for receiving the verification audio file and validation problem that the server is sent described in broadcasting
Audio file is demonstrate,proved, and exports the validation problem, receives the response of the validation problem, the response is sent to the clothes
Business device.
Further,
The client includes audio input device and audio output device；
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form；
The client, for playing the verification audio file and audio format using the audio output device
The validation problem receives the response of speech form using the audio input device.
In embodiments of the present invention, the verification audio file of at least two tracks is included by client terminal playing, and is exported
Validation problem, so that user answers the validation problem according to the content in the verification audio file of broadcasting, very due to computer
Content in audio file of the hardly possible identification comprising at least two tracks, is also difficult to obtain the response of accurate validation problem, but
It is that true man can readily identify the content in the audio file comprising at least two tracks, and then can be easy to
To the response of accurate validation problem, and then improve the safety of verification process.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow chart of the method for speech verification that one embodiment of the invention provides；
Fig. 2 is the flow chart of the method for another speech verification that one embodiment of the invention provides；
Fig. 3 is a kind of schematic diagram of the server for speech verification that one embodiment of the invention provides；
Fig. 4 is a kind of schematic diagram of the system for speech verification that one embodiment of the invention provides.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, an embodiment of the present invention provides a kind of method of speech verification, it is applied to server, this method can
To include the following steps：
Step 101：By the verification audio file comprising at least two tracks and for the verification of the verification audio file
Problem is sent to client, so as to verify audio file described in the client terminal playing, and exports the validation problem；
Step 102：Receive the response for the validation problem that the client is sent；
Step 103：According to the verification audio file and the response, it is determined whether pass through verification.
In embodiments of the present invention, the verification audio file of at least two tracks is included by client terminal playing, and is exported
Validation problem, so that user answers the validation problem according to the content in the verification audio file of broadcasting, very due to computer
Content in audio file of the hardly possible identification comprising at least two tracks, is also difficult to obtain the response of accurate validation problem, but
It is that true man can readily identify the content in the audio file comprising at least two tracks, and then can be easy to
To the response of accurate validation problem, and then improve the safety of verification process.
In general, validation problem is fairly simple, and true man are after the content for having listened verification audio file, Neng Gougen
It is easily obtained correct option according to the content.And computer verifies the content of audio file due to None- identified, so it is difficult to
Obtain correct option.
In an embodiment of the present invention, this method further comprises：
At least one first problem is pre-set, corresponding at least two first sound is set for each first problem
The information of each first audio file is arranged in frequency file；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to before client, is further comprised：
The validation problem is determined from least one first problem；
From corresponding described at least two first audio file of the validation problem, at least two first objects are determined
Audio file；
According at least two targets, first audio file, the verification audio file is generated, wherein each described
The first audio file of target corresponds to a track of the verification audio file；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
According to the information of at least two first objects audio file, determine the validation problem for described at least
First Validation Answer Key of two first object audio files；
Judge whether the response is consistent with first Validation Answer Key, if it is, determine through verification, otherwise,
Determination does not pass through verification.
In embodiments of the present invention, for different problems, different audio files is set.It, can when determining validation problem
To be randomly choosed from pre-set at least one first problem.And when determining at least two first object audio files,
It can be randomly choosed from corresponding at least two first audio file of the validation problem.
Here verification audio file is not fixed, with the difference of determining target audio file, obtained verification
Audio file is also different.First Validation Answer Key is nor fix, with the difference of determining target audio file, the first verification
Answer is also different.The safety higher of the program
For example, problem is：It please say the song title of a wherein songFor at least two audios of the problem
File needs to be song, and the information of these audio files includes song title.For the problem, from the two audio files
Information in search song title, judge response in song title whether be one of those, if it is, by verification, no
It is not pass through verification.In addition, in order to enable true man can be more prone to obtain correct answer, these songs preferably compare
Common, utilize national anthem etc..
In an embodiment of the present invention, this method further comprises：
Pre-set it is at least one include at least two tracks the second audio file；
Pre-set the corresponding Second Problem of each second audio file and answer；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to before client, is further comprised：
The verification audio file is determined from least one second audio file；
Determine the corresponding validation problem of the verification audio file and the second Validation Answer Key；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
Judge whether the response is consistent with second Validation Answer Key, if it is, determine through verification, otherwise,
Determination does not pass through verification.
In embodiments of the present invention, the second audio file, Second Problem and answer are all pre-set, and verify sound
For frequency file without synthesis, the second Validation Answer Key is also fixed.
For example, may include in the second audio file：At least two songs, each song correspond to a track, the
Two problems can be the song title of a wherein song, and answer is the song title of any one song at least two songs.
In an embodiment of the present invention, this method further comprises：
Pre-set verification time length；
It is described by the verification audio file comprising at least two tracks and for it is described verification audio file verification ask
Topic is sent to after client, is further comprised：
Start timing；
Judge whether to receive the response in the verification time length, if it is, executing described in the basis
Verify audio file and the response, it is determined whether by verification, otherwise, it determines not terminating current process by verification.
In an embodiment of the present invention, the time for answering validation problem is limited by verification time length, is verified when answering
When the time of problem is more than verification time length, it may be determined that do not pass through verification.In this way, avoiding computer can be by longer
Time resolution goes out to verify the possibility of audio file, improves the safety of verification process.
Here verification time length can be any value in -5 seconds 3 seconds.
In an embodiment of the present invention, described according to the verification audio file and the response, it is determined whether pass through
After verification, further comprise：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man.
In an embodiment of the present invention, the validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
In embodiments of the present invention, validation problem can be audio format, and response can be speech form.In this way,
The input-output equipment of client need to only have voice output unit (such as loud speaker) and sound input unit (such as Mike
Wind), it realizes fairly simple.
As shown in Fig. 2, an embodiment of the present invention provides a kind of method of speech verification, it is applied to server, this method can
To include the following steps：
Step 201：At least one first problem is pre-set, for each first problem setting corresponding at least two the
The information of each first audio file is arranged in one audio file.
Specifically, each first problem can be audio format.
For example, a first problem is：It please say the song title of a wherein songFor the first problem, if
Set the audio file of corresponding at least two song.More preferably, song here selects relatively common, such as：《The army of volunteers
March》、《It is very sweet》.The information of the audio file of each song includes song title.
Step 202：Validation problem is determined from least one first problem.
Specifically, it can randomly choose, can also be different according to the business handled, select different validation problems.
For example, validation problem is：It please say the song title of a wherein song
Step 203：From corresponding at least two first audio file of validation problem, at least two first objects are determined
Audio file.
For example, it from the audio file of at least two songs, determines《The March of the Volunteers》、 《It is very sweet》Make
For first object audio file.
Step 204：According at least two targets, first audio file, verification audio file is generated, wherein each mesh
Mark the track that the first audio file corresponds to verification audio file.
Specifically, the first audio file of target is corresponded with verification audio file.
For example, will《The March of the Volunteers》With《It is very sweet》Synthesize verification audio file, wherein verification audio
File includes two tracks, and a track corresponds to《The March of the Volunteers》, another track correspondence《It is very sweet》.
Step 205：By the verification audio file comprising at least two tracks and for the validation problem of verification audio file
It is sent to client, so that client terminal playing verifies audio file, and exports validation problem.
Specifically, after receiving verification audio file and validation problem, validation problem is first played, then plays verification
Audio file.User's (may be true man, it may be possible to computer) of client can be inputted by the form of voice and be responded.
Step 206：Receive the response for the validation problem that client is sent.
Specifically, response input by user is sent to server by client.
For example, which is speech form, and content is：《It is very sweet》.
Step 207：According to the information of at least two first objects audio file, determine validation problem for this at least
First Validation Answer Key of two first object audio files.
Specifically, for different first object audio files, the answer of the same validation problem may be different.
For example, according to《The March of the Volunteers》With《It is very sweet》The information of this two song, determination " please say it
In a song song title" answer of this validation problem is：" March of the Volunteers " and/or " very sweet ".
Step 208：Judge whether response is consistent with the first Validation Answer Key, if so, 209 are thened follow the steps, otherwise,
Execute step 210.
For example, by parse speech form response, if the content parsed include " March of the Volunteers ",
Any one in " very sweet ", then by verification, if not including " March of the Volunteers " and " sweet tea in the content parsed
Any one in sweet honey ", then do not pass through verification.
Step 209：Determination passes through verification.
Specifically, illustrate that the user of client is true man by verification.
Step 210：Determination does not pass through verification.
Specifically, do not illustrate that the user of client is not true man by verification.
In embodiments of the present invention, true man can be easier by verification, and machine and software etc. are difficult in no mankind
Intelligence passes through verification in the case of participating in.
As shown in figure 3, a kind of server of speech verification provided in this embodiment, including：
Transmission unit 301, for will include the verification audio file of at least two tracks and for the verification audio it is literary
The validation problem of part is sent to client, so as to verify audio described in the client terminal playing, and exports the validation problem；
Receiving unit 302, the response for receiving the validation problem that the client is sent；
Authentication unit 303, for according to the verification audio file and the response, it is determined whether pass through verification.
In an embodiment of the present invention, which further comprises：
First storage unit, for preserving at least one first problem, each first problem corresponding at least two
First audio file, the information of each first audio file；
Further comprise：
Generation unit, for determining the validation problem from least one first problem, from the validation problem
In corresponding described at least two first audio files, at least two first object audio files are determined, according to described at least two
The first audio file of a target generates the verification audio file, wherein each the first audio file of the target corresponds to institute
State a track of verification audio file；
The authentication unit determines the verification for the information according at least two first objects audio file
Problem is directed to the first Validation Answer Key of at least two first objects audio file, judges described whether respond with described the
One Validation Answer Key is consistent, if it is, determining by verification, otherwise, it determines not passing through verification.
In an embodiment of the present invention, which further comprises：
Second storage unit, for it is at least one include at least two tracks the second audio file, each described second
The corresponding Second Problem of audio file and answer；
Further comprise：
Determination unit determines institute for determining the verification audio file from least one second audio file
State the corresponding validation problem of verification audio file and the second Validation Answer Key；
The authentication unit, for judging whether the response is consistent with second Validation Answer Key, if it is,
It determines by verification, otherwise, it determines not passing through verification.
In an embodiment of the present invention, which further comprises：
Setting unit, for verification time length to be arranged；
Further comprise：
Timing unit judges whether to receive the response in the verification time length, such as starting timing
Fruit is then to execute the triggering authentication unit, otherwise, it determines not passing through verification.
In an embodiment of the present invention, described according to the verification audio file and the response, it is determined whether pass through
After verification, further comprise：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man.
In an embodiment of the present invention, the validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
As shown in figure 4, an embodiment of the present invention provides a kind of systems of speech verification, including：
Any server 402 at least one client 401 and the embodiment of the present invention；
The client 401 is played for receiving the verification audio file and validation problem that the server 402 is sent
The verification audio file, and the validation problem is exported, the response of the validation problem is received, the response is sent to
The server 402.
Three clients 401 are shown in Fig. 4.
In an embodiment of the present invention, the client includes audio input device and audio output device；
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form；
The client, for playing the verification audio file and audio format using the audio output device
The validation problem receives the response of speech form using the audio input device.
In embodiments of the present invention, audio input device may include that microphone, microphone array and corresponding noise reduction are set
It is standby.
In embodiments of the present invention, client is without relying on the non-acoustic input such as button, remote controler, touch screen, camera
Equipment.
In embodiments of the present invention, audio output device may include speaker, earphone etc..
In embodiments of the present invention, client is without relying on the non-acoustic output equipment such as display screen.
In embodiments of the present invention, client relies only on audio input device and is inputted, and audio output device is as defeated
Go out.There is great convenience on intelligent sound product applied to no display equipment.Simultaneously for dysopia user more
Add close friend.
The contents such as the information exchange between each unit, implementation procedure in above-mentioned apparatus, due to implementing with the method for the present invention
Example is based on same design, and particular content can be found in the narration in the method for the present invention embodiment, and details are not described herein again.
An embodiment of the present invention provides a kind of readable mediums, including execute instruction, when the processor of storage control executes
The method that when executing instruction, the storage control executes any one speech verification provided in an embodiment of the present invention.
An embodiment of the present invention provides a kind of storage controls, including：Processor, memory and bus；
The memory is executed instruction for storing, and the processor is connect with the memory by the bus, when
When the storage control operation, the processor executes executing instruction for the memory storage, so that the storage controls
The method that device executes any one speech verification provided in an embodiment of the present invention.
The each embodiment of the present invention at least has the advantages that：
1, in embodiments of the present invention, the verification audio file of at least two tracks is included by client terminal playing, and defeated
Go out validation problem, so that user answers the validation problem according to the content in the verification audio file of broadcasting, due to computer
It is difficult the content in audio file of the identification comprising at least two tracks, is also difficult to obtain the response of accurate validation problem,
But true man can readily identify the content in the audio file comprising at least two tracks, and then can be easy to
The response of accurate validation problem is obtained, and then improves the safety of verification process.
2, in embodiments of the present invention, the time for answering validation problem is limited by verification time length, is verified when answering
When the time of problem is more than verification time length, it may be determined that do not pass through verification.In this way, avoiding computer can be by longer
Time resolution goes out to verify the possibility of audio file, improves the safety of verification process.
3, in embodiments of the present invention, client relies only on audio input device and is inputted, audio output device conduct
Output is applied to have great convenience on the intelligent sound product without display equipment, realizes fairly simple.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity
Or operation is distinguished with another entity or operation, is deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence " including a 〃 〃 ",
It is not precluded in the process, method, article or apparatus that includes the element that there is also other identical factors.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above method embodiment can lead to
The relevant hardware of program instruction is crossed to complete, program above-mentioned can be stored in computer-readable storage medium, the journey
Sequence when being executed, executes step including the steps of the foregoing method embodiments；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or
In the various media that can store program code such as person's CD.
Finally, it should be noted that：The foregoing is merely presently preferred embodiments of the present invention, is merely to illustrate the skill of the present invention
Art scheme, is not intended to limit the scope of the present invention.That is done all within the spirits and principles of the present invention any repaiies
Change, equivalent replacement, improvement etc., be included within the scope of protection of the present invention.
Claims (10)
1. a kind of method of speech verification, which is characterized in that it is applied to server, including：
It is sent to visitor by the verification audio file comprising at least two tracks and for the validation problem of the verification audio file
Family end so as to verify audio file described in the client terminal playing, and exports the validation problem；
Receive the response for the validation problem that the client is sent；
According to the verification audio file and the response, it is determined whether pass through verification.
2. according to the method described in claim 1, it is characterized in that,
Further comprise：
At least one first problem is pre-set, corresponding at least two first audios text is set for each first problem
The information of each first audio file is arranged in part；
Described by the verification audio file comprising at least two tracks and for the validation problem hair of the verification audio file
Before giving client, further comprise：
The validation problem is determined from least one first problem；
From corresponding described at least two first audio file of the validation problem, at least two first object audio texts are determined
Part；
According at least two targets, first audio file, the verification audio file is generated, wherein each target the
One audio file corresponds to a track of the verification audio file；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
According to the information of at least two first objects audio file, determine the validation problem for described at least two the
First Validation Answer Key of one target audio file；
Judge whether the response is consistent with first Validation Answer Key, if it is, determine through verification, otherwise, it determines
Verification is not passed through.
3. according to the method described in claim 1, it is characterized in that,
Further comprise：
Pre-set it is at least one include at least two tracks the second audio file；
Pre-set the corresponding Second Problem of each second audio file and answer；
Described by the verification audio file comprising at least two tracks and for the validation problem hair of the verification audio file
Before giving client, further comprise：
The verification audio file is determined from least one second audio file；
Determine the corresponding validation problem of the verification audio file and the second Validation Answer Key；
It is described according to the verification audio file and the response, it is determined whether by verification, including：
Judge whether the response is consistent with second Validation Answer Key, if it is, determine through verification, otherwise, it determines
Verification is not passed through.
4. according to any method in claim 1-3, which is characterized in that
Further comprise：
Pre-set verification time length；
Described by the verification audio file comprising at least two tracks and for the validation problem hair of the verification audio file
After giving client, further comprise：
Start timing；
Judge whether to receive the response in the verification time length, if it is, executing described according to the verification
Audio file and the response, it is determined whether by verification, otherwise, it determines not terminating current process by verification；
And/or
Described according to the verification audio file and the response, it is determined whether after verification, further comprise：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man；
And/or
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
5. a kind of server of speech verification, which is characterized in that including：
Transmission unit, for comprising at least two tracks audio file will to be verified and for the verification of the verification audio file
Problem is sent to client, so as to verify audio described in the client terminal playing, and exports the validation problem；
Receiving unit, the response for receiving the validation problem that the client is sent；
Authentication unit, for according to the verification audio file and the response, it is determined whether pass through verification.
6. server according to claim 5, which is characterized in that
Further comprise：
First storage unit, for preserving at least one first problem, each first problem corresponding at least two first
Audio file, the information of each first audio file；
Further comprise：
Generation unit is corresponded to for determining the validation problem from least one first problem from the validation problem
Described at least two first audio files in, at least two first object audio files are determined, according at least two mesh
The first audio file is marked, the verification audio file is generated, wherein each the first audio file of the target corresponds to the verification
One track of audio file；
The authentication unit determines the validation problem for the information according at least two first objects audio file
For the first Validation Answer Key of at least two first objects audio file, judge whether the response is verified with described first
Answer is consistent, if it is, determining by verification, otherwise, it determines not passing through verification.
7. server according to claim 5, which is characterized in that
Further comprise：
Second storage unit, for it is at least one include at least two tracks the second audio file, each second audio
The corresponding Second Problem of file and answer；
Further comprise：
Determination unit is tested for the determination verification audio file from least one second audio file described in determination
Demonstrate,prove the corresponding validation problem of audio file and the second Validation Answer Key；
The authentication unit, for judging whether the response is consistent with second Validation Answer Key, if it is, determining logical
Verification is crossed, otherwise, it determines not passing through verification.
8. according to any server in claim 5-7, which is characterized in that
Further comprise：
Setting unit, for verification time length to be arranged；
Further comprise：
Timing unit judges whether to receive the response in the verification time length for starting timing, if so,
The triggering authentication unit is then executed, otherwise, it determines not passing through verification；
And/or
Described according to the verification audio file and the response, it is determined whether after verification, further comprise：
When passing through verification, determine that the input response is true man；
When not over verification, determine that the input response is not true man；
And/or
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form.
9. a kind of system of speech verification, which is characterized in that including：
Any server at least one client and claim 6-8；
The client plays the verification sound for receiving the verification audio file and validation problem that the server is sent
Frequency file, and the validation problem is exported, the response of the validation problem is received, the response is sent to the server.
10. system according to claim 9, which is characterized in that
The client includes audio input device and audio output device；
The validation problem includes：The validation problem of audio format；
The response includes：The response of speech form；
The client is tested for being played using the audio output device described in the verification audio file and audio format
Card problem receives the response of speech form using the audio input device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810015295.8A CN108418788A (en) | 2018-01-08 | 2018-01-08 | A kind of method of speech verification, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810015295.8A CN108418788A (en) | 2018-01-08 | 2018-01-08 | A kind of method of speech verification, server and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108418788A true CN108418788A (en) | 2018-08-17 |
Family
ID=63125819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810015295.8A Pending CN108418788A (en) | 2018-01-08 | 2018-01-08 | A kind of method of speech verification, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108418788A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131125A (en) * | 2018-10-31 | 2020-05-08 | 薛康泰华 | Dynamic verification method and software based on voice |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420305A (en) * | 2008-11-28 | 2009-04-29 | 重庆大学 | Speech identifying code implementing method |
| CN101662365A (en) * | 2009-09-18 | 2010-03-03 | 浙江大学 | Generation method of Chinese voice verification code |
| US20100095350A1 (en) * | 2008-10-15 | 2010-04-15 | Towson University | Universally usable human-interaction proof |
| CN103246837A (en) * | 2012-02-13 | 2013-08-14 | 联想(北京)有限公司 | Method for providing verification codes and user equipment |
| CN105224844A (en) * | 2014-07-01 | 2016-01-06 | 腾讯科技（深圳）有限公司 | Verification method, system and device |
| CN105469788A (en) * | 2015-12-09 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Voice information verification method and apparatus |
| CN105939250A (en) * | 2016-05-25 | 2016-09-14 | 珠海市魅族科技有限公司 | Audio processing method and apparatus |
| CN107222490A (en) * | 2017-06-19 | 2017-09-29 | 广州市讯飞樽鸿信息技术有限公司 | A kind of speech verification method |
-
2018
- 2018-01-08 CN CN201810015295.8A patent/CN108418788A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100095350A1 (en) * | 2008-10-15 | 2010-04-15 | Towson University | Universally usable human-interaction proof |
| CN101420305A (en) * | 2008-11-28 | 2009-04-29 | 重庆大学 | Speech identifying code implementing method |
| CN101662365A (en) * | 2009-09-18 | 2010-03-03 | 浙江大学 | Generation method of Chinese voice verification code |
| CN103246837A (en) * | 2012-02-13 | 2013-08-14 | 联想(北京)有限公司 | Method for providing verification codes and user equipment |
| CN105224844A (en) * | 2014-07-01 | 2016-01-06 | 腾讯科技（深圳）有限公司 | Verification method, system and device |
| CN105469788A (en) * | 2015-12-09 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Voice information verification method and apparatus |
| CN105939250A (en) * | 2016-05-25 | 2016-09-14 | 珠海市魅族科技有限公司 | Audio processing method and apparatus |
| CN107222490A (en) * | 2017-06-19 | 2017-09-29 | 广州市讯飞樽鸿信息技术有限公司 | A kind of speech verification method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131125A (en) * | 2018-10-31 | 2020-05-08 | 薛康泰华 | Dynamic verification method and software based on voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3611895B1 (en) | Method and device for user registration, and electronic device | |
| US11042616B2 (en) | Detection of replay attack | |
| CN104123115B (en) | Audio information processing method and electronic device | |
| EP2880834B1 (en) | Using the ability to speak as a human interactive proof | |
| CN109960809B (en) | Dictation content generation method and electronic equipment | |
| EP3721605A1 (en) | Streaming radio with personalized content integration | |
| EP3611724A1 (en) | Voice response method and device, and smart device | |
| US20020088336A1 (en) | Method of identifying pieces of music | |
| CN111161746B (en) | Voiceprint registration method and system | |
| CN106548792A (en) | Intelligent sound box device, mobile terminal and music processing method | |
| CN111081260A (en) | Method and system for identifying voiceprint of awakening word | |
| US9792894B2 (en) | Speech synthesis dictionary creating device and method | |
| CN108418788A (en) | A kind of method of speech verification, server and system | |
| CN105225664B (en) | Information verification method and device and sound sample generation method and device | |
| CN110197663B (en) | Control method and device and electronic equipment | |
| CN109271480B (en) | Voice question searching method and electronic equipment | |
| KR20100028748A (en) | System and method for providing advertisement | |
| CN113707128B (en) | Test method and system for full duplex voice interaction system | |
| CN109615731A (en) | A kind of audio-frequency inputting method based on recognition of face | |
| CN109688430A (en) | A kind of court trial file playback method, system and storage medium | |
| CN110516043A (en) | Answer generation method and device for question answering system | |
| CN111081227B (en) | Recognition method of dictation content and electronic equipment | |
| CN111785280A (en) | Identity authentication method and device, storage medium and electronic equipment | |
| JP5034111B2 (en) | Data storage system, data storage / playback method, and program | |
| CN110838211A (en) | Voice answering method, device and 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 |
Application publication date: 20180817 |
|
| RJ01 | Rejection of invention patent application after publication |