CN104361886B - Speech ciphering method and device and voice decryption method and device - Google Patents
Speech ciphering method and device and voice decryption method and device Download PDFInfo
- Publication number
- CN104361886B CN104361886B CN201410592233.5A CN201410592233A CN104361886B CN 104361886 B CN104361886 B CN 104361886B CN 201410592233 A CN201410592233 A CN 201410592233A CN 104361886 B CN104361886 B CN 104361886B
- Authority
- CN
- China
- Prior art keywords
- voice
- characteristic parameter
- encrypted
- decryption
- decrypt
- 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.)
- Active
Links
Landscapes
- Storage Device Security (AREA)
Abstract
The embodiment of the present invention provides a kind of speech ciphering method and device and voice decryption method and device.The speech ciphering method includes：The character in the voice for encryption is recognized, encrypted characters sequence is obtained；Extract the characteristic parameter of the voice for being used to encrypt；It is encrypted with the obtained encrypted characters sequence pair of identification information to be encrypted, and preserve the encrypted characters sequence and the characteristic parameter, for when decryption obtains described information, the characteristic parameter with decryption character string and for the voice of decryption is matched.Therefore decoding difficulty is added, improves the security of encryption information.
Description
Technical field
The present embodiments relate to field of information security technology, more particularly to a kind of speech ciphering method and device and language
Sound decryption method and device.
Background technology
Voice encryption technology is a kind of conventional information encryption, mainly by speech recognition, from the voice of input
In identify character, obtain encrypted characters sequence, then carried out by AES with encrypted characters sequence pair confidential information to be added
Encryption, to ensure the safety of described information.Accordingly, when the information encrypted being decrypted, by speech recognition to for
The voice of decryption carries out speech recognition, and character is identified from the voice for decryption, obtains decrypting character string.Afterwards, will
Decryption character string is matched with encrypted characters sequence, if the match is successful, passes through solution corresponding with above-mentioned AES
The information that close algorithm has been encrypted with decryption character string or encrypted characters sequence pair is decrypted, and obtains protected information.Can
To find out, existing voice encryption and decryption technology cause encrypted information to be easier to be decrypted, and cause the security of information
Reduction.
The content of the invention
The embodiment of the present invention provides a kind of speech ciphering method and device and voice decryption method and device, to increase brokenly
Difficulty is translated, the security of information is improved.
In a first aspect, the embodiments of the invention provide a kind of speech ciphering method, including：
The character in the voice for encryption is recognized, encrypted characters sequence is obtained；
Extract the characteristic parameter of the voice for being used to encrypt；
It is encrypted with the obtained encrypted characters sequence pair of identification information to be encrypted, and preserves the encrypted characters
Sequence and the characteristic parameter, for when decryption obtains described information, the voice with decryption character string and for decryption
Characteristic parameter matched.
Second aspect, the embodiment of the present invention additionally provides a kind of voice encryption device, including：
Sound identification module, for recognizing the character in the voice for encryption, obtains encrypted characters sequence；
Characteristic extracting module, the characteristic parameter for extracting the voice for being used to encrypt；
Encrypting module, for recognizing obtained encrypted characters sequence pair letter to be encrypted with the sound identification module
Breath is encrypted, and preserves the encrypted characters sequence and the characteristic parameter, for when decryption obtains described information, with
Decryption character string and the characteristic parameter for the voice of decryption are matched.
Speech ciphering method and device provided in an embodiment of the present invention, by being extracted during voice encryption and preserving use
In the characteristic parameter of the voice of encryption information, for when decryption obtains described information, with decryption character string and for solving
The characteristic parameter of close voice is matched so that when the decryption person for having bad attempt attempts to decode encrypted information, no
The character for only needing voice to carry is consistent, and voice feature also will the match is successful can be only achieved the purpose of decoding so that
Decoding difficulty is added, the security of encryption information is improved.
The third aspect, the embodiment of the present invention additionally provides a kind of voice decryption method, including：
Recognize for being encrypted the voice that information is decrypted, obtaining decrypting character string；
Extract the characteristic parameter of the voice for being used to decrypt；
By the decryption character string and the characteristic parameter and the encrypted characters sequence of preservation of the voice for being used to decrypt
Matched respectively with characteristic parameter, the encrypted characters sequence and characteristic parameter are the voice encrypted to the encrypted information
Encrypted characters sequence and characteristic parameter；
After the match is successful, solved with information is encrypted described in the decryption character string or the encrypted characters sequence pair
It is close.
Fourth aspect, the embodiment of the present invention additionally provides a kind of voice decryption device, including：
Sound identification module, is used to, to being encrypted the voice that information is decrypted, obtain decrypting character string for recognizing；
Characteristic extracting module, the characteristic parameter for extracting the voice for being used to decrypt；
Matching module, for by it is described decryption character string and it is described be used for decrypt voice characteristic parameter with preserve
Encrypted characters sequence and characteristic parameter are matched respectively, and the encrypted characters sequence and characteristic parameter are to the encrypted letter
The encrypted characters sequence and characteristic parameter of the voice of encryption for information；
Deciphering module, after the match is successful, with quilt described in the decryption character string or the encrypted characters sequence pair
Encryption information is decrypted.
Voice decryption method provided in an embodiment of the present invention and device, by the feature that voice is extracted during decryption
Parameter, and matched into respectively with the encrypted characters sequence and characteristic parameter preserved in decryption character string and the characteristic parameter of extraction
In the case of work(, it is decrypted with decryption character string or the encrypted information of encrypted characters sequence pair, relative to prior art
Matching only is carried out to decryption character string and encrypted characters sequence and adds decoding difficulty, the security of information is improved.
Brief description of the drawings
In order to illustrate more clearly of the present invention, one will be done to the required accompanying drawing used in the present invention below and be simply situated between
Continue, it should be apparent that, drawings in the following description are some embodiments of the present invention, are come for those of ordinary skill in the art
Say, without having to pay creative labor, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 a are a kind of flow chart for speech ciphering method that the embodiment of the present invention one is provided；
Fig. 1 b are the waveform diagram of voice decibel value in speech ciphering method provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart for speech ciphering method that the embodiment of the present invention two is provided；
Fig. 3 is a kind of structural representation for voice encryption device that the embodiment of the present invention three is provided；
Fig. 4 is a kind of flow chart for voice decryption method that the embodiment of the present invention four is provided；
Fig. 5 is the structural representation that a kind of voice that the embodiment of the present invention five is provided decrypts device.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to the embodiment of the present invention
In technical scheme be described in further detail, it is clear that described embodiment is a part of embodiment of the invention, rather than entirely
The embodiment in portion.It is understood that specific embodiment described herein is only used for explaining the present invention, rather than to the present invention's
Limit, based on the embodiment in the present invention, those of ordinary skill in the art are obtained under the premise of creative work is not made
Every other embodiment, belong to the scope of protection of the invention.It also should be noted that, for the ease of description, accompanying drawing
In illustrate only part related to the present invention rather than full content.
Embodiment one
Fig. 1 a are referred to, are a kind of flow chart for speech ciphering method that the embodiment of the present invention one is provided.The present invention is implemented
The method of example can be performed by configuring with hardware and/or the voice encryption device of software realization, and this realizes that device is typically
It is configured in the terminal that voice encryption service can be provided, for example, configuration is in the various mobile terminals such as smart mobile phone, tablet personal computer
In.
This method includes：Operation 11~operation 13.
In operation 11, the character in the voice for encryption is recognized, encrypted characters sequence is obtained.
This operation is particular by speech recognition technology, and identification obtains encrypted characters sequence from the voice for encryption.
Wherein, the voice for encryption refers to the voice that information to be encrypted is encrypted, and both can be that user passes through
The voice or the language of terminal local storage of microphone input in the terminal of voice encryption service can be provided
Sound, can also be the sound bite downloaded obtain in real time.Preferably using user by the way that the end that voice encryption is serviced can be provided
The voice of microphone input in end, for information to be encrypted, user can input suitable voice according to their needs, just
In user's memory, and the content user of the voice of input can add flexibility with autonomous control.
The voice for being used to encrypt both can be the other forms such as Chinese form or English, the present embodiment pair
This is not limited, as long as the terminal that can be provided voice encryption service is correctly recognized.
The encrypted characters sequence, refers to the character obtained by being recognized from the voice for encryption, according to for encrypting
Voice in can recognize that phoneme sequencing, the character string of formation.For example, the voice for encryption is " enabling ", identification
Character " kai " and character " men " are obtained, by character " kai " and character " men " according to recognizable phoneme in the voice for encryption
Sequencing, formed encrypted characters sequence " kaimen ".
In operation 12, the characteristic parameter of the voice for being used to encrypt is extracted.
The feature of voice including the order of importance and emergency etc., as first speak it is generally overcast wait a moment, second is spoken, and generally fast and sound is very high,
That is, different people has different phonetic features, if extracting these features and being preserved, and it is used in decryption
The feature of voice with attempting to decrypt is matched, then can ensure that the people only encrypted could decrypt encrypted information, carry
The security of high information.
Operate in 13, the encrypted characters sequence pair obtained with identification information to be encrypted is encrypted, and preserves institute
Encrypted characters sequence and the characteristic parameter are stated, for when decryption obtains described information, with decrypting character string and being used for
The characteristic parameter of the voice of decryption is matched.
This operation not only includes the behaviour that the encrypted characters sequence pair obtained with identification information to be encrypted is encrypted
Make, and comprising the operation for preserving the encrypted characters sequence and the characteristic parameter, both limit without order, can also be simultaneously
Row is performed.When being encrypted with the obtained encrypted characters sequence pair of identification information to be encrypted, the AES used
It can be AES256 etc., not be limited here.
Wherein, the information to be encrypted can include：The all kinds such as document, video file, audio file or picture,
It can also be the combination of foregoing several types.
Wherein, preserve the encrypted characters sequence and the characteristic parameter is particularly used for obtaining described information in decryption
When, the characteristic parameter with decryption character string and for the voice of decryption is matched respectively, in other words, to being encrypted information
When being decrypted, not only need to be matched the encrypted characters sequence for decrypting character string with preserving, in addition it is also necessary to will be used to solve
The characteristic parameter of close voice is matched with the characteristic parameter of the voice for being used to encrypt preserved.
The technical scheme of the present embodiment, by the way that the voice for encryption information is extracted and preserved during voice encryption
Characteristic parameter, for when decryption obtains described information, the characteristic parameter of the voice with decryption character string and for decryption
Matched so that when the decryption person for having bad attempt attempts to decode encrypted information, the word for not only needing voice to carry
Symbol is consistent, and voice feature also will the match is successful can be only achieved the purpose of decoding, so as to add decoding difficulty, improve
The security of encryption information.
It should be noted that in the present embodiment, operation 11 and operation 12 are separate, are limited without inevitable order
System, can be performed using the order opposite with the present embodiment, can also performed parallel.
It should also be noted that, being used for the characteristic parameter of the voice of encryption described in said extracted may include：Extract described use
At least one in the duration of the voice of encryption, pace value and decibel value.
The decibel value of the voice for encryption is extracted, can obtain described be used for after the voice of encryption is identified
Decibel value on each time point；Or can also be the decibel value for obtaining each character in the encrypted characters sequence.As schemed
Shown in 1b, decibel value is curved on a timeline, and time point is different, and decibel value is also different.The waveform in Fig. 1 b
Figure changes into data, and it is the decibel value on each time point that can preserve into an array.Such as say " z_h_i__m_
A_______k_a_i___m_e_n " (reference can be made to explanation in following embodiments two) time is 3 seconds, that is to say, that have 30
0.1 second, that decibel value was represented by array：[30,20,40,30,35,30,20,10,50,50,50,40,25,15,5,0,0,
0,0,30,35,35,35,25,15,35,35,35,35,35].Encrypted characters sequence, pace value and decibel value can be retained separately
To a file.Even for identical encrypted characters sequence, due to the difference of encipherer's tongue, typically result in different
The decibel value of the voice for being used to encrypt of encipherer's input is inconsistent, therefore preserves encrypted characters sequence and for adding in encryption
The decibel value of close voice, during decryption, even if decryption character string and encrypted characters sequences match success, still can by for
Difficulty is decoded in the decibel value increase of the voice of encryption, so as to improve the security of encryption information.
The characteristic parameter of extraction is more, time-consuming longer, but the difficulty decoded encrypted information is bigger, encryption letter
The security of breath is higher；The characteristic parameter of extraction is fewer, time-consuming shorter, but the difficulty decoded encrypted information is got over
Low, the security of encryption information is lower, therefore the suitable characteristic parameter of selective extraction, can take into account encryption efficiency and encryption information
Security.
Illustrate the implementation of pace value for extracting the voice for being used to encrypt below by specific embodiment.
Embodiment two
Referring to Fig. 2, a kind of flow chart of the speech ciphering method provided for the embodiment of the present invention two.The present embodiment is upper
State on the basis of embodiment that there is provided the preferred scheme for extracting the characteristic parameter of voice this operation for being used to encrypting, tool
Body provides the preferred scheme for the pace value for extracting the voice for being used to encrypt.
The method for optimizing includes：Operation 21~operation 22.
In operation 21, the time interval between two neighboring character in the encrypted characters sequence is obtained.
In the present embodiment, by obtaining the time interval in the encrypted characters sequence between two neighboring character, will
The time interval arrived is as described for the pace value for the voice encrypted.In other words, based in the encrypted characters sequence
Pause between two neighboring character, characterizes the pace value of the voice for being used to encrypt.For example, someone will be added to information
When close, virtual Mike's button on screen is pinned first, against speaking, for example, " open sesame " is said, words lift hand is finished, and end is said
Words, the mode of wherein beginning and end is various, is not limited here.
Speech recognition can be carried out to " open sesame ", analyze the distribution of following character on a timeline in encryption device：
#______z_h_i__m_a_______k_a_i___m_e_n____#
Wherein, first " # " represents to start, and second " # " represents to terminate；Each " _ " or the time shared by letter
It is 0.1 second.All it is to wait for the time, not considering before z and after n, only analyzes the part between z to n, obtain wherein adjacent two
Time interval between individual letter, namely to the pause time of each two phoneme.
Due to the difference of encipherer's tongue, cause adjacent two in the voice for being used to encrypt that different encipherers input
Pause between individual character is inconsistent, therefore, during decryption, even if decryption character string and the success of encrypted characters sequences match, still
Decoding difficulty can be increased according to the matching result of two neighboring alphabetical time interval between encryption and decryption voice, so as to improve
The security of encrypted information.
In operation 22, the duration of the voice for being used to encrypt is obtained, according to the duration and the encrypted characters sequence
The quantity of middle character, obtains the pace value of the voice for being used to encrypt.
" #______z_h_i__m_a_______k_a_i___m_e_n____# " for example gone out by speech recognition, can be with
Obtain voice duration, 40 × 0.1 seconds=4 seconds, have 11 characters, therefore pace value can be obtained for 4 ÷ 11 seconds.
Because encipherer speaks the difference of speed, typically result in different encipherers' inputs the voice for being used to encrypt when
Length is inconsistent, therefore during decryption, still can be according to for adding solution even if decryption character string and the success of encrypted characters sequences match
Difficulty is decoded in the matching result increase of pace value between close voice, so as to further improve the security of encryption information.
Difference with operation 21 is that operation 21 is based on stopping between two neighboring character in the encrypted characters sequence
, characterize the pace value of the voice for being used to encrypt；And operate 22 durations based on the voice for being used to encrypt and described
The quantity of character in encrypted characters sequence, by the time-consuming of each character, characterizes the pace value of the voice for being used to encrypt.
It should be noted that in the present embodiment, operation 21 and operation 22 are separate, are used for described in extraction
The preferred embodiment of the pace value of the voice of encryption, in other words, extracting the pace value of the voice for being used to encrypt can wrap
At least one in operation 21 and operation 22 is included, when performing multi-mode operation, its execution sequence is not limited.
When combine perform when, the characteristic parameter of extraction is more, take it is longer, but to difficulty that encrypted information is decoded
Degree is bigger, and the security of encryption information is higher；When individually performing one of which, the characteristic parameter of extraction is fewer, time-consuming shorter,
But the difficulty decoded encrypted information is lower, and the security of encryption information is lower, therefore selective extraction is suitably special
Parameter is levied, the security of encryption efficiency and encryption information can be taken into account.
Embodiment three
Referring to Fig. 3, a kind of structural representation of the voice encryption device provided for the embodiment of the present invention three.The device bag
Include：Sound identification module 31, characteristic extracting module 32 and encrypting module 33.
Wherein, identification module 31 is used to recognize the character in the voice for encryption, obtains encrypted characters sequence；Feature is carried
Modulus block 32 is used for the characteristic parameter for extracting the voice for being used to encrypt；The sound identification module of encrypting module 33
Recognize that obtained encrypted characters sequence pair information to be encrypted is encrypted, and preserve the encrypted characters sequence and described
Characteristic parameter, for when decryption obtains described information, the characteristic parameter of the voice with decryption character string and for decryption
Matched.
The technical scheme of the present embodiment, by the way that the voice for encryption information is extracted and preserved during voice encryption
Characteristic parameter, for when decryption obtains described information, the characteristic parameter of the voice with decryption character string and for decryption
Matched so that when the decryption person for having bad attempt attempts to decode encrypted information, the word for not only needing voice to carry
Symbol is consistent, and voice feature also will the match is successful can be only achieved the purpose of decoding, so as to add decoding difficulty, improve
The security of encryption information.
In such scheme, characteristic extracting module 32 preferably includes time extracting sub-module, word speed extracting sub-module and divided
At least one in shellfish extracting sub-module.
Wherein, time extracting sub-module is used for the duration for extracting the voice for being used to encrypt；Word speed extracting sub-module is used
In the pace value for extracting the voice for being used to encrypt；Decibel extracting sub-module is used for point for extracting the voice for being used to encrypt
Shellfish value.
The word speed extracting sub-module is at least one of following for performing：
Obtain the time interval between two neighboring character in the encrypted characters sequence；
The duration of the voice for being used to encrypt is obtained, according to the number of character in the duration and the encrypted characters sequence
Amount, obtains the pace value of the voice for being used to encrypt.
The decibel extracting sub-module is used for：
Obtain the decibel value on each time point after the voice for being used to encrypt is identified；Or
Decibel value for obtaining each character in the encrypted characters sequence.
Voice encryption device provided in an embodiment of the present invention can perform the voice encryption that any embodiment of the present invention is provided
Method, possesses the corresponding functional module of execution method and beneficial effect.
Example IV
Referring to Fig. 4, a kind of flow chart of the voice decryption method provided for the embodiment of the present invention four.The embodiment of the present invention
Method device can be decrypted with the voice of hardware and/or software realization be performed by configuring, this realizes that device is typically and matches somebody with somebody
It is placed in the terminal that voice decryption service can be provided, for example, configuration is in the various mobile terminals such as smart mobile phone, tablet personal computer
In.
This method includes：Operation 41~operation 44.
In operation 41, recognize for being encrypted the voice that information is decrypted, obtaining decrypting character string.
This operation is particular by speech recognition technology, from for being recognized in being encrypted the voice that information is decrypted
To decryption character string.
The decryption character string, refers to by recognizing obtained character from the voice that encrypted information is decrypted,
According to for the sequencing to being encrypted can recognize that phoneme in the voice that information is decrypted, the character string of formation.
In operation 42, the characteristic parameter of the voice for being used to decrypt is extracted.
The extracting mode of characteristic parameter of this operation with extracting the voice for encryption in above-mentioned encryption embodiment is identical, this
In do not repeat.
Operate in 43, by the characteristic parameter and the encryption of preservation of the decryption character string and the voice for being used to decrypt
Character string and characteristic parameter are matched respectively, and the encrypted characters sequence and characteristic parameter are that the encrypted information is added
The encrypted characters sequence and characteristic parameter of close voice.
Not only include the voice to the encrypted information encryption by the decryption character string and preservation in this operation
Encrypted characters sequence matched, in addition to by it is described be used for decrypt voice characteristic parameter with preservation added to described
The characteristic parameter of the voice of secret letter encryption for information is matched.
Wherein, the terminal can be stored in the encrypted characters sequence and characteristic parameter that are encrypted the voice that information is encrypted
In.
Wherein, by the decryption character string and the encrypted characters sequence of the voice to the encrypted information encryption preserved
Row are matched, and are preferably matched the decryption character string completely with the encrypted characters sequence, to increase decoding
Difficulty, improves the security of encrypted information.
Wherein, the characteristic parameter of the voice for being used to decrypt is matched with the characteristic parameter preserved, preferably included：
Judge the voice for being used to decrypt characteristic parameter value whether the preservation characteristic parameter value predetermined deviation model
In enclosing, if the value of the characteristic parameter of the voice for being used to decrypt is in the range of the predetermined deviation, the match is successful.Change speech
It, as long as by the characteristic parameter of the voice for being used to decrypt and the characteristic parameter progress fuzzy matching preserved, carrying out fuzzy
With the reason for be, because identical encipherer says same sentence encryption voice every time, although encrypted characters sequence is consistent, but by
Can not possibly be completely the same in each utterance, cause characteristic parameter completely the same, therefore in order to improve decryption effect
Rate, need not be just the same as long as the characteristic parameter and the characteristic parameter of preservation for the voice of decryption are substantially the same.It is right
The deviation range that the value of the characteristic parameter of the preservation can be preset in the similarity of fuzzy matching is realized.
Assuming that for being illustrated exemplified by the voice " open sesame " of encryption to matching duration.Obtained by speech recognition
To " z_h_i__m_a_______k_a_i___m_e_n " (reference can be made to explanation in above-described embodiment two) and duration 3 seconds, so that
Obtain encrypted characters sequence -- " zhimakaimen ", preserve " zhimakaimen " and duration 3 seconds.During decryption, speech recognition is obtained
After the decryption character string arrived is " zhimakaimen ", also to judge voice for decryption duration whether 3 seconds ± 3 ×
In the range of 20%, wherein, ± 3 × 20% is predetermined deviation scope, depending on being visually actually needed, is not limited here.If with
In decryption voice duration in the range of 3 seconds ± 3 × 20%, i.e., when between 2.4 seconds~3.6 seconds, then duration is matched into
Work(.
Still solved for adding exemplified by the voice " open sesame " of encryption (referring to the explanation in above-described embodiment two) to matching
Time interval in close character string between two neighboring character is illustrated., from the 1st character " z " to the 11st character " n ",
Time interval between two neighboring character is respectively 0.1 second, 0.1 second, 0.2 second, 0.1 second, 0.7 second, 0.1 second, 0.1 second, 0.3
Second, 0.1 second and 0.1 second.It will again be assumed that predetermined deviation scope is time interval between two neighboring character in encrypted characters sequence
± 20%, then when decrypting character string with the success of encrypted characters sequences match, if per two neighboring word in decryption character string
The difference between the time interval between time interval adjacent character corresponding with encrypted characters sequence between symbol, in encryption
In the range of ± 20% of time interval in character string between corresponding adjacent character, per adjacent two in such as decryption character string
Time interval between individual character by character string be arranged as 0.09 second, 0.11 second, 0.17 second, 0.1 second, 0.57 second, 0.09
Second, 0.1 second, 0.25 second, 0.11 second and 0.09 second, then the match is successful.
Similarly, the decibel value for the voice for encryption after identified at each time point, can also set corresponding
Predetermined deviation scope, judge voice for decryption it is identified after each time point decibel value and the voice for encrypting
In deviation between decibel value on corresponding each time point, if be that then the match is successful as crossed in the range of predetermined deviation.
Or, corresponding predetermined deviation model only can also be set to the corresponding decibel value of each character in encrypted characters sequence
Enclose, judge in decryption character string between the decibel value of the decibel value character corresponding with encrypted characters sequence of each character
Whether deviation is in the range of predetermined deviation, if so, then the match is successful.
Due to also needing to the characteristic parameter progress by the characteristic parameter of the voice for being used to decrypt and preservation when decrypting
With fuzzy matching, so, even if encrypted characters sequence exposes, if it fails to match for characteristic parameter, it can not still decrypt and obtain being protected
The information of shield, therefore, not only increases the security of information, and can disclose Chinese language word if encrypting as prompting, keeps away
Exempt to forget Password by the user of voice encryption technical protection information.
In operation 44, after the match is successful, it is encrypted with described in the decryption character string or the encrypted characters sequence pair
Information is decrypted.
The technical scheme of the present embodiment, by extracting the characteristic parameter of voice during decryption, and in decryption character
Sequence and the characteristic parameter of extraction and the encrypted characters sequence and characteristic parameter that preserve are in the case that the match is successful respectively, with decryption
The encrypted information of character string or encrypted characters sequence pair is decrypted, relative to prior art only to decryption character string and
Encrypted characters sequence carries out matching and adds decoding difficulty, improves the security of information.
It should be noted that in the present embodiment, operation 41 and operation 42 are separate, are limited without inevitable order
System, can be performed using the order opposite with the present embodiment, can also performed parallel.
By previous embodiment one and embodiment two, the characteristic parameter for extracting the voice for being used to encrypt preferably is wrapped
Include：Extract at least one in duration, pace value and the decibel value of the voice for being used to encrypt.Correspondingly, described use is extracted
In the characteristic parameter of the voice of decryption, preferably include：In the duration, pace value and the decibel value that extract the voice for being used to decrypt
At least one.The specific which type of characteristic parameter for extracting the voice for being used to decrypt, depending on preservation to described
The type of the characteristic parameter of the voice of encrypted information encryption.
Wherein, extracting the pace value of the voice for being used to decrypt can both include obtaining phase in the decryption character string
Time interval between adjacent two characters；The duration for obtaining the voice for being used to decrypt can also be included, according to the duration
And the quantity for decrypting character in character string, obtain the pace value of the voice for being used to decrypt.
Similar with previous embodiment two, here is omitted.
Wherein, the decibel value of the voice for being used to decrypt is extracted, can obtain the voice for being used to decrypt to be known
Decibel value after not on each time point；Or can also be the decibel for obtaining each character in the decryption character string
Value.
Embodiment five
Referring to Fig. 5, decrypting the structural representation of device for a kind of voice that the embodiment of the present invention five is provided.The device bag
Include：Sound identification module 51, characteristic extracting module 52, matching module 53 and deciphering module 54.
Wherein, identification module 51, which is used to recognize, is used to, to being encrypted the voice that information is decrypted, obtain decrypting character sequence
Row；Characteristic parameter extraction module 52 is used for the characteristic parameter for extracting the voice for being used to decrypt；Matching module 53 is used for institute
State the characteristic parameter and the encrypted characters sequence and characteristic parameter point of preservation of decryption character string and the voice for being used to decrypt
Do not matched, the encrypted characters sequence and the encrypted characters sequence that characteristic parameter is the voice to the encrypted information encryption
Row and characteristic parameter；After deciphering module 54 is for the match is successful, with the decryption character string or the encrypted characters sequence pair
The encrypted information is decrypted.
The technical scheme of the present embodiment, by extracting the characteristic parameter of voice during decryption, and in decryption character
Sequence and the characteristic parameter of extraction and the encrypted characters sequence and characteristic parameter that preserve are in the case that the match is successful respectively, with decryption
The encrypted information of character string or encrypted characters sequence pair is decrypted, relative to prior art only to decryption character string and
Encrypted characters sequence carries out matching and adds decoding difficulty, improves the security of information.
In such scheme, characteristic extracting module 52 preferably includes time extracting sub-module, word speed extracting sub-module and divided
At least one in shellfish extracting sub-module.
Wherein, time extracting sub-module is used for the duration for extracting the voice for being used to decrypt；Word speed extracting sub-module is used
In the pace value for extracting the voice for being used to decrypt；Decibel extracting sub-module is used for point for extracting the voice for being used to decrypt
Shellfish value.
The word speed extracting sub-module is preferred for performing at least one of following：
Obtain the time interval between two neighboring character in the decryption character string；
The duration of the voice for being used to decrypt is obtained, according to the number of character in the duration and the decryption character string
Amount, obtains the pace value of the voice for being used to decrypt.
The decibel extracting sub-module is preferred for：Obtain after the voice for being used to decrypt is identified at each time point
On decibel value；Or obtain the decibel value of each character in the decryption character string.
In such scheme, the matching module 53 specifically can be used for：Judge the feature of the voice for being used to decrypt
Whether the value of parameter is in the range of the predetermined deviation of the value of the characteristic parameter of the preservation, if the spy of the voice for being used to decrypt
The value of parameter is levied in the range of the predetermined deviation, then the match is successful.
Voice decryption device provided in an embodiment of the present invention can perform the voice decryption that any embodiment of the present invention is provided
Method, possesses the corresponding functional module of execution method and beneficial effect.
Finally it should be noted that：Various embodiments above is merely to illustrate technical scheme, rather than it is limited
System；In embodiment preferred embodiment, not it is limited, to those skilled in the art, the present invention can be with
There are various changes and change.All any modification, equivalent substitution and improvements made within spirit and principles of the present invention etc.,
It should be included within protection scope of the present invention.
Claims (10)
1. a kind of speech ciphering method, it is characterised in that including：
The character in the voice for encryption is recognized, encrypted characters sequence is obtained；
Extract the characteristic parameter of the voice for being used to encrypt；
It is encrypted with the obtained encrypted characters sequence pair of identification information to be encrypted, and preserves the encrypted characters sequence
And the characteristic parameter, for when decryption obtains described information, the spy of the voice with decryption character string and for decryption
Parameter is levied to be matched；
Wherein, the characteristic parameter of voice encrypted is used for described in the extraction, including：
Extract at least one in duration, pace value and the decibel value of the voice for being used to encrypt；
At least one of wherein, for the pace value for the voice encrypted described in extracting, including following：
Obtain the time interval between two neighboring character in the encrypted characters sequence；
The duration of the voice for being used to encrypt is obtained, according to the quantity of character in the duration and the encrypted characters sequence,
Obtain the pace value of the voice for being used to encrypt.
2. according to the method described in claim 1, it is characterised in that extract the decibel value of the voice for being used to encrypt, including：
Obtain the decibel value on each time point after the voice for being used to encrypt is identified；Or
Obtain the decibel value of each character in the encrypted characters sequence.
3. a kind of voice encryption device, it is characterised in that including：
Sound identification module, for recognizing the character in the voice for encryption, obtains encrypted characters sequence；
Characteristic extracting module, the characteristic parameter for extracting the voice for being used to encrypt；
Encrypting module, for recognizing that obtained encrypted characters sequence pair information to be encrypted is entered with the sound identification module
Row encryption, and the encrypted characters sequence and the characteristic parameter are preserved, for when decryption obtains described information, with decryption
Character string and characteristic parameter for the voice of decryption are matched；
Wherein, the characteristic extracting module includes at least one following submodule：
Time extracting sub-module, the duration for extracting the voice for being used to encrypt；
Word speed extracting sub-module, the pace value for extracting the voice for being used to encrypt；
Decibel extracting sub-module, the decibel value for extracting the voice for being used to encrypt；
Wherein, the word speed extracting sub-module is at least one of following for performing：
Obtain the time interval between two neighboring character in the encrypted characters sequence；
The duration of the voice for being used to encrypt is obtained, according to the quantity of character in the duration and the encrypted characters sequence,
Obtain the pace value of the voice for being used to encrypt.
4. device according to claim 3, it is characterised in that the decibel extracting sub-module is used for：
Obtain the decibel value on each time point after the voice for being used to encrypt is identified；Or
Obtain the decibel value of each character in the encrypted characters sequence.
5. a kind of voice decryption method, it is characterised in that including：
Recognize for being encrypted the voice that information is decrypted, obtaining decrypting character string；
Extract the characteristic parameter of the voice for being used to decrypt；
By the characteristic parameter of the decryption character string and the voice for being used to decrypt and the encrypted characters sequence preserved and spy
Levy parameter to be matched respectively, the encrypted characters sequence and characteristic parameter are adding to the voice of the encrypted information encryption
Close character string and characteristic parameter；
After the match is successful, it is decrypted with information is encrypted described in the decryption character string or the encrypted characters sequence pair；
Wherein, the characteristic parameter of voice decrypted is used for described in the extraction, including：
Extract at least one in duration, pace value and the decibel value of the voice for being used to decrypt.
At least one of wherein, for the pace value for the voice decrypted described in extracting, including following：
Obtain the time interval between two neighboring character in the decryption character string；
The duration of the voice for being used to decrypt is obtained, according to the quantity of character in the duration and the decryption character string,
Obtain the pace value of the voice for being used to decrypt.
6. method according to claim 5, it is characterised in that extract the decibel value of the voice for being used to decrypt, including：
Obtain the decibel value on each time point after the voice for being used to decrypt is identified；Or
Obtain the decibel value of each character in the decryption character string.
7. according to any described methods of claim 5-6, it is characterised in that by the characteristic parameter of the voice for being used to decrypt
Matched with the characteristic parameter of preservation, including：
Judge the voice for being used to decrypt characteristic parameter value whether the preservation characteristic parameter value it is default partially
In poor scope, if the value of the characteristic parameter of the voice for being used to decrypt is in the range of the predetermined deviation, the match is successful.
8. a kind of voice decrypts device, it is characterised in that including：
Sound identification module, is used to, to being encrypted the voice that information is decrypted, obtain decrypting character string for recognizing；
Characteristic extracting module, the characteristic parameter for extracting the voice for being used to decrypt；
Matching module, for by it is described decryption character string and it is described be used for decrypt voice characteristic parameter with preserve encryption
Character string and characteristic parameter are matched respectively, and the encrypted characters sequence and characteristic parameter are that the encrypted information is added
The encrypted characters sequence and characteristic parameter of close voice；
Deciphering module, after the match is successful, is encrypted with described in the decryption character string or the encrypted characters sequence pair
Information is decrypted；
Wherein, the characteristic extracting module includes at least one following submodule：
Time extracting sub-module, the duration for extracting the voice for being used to decrypt；
Word speed extracting sub-module, the pace value for extracting the voice for being used to decrypt；
Decibel extracting sub-module, the decibel value for extracting the voice for being used to decrypt.
Wherein, the word speed extracting sub-module is at least one of following for performing：
Obtain the time interval between two neighboring character in the decryption character string；
The duration of the voice for being used to decrypt is obtained, according to the quantity of character in the duration and the decryption character string,
Obtain the pace value of the voice for being used to decrypt.
9. device according to claim 8, it is characterised in that the decibel extracting sub-module is used for：
Obtain the decibel value on each time point after the voice for being used to decrypt is identified；Or
Obtain the decibel value of each character in the decryption character string.
10. according to any described devices of claim 8-9, it is characterised in that the matching module specifically for：
Judge the voice for being used to decrypt characteristic parameter value whether the preservation characteristic parameter value it is default partially
In poor scope, if the value of the characteristic parameter of the voice for being used to decrypt is in the range of the predetermined deviation, the match is successful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410592233.5A CN104361886B (en) | 2014-10-29 | 2014-10-29 | Speech ciphering method and device and voice decryption method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410592233.5A CN104361886B (en) | 2014-10-29 | 2014-10-29 | Speech ciphering method and device and voice decryption method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104361886A CN104361886A (en) | 2015-02-18 |
| CN104361886B true CN104361886B (en) | 2017-11-03 |
Family
ID=52529142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410592233.5A Active CN104361886B (en) | 2014-10-29 | 2014-10-29 | Speech ciphering method and device and voice decryption method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104361886B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812573A (en) * | 2016-04-28 | 2016-07-27 | 努比亚技术有限公司 | Voice processing method and mobile terminal |
| CN116781417B (en) * | 2023-08-15 | 2023-11-17 | 北京中电慧声科技有限公司 | Anti-cracking voice interaction method and system based on voice recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000647A (en) * | 2007-01-08 | 2007-07-18 | 北京飞天诚信科技有限公司 | Method and device for raising safety of data input |
| CN101409819A (en) * | 2008-11-27 | 2009-04-15 | 杭州电子科技大学 | Method for encrypting and deciphering digital camera picture based on voiceprint |
| CN102073829A (en) * | 2011-01-10 | 2011-05-25 | 杭州电子科技大学 | Document encrypting method and document decrypting method on basis of voice print |
| CN102819702A (en) * | 2012-07-19 | 2012-12-12 | 腾讯科技（深圳）有限公司 | File encryption operation method and file encryption operation system |
| CN103118002A (en) * | 2012-12-21 | 2013-05-22 | 北京飞漫软件技术有限公司 | Method of speech sound used as secret key to achieve data resource cloud storage management |
| CN103699834A (en) * | 2013-09-11 | 2014-04-02 | 李霆 | Multifunctional virtual vault and data encrypting method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1908249B1 (en) * | 2005-07-27 | 2012-08-15 | International Business Machines Corporation | Systems and method for secure delivery of files to authorized recipients |
-
2014
- 2014-10-29 CN CN201410592233.5A patent/CN104361886B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000647A (en) * | 2007-01-08 | 2007-07-18 | 北京飞天诚信科技有限公司 | Method and device for raising safety of data input |
| CN101409819A (en) * | 2008-11-27 | 2009-04-15 | 杭州电子科技大学 | Method for encrypting and deciphering digital camera picture based on voiceprint |
| CN102073829A (en) * | 2011-01-10 | 2011-05-25 | 杭州电子科技大学 | Document encrypting method and document decrypting method on basis of voice print |
| CN102819702A (en) * | 2012-07-19 | 2012-12-12 | 腾讯科技（深圳）有限公司 | File encryption operation method and file encryption operation system |
| CN103118002A (en) * | 2012-12-21 | 2013-05-22 | 北京飞漫软件技术有限公司 | Method of speech sound used as secret key to achieve data resource cloud storage management |
| CN103699834A (en) * | 2013-09-11 | 2014-04-02 | 李霆 | Multifunctional virtual vault and data encrypting method |
Non-Patent Citations (1)
| Title |
|---|
| 声音的特征;杨小锋;《教师发声训练教程》;北京师范大学出版社;20120630;第19-22页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104361886A (en) | 2015-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8862888B2 (en) | Systems and methods for three-factor authentication | |
| US8577684B2 (en) | Selective security masking within recorded speech utilizing speech recognition techniques | |
| CN107169374A (en) | Encryption and decryption system and method based on vocal print and speech recognition technology | |
| US10341305B2 (en) | Encrypted communications method and communications terminal, and computer storage medium | |
| CN103294961A (en) | Method and device for file encrypting/decrypting | |
| CN107194268A (en) | A kind of information processing method, device, computer installation and readable storage medium storing program for executing | |
| CN104917603B (en) | A kind of information security transfer method receives terminal and sends terminal | |
| CN104393994B (en) | Audio data secure transmission method, system and terminal | |
| CN107533598B (en) | Input method and device of login password of application program and terminal | |
| CN103377347B (en) | File encryption, decryption method and device | |
| CN104361886B (en) | Speech ciphering method and device and voice decryption method and device | |
| WO2017215186A1 (en) | Secure login method and device, and a storage medium | |
| CN108667815A (en) | Block chain secret key encipher-decipher method, device and terminal based on bio-identification | |
| CN102333066A (en) | Network security verification method by employing combination of speaker voice identity verification and account number password protection in online game | |
| CN102377729A (en) | User registration and logon method by combining speaker speech identity authentication and account code protection in network games | |
| CN102368850A (en) | Method for carrying out encryption and decryption on video file on mobile phone | |
| CN102647712A (en) | Mobile phone data encryption method and decryption method | |
| WO2015196642A1 (en) | Data encryption method, decryption method and device | |
| CN110380856A (en) | Terminal device and its voice information processing method, device and storage medium | |
| CN102902933B (en) | Based on the file saving method of file fragmentation process | |
| CN108052828B (en) | Method and device for generating screen recording file, terminal and storage medium | |
| CN106557708A (en) | A kind of method for security protection and system | |
| CN108256343A (en) | Encryption method, device and the decryption method of Shader files, device | |
| CN109995526A (en) | A kind of storage method of key and the call method and device of device, key | |
| CN104580255B (en) | Authentication method and system of the identification equipment based on recognizable code stream to terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |