CN100444188C - Vocal-print puzzle lock system - Google Patents

Abstract

The disclosed sound-groove cipher lock system comprises: a sound-groove key to encipher of decipher the electric data and form the cipher lock; and a validation system included a pre-process part, a feature acquirement part, a training system and a testing system, which can generate eigen value for former key. This invention can improve data security for wide application.

Description

Vocal-print puzzle lock system

Technical field

The present invention relates to a kind of vocal-print puzzle lock system; particularly relate to a kind of use on electronic bits of data; as the vocal-print puzzle lock system of electronic record or electronic bits of data folder etc., this vocal-print puzzle lock can be for fixing or carry setting, to strengthen the safeguard protection of personal electric data.

Background technology

At present, utilize personal biology characteristics to carry out the major technique that identity identification becomes the personal identification identification gradually.On identification technique, recognizable biological characteristic comprises face identification, identification of fingerprint, palmmprint identification, sound-groove identification, the identification of eyeball iris and nuclifort (DNA) ordering pairing identification etc. at present.

Generally only use personal identification number protected at the electronic bits of data safeguard protection, but simple personal identification number can't provide effective safeguard protection, for example password leaks, cracks etc.Therefore, the electronic bits of data safeguard protection must be sought other safeguard measure, utilizes and strengthens the personal identification discriminating function, to promote the security of protection electronic bits of data.If based on framework cost and the practical operation of considering identification technique, can find that sound-groove identification relatively is suitable as the personal identification identification and uses.

Existing vocal print verification method, as No. 490655 " utilizing sound spectrum information to debate method and its device of knowing the user " patent of invention of TaiWan, China patent announcement, it utilizes the distinctive sound spectrum information identification of different users user's identity, and whether process is authorized with the decision user.After this method comprises the steps: that (1) user sends voice, the terminal point of detecting voice; (2) take out phonetic feature in the sound spectrum of these voice certainly; (3) whether decision needs training, if "Yes" then with this phonetic feature as a reference sample, set a boundary simultaneously, if "No" then carries out next step; (4) this phonetic feature and reference sample are carried out the pattern comparison; (5) calculate both spacing according to this comparison result; (6) this result of calculation and setting boundary are compared; (7) determine according to this comparative result whether this user is the authorized user.This method can be used on the mobile phone, utilizes the unique information taking-up of voice print analysis method with voice, carries out the identification user.Mainly utilize for No. 490655 the main value of each time-frame (frame) and the boundary of user's setting to compare, behind the initial point and terminal point of decision voice, the speech sound signal that utilizes the conversion of Princen-Bradley wave filter to detect again is so that obtain corresponding found spectrogram.This found spectrogram is compared with the reference sound spectrum sample that stores in advance, with identification user's vocal print.

In brief, No. 490655 needs carry out the computing of the coupling and the distance of pattern, and when not beyond the mark as if this computing distance, the user can pass through sound-groove identification.Yet, when the computing of coupling of carrying out pattern and distance, must calculate the distance between reference sample and test sample book No. 490655.In fact, the space of the shared data bank of this reference sample is quite big, so it not only needs bigger data bank space and longer archives transmission time of needs.In the safeguard protection of personal electric data, in case when reference sample is excessive, be unsuitable for being carried on the limited Storage Media in storage area.

Therefore, still be necessary further to improve its reference sample big problem that takes up room for No. 490655, so can save the data bank space of storage reference sample, be carried on the limited Storage Media in storage area or install so that be applicable to.

Summary of the invention

Fundamental purpose of the present invention provides a kind of vocal-print puzzle lock system, it utilizes vocal print key (voiceprintkey) electronic bits of data to be encrypted (encrypt) or deciphering (decrypt) computing, to constitute vocal-print puzzle lock, make the present invention have the effect that promotes the electronic bits of data security.

Secondary objective of the present invention provides a kind of vocal-print puzzle lock system, it adopts the vocal print verification system, before training and test acquisition phonetic feature, utilize front-end processing (front-end processing) that efficient voice information is captured from original input voice, with the invalid voice messaging of filtering, make the present invention have the effect that reduces the Data Processing amount and promote discrimination power.

Secondary objective of the present invention provides a kind of vocal-print puzzle lock system, it is in test, utilize front-end processing to reduce efficient voice information, and capture phonetic feature, and utilize Viterbi (Viterbi) algorithm to obtain the most similar path, so that computation model parameter (expectation value of each state and variance) is for storing, when voice training or test, only similar probability gets final product between need computation model parameter and the tested speech feature, to obtain the vocal print eigenwert, make the present invention have the effect of simplifying training and test jobs.

To achieve the above object of the invention, the present invention adopts following technical scheme: this vocal-print puzzle lock system comprises the vocal print key, and it is in order to encrypt electronic bits of data or decrypt operation, to constitute vocal-print puzzle lock.The vocal print verification system is in order to produce the vocal print eigenwert, and this vocal print eigenwert is chosen this vocal print key certainly.Described vocal print verification system comprises front-end processing portion, feature acquisition portion, training system and test macro, so that original input voice data is trained or test jobs.

On training utterance, this training system utilizes this front-end processing portion from the effective training utterance information of this original input voice DAQ; Utilize this feature acquisition portion to capture this effective training utterance feature again; Carry out this effective training utterance information of computing again to obtain the most similar path, so that as model parameter.On tested speech, this test macro utilizes this front-end processing portion from this original input voice DAQ Validity Test voice messaging equally; Utilize this feature acquisition portion to capture this Validity Test phonetic feature again; Carry out similar probability between this tested speech feature of computing and the model parameter again so that the output identification result.

Adopt said structure, by the vocal print verification system, before the acquisition phonetic feature, utilize front-end processing with efficient voice information from original input voice DAQ, with the invalid voice messaging of filtering, so can reduce the Data Processing amount and promote discrimination power.

In addition, the present invention utilizes the vocal print verification system to produce the vocal print key, for example chooses the vocal print eigenwert, utilizes this vocal print key that electronic bits of data is encrypted or decrypt operation, and to constitute vocal-print puzzle lock, this vocal-print puzzle lock is in order to protect this electronic bits of data.

Description of drawings

Fig. 1 is the process flow diagram that vocal-print puzzle lock system adopts the vocal print verification system among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 2 is the synoptic diagram that concerns of the state of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention and sound frame;

Fig. 3 is the sound frame of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention and the original allocation pattern diagram of state;

Fig. 4 is the state exchange synoptic diagram of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 5 is the most similar path synoptic diagram of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 6 is the equal partial frame synoptic diagram of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 7 redistributes sound frame synoptic diagram the first time of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 8 redistributes sound frame synoptic diagram the second time of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Fig. 9 is the optimal allocation sound frame synoptic diagram of the vocal print verification system that vocal-print puzzle lock system adopts among the embodiment of vocal-print puzzle lock system of the present invention;

Figure 10 is the process flow diagram that vocal-print puzzle lock system utilizes fixed vocal-print puzzle lock to encrypt and decipher in first preferred embodiment of vocal-print puzzle lock system of the present invention;

Figure 11 is the process flow diagram that vocal-print puzzle lock system utilizes the Portable vocal-print puzzle lock to encrypt and decipher in second preferred embodiment of vocal-print puzzle lock system of the present invention.

Embodiment

Below in conjunction with accompanying drawing and preferred embodiment purpose of the present invention, feature and beneficial effect are described in further detail.

Preferred embodiment vocal-print puzzle lock system of the present invention adopts a vocal print verification system, so that original input voice data is trained or test jobs.Fig. 1 is the process flow diagram of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.

Referring to Fig. 1, the vocal print verification system 1 that preferred embodiment vocal-print puzzle lock system of the present invention adopts comprises a training system 10 and a test macro 20, so that original input voice data is trained or test jobs.Described vocal print verification system 1 also comprises a front-end processing portion, a feature acquisition portion, a reservoir and an operational part.Described front-end processing portion and feature acquisition portion carry out front-end processing and feature acquisition for this training system 10 and test macro 20, described reservoir is stored for phonetic feature, and described operational part is then with the in addition computing of this store voice feature and input phonetic feature.

When the user enters this vocal print verification system 1, at first import account number, so that confirm identity.Then, this system is according to input account number inquiry data bank, and whether this input account number belongs to is set up.If this input account number is not set up, then enter this training system 10 and carry out the voice training operation, so that the voice data of setting up and storing this input account number.If this input account number is set up, then enter this test macro 20 and carry out the tone testing operation, so that whether the phonetic feature of this input account number of identification meets the voice data that has stored this input account number.

Before the acquisition phonetic feature, utilize this front-end processing portion that efficient voice information is captured in original input voice data, with the invalid voice messaging of filtering.The present invention's detecting comprises in short-term apart from energy (Short-Energy) and zero-crossing rate (Zero-Crossing Rate).The present invention adopts the computing method in conjunction with Gauss's probability distribution, and its equation is as follows:

$b_i\left(\stackrel{\→}{x}\right)=\frac{1}{{\left(2\mathrm{\π}\right)}^{D/2}{\left|{\mathrm{\Σ}}_i\right|}^{1/2}}\exp \{-\frac{1}{2}{(\stackrel{\→}{x}-\stackrel{\→}{u_i})}^{\′}{\mathrm{\Σ}}_i^{-1}(\stackrel{\→}{x}-\stackrel{\→}{u_i})\}---\left(1\right)$

Wherein For original signal with its be divided into several D dimension the sound frame,

I=1 ..., M, for affiliated probability,

Expectation value, ∑ for ground unrest _iVariance for ground unrest.At this, because

In D=256 be a definite value, so its omission will not be calculated, equation (1) is simplified as follows:

$b_i\left(\stackrel{\→}{x}\right)=\frac{1}{{\left|{\mathrm{\Σ}}_i\right|}^{1/2}}\exp \{-\frac{1}{2}{(\stackrel{\→}{x}-\stackrel{\→}{u_i})}^{\′}{\mathrm{\Σ}}_i^{-1}(\stackrel{\→}{x}-\stackrel{\→}{u_i})\}---\left(2\right)$

Exponent arithmetic in the following formula might be excessive on operational data, so after it is taken the logarithm, equation (2) simplification is as follows:

$b_i\left(\stackrel{\→}{x}\right)\ln \left(\frac{1}{{\left|{\mathrm{\Σ}}_i\right|}^{1/2}}\exp \right\{-\frac{1}{2}{(\stackrel{\→}{x}-\stackrel{\→}{u_i})}^{\′}{\mathrm{\Σ}}_i^{-1}(\stackrel{\→}{x}-\stackrel{\→}{u_i})\left\}\right)$

$=\mathrm{<figure-callout\; id="1"\; label="ln"\; filenames="C20051008894400161.png,C20051008894400171.png"\; state="\{\{state\}\}">ln</figure-callout>}\frac{1}{{\left|{\mathrm{\&Sigma;}}_i\right|}^{1/2}}-\frac{1}{2}{(\stackrel{\&RightArrow;}{x}-\stackrel{\&RightArrow;}{u_i})}^{\&prime;}{\mathrm{\&Sigma;}}_i^{-1}(\stackrel{\&RightArrow;}{x}-\stackrel{\&RightArrow;}{u_i})$

$b_i\left(\stackrel{\&RightArrow;}{x}\right)=(-\frac{1}{2})\ln \left|{\mathrm{\&Sigma;}}_i\right|-\frac{1}{2}{(\stackrel{\&RightArrow;}{x}-\stackrel{\&RightArrow;}{u_i})}^{\&prime;}{\mathrm{\&Sigma;}}_i^{-1}(\stackrel{\&RightArrow;}{x}-\stackrel{\&RightArrow;}{u_i})---\left(3\right)$

Capture former input voice data front end 256 points, calculate, then this two number and former input voice data this equation of substitution (3) are carried out computing in short-term apart from the expectation value and the variance of energy and zero-crossing rate.Utilize in short-term and distinguish efficient voice information and invalid voice messaging apart from the distribution probability of energy and zero-crossing rate, with the in addition filtering of invalid voice messaging, not only reduce data quantity, the while also can correctly capture efficient voice information.

When this feature acquisition portion captures feature, the present invention adopts two speech recognition features parameters, it comprises linear prediction cepstral coefficients (Linear Prediction Cepstrum Coefficient, LPCC) and Mel frequency marking cepstrum parameter (Mel Frequency Cepstrum Coefficient, MFCC) both each 12 cepstrum parameters (Cepstral Coefficients) and 12 single order cepstrum parameters (Delta-CepstralCoefficients).With the cepstrum parameter c _nTo the time intercropping partial differential

${\mathrm{\&Delta;c}}_n\left(t\right)=\frac{{\&PartialD;c}_n\left(t\right)}{\&PartialD;t}=\frac{\underset{k=-K}{\overset{K}{\mathrm{\&Sigma;}}}{\mathrm{kc}}_n(t+k)}{\underset{k=-K}{\overset{K}{\mathrm{\&Sigma;}}}{k}^2}---\left(4\right)$

K is for considering sound frame number.

Because the formula (4) of single order cepstrum parameter is too complicated, thus it is simplified, following various be the situation of only considering each two time-frame of front and back, the equation simplification is as follows:

${\mathrm{\&Delta;C}}_n^0[2*C(2,n)+C(1,n)]/5---\left(5\right)$

${\mathrm{\&Delta;C}}_{\mathrm{<figure-callout\; id="1"\; label="n"\; filenames="C20051008894400161.png,C20051008894400171.png"\; state="\{\{state\}\}">n</figure-callout>}}^1=[2*C(3,n)+C(2,n)-C(0,n)]/6---\left(6\right)$

${\mathrm{\&Delta;C}}_n^i=[2*C(i+2,n)+C(i+1,n)-C(i-1,n)-2*C(i-2,n)]/10---\left(7\right)$

${\mathrm{\&Delta;C}}_n^{L-2}=[C(L-1,n)-C(L-3,n)-2*C(L-4,n)]/6---\left(8\right)$

${\mathrm{\&Delta;C}}_n^{L-1}=[-C(L-2,n)-2*C(L-3,n)]/5---\left(9\right)$

Equation (5) is in (9), and Cn is n rank eigenwerts, and L is a time-frame sum in the signal, and i is the time-frame numbering.

The state of the vocal print verification system that Fig. 2 adopts for preferred embodiment vocal-print puzzle lock system of the present invention and sound frame concern synoptic diagram.

On training utterance, voice have the idea of what is called " state ", the variation of mouth type and sound channel when state is pronunciation.Generally speaking, the mouth type of speaking each time necessarily changes, so the feature performance that each state all is voice to be changed.Sometimes a single-tone but might contain a plurality of states.A state also has fixed measure unlike the sound frame, a common state comprises several or dozens of sound frame.

With reference to Fig. 2, first state comprises three sound frames, second state comprises six sound frames and the third state comprises four sound frames.The present invention at first utilizes equal butt formula to suppose between this state and the sound frame to concern.Then, the present invention calculates the parameter of initial model, and it comprises expectation value and variance.Utilize the parameter of this initial model to redistribute between sound frame and the state and concern, to obtain new point of contact.Utilize this new point of contact to recomputate the pairing sound frame of each state again.Repeat to redistribute between sound frame and the state relation again and again and recomputate the pairing sound frame of each state, till maximal phase no longer rises like probability.

Fig. 3 is the sound frame of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention and the original allocation pattern diagram of state.This original allocation pattern three sample voice is for example divided equally action.

At originate mode voice are done to divide equally action, possibly can't divide exactly after dividing equally, unnecessary sound frame is then divided it equally at first and last state.With reference to Fig. 3, in allocation model, sample voice is divided equally must consider 3 points: 1st, first sound frame necessarily belongs to first state; 2nd, last sound frame necessarily belongs to last state; 3rd, the state variation of sound frame has only constant or is changed to the next one.Adopt Gauss to distribute probability to calculate each sound frame and belong to the probability of each state, and utilize the Viterbi algorithm to obtain the most similar path.

Fig. 4 is the state exchange synoptic diagram of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.

With reference to Fig. 4, when three states, the direction of L sound frame possibility state exchange.Be considered as the state that can not belong to playing the fork tone frame, the direction of arrow is considered as may the state variation path.

Fig. 5 is the most similar path synoptic diagram of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.With reference to Fig. 5, the most similar path of acquisition feature has that first state comprises the 1st to 3 sound frame, second state comprises the 4th to 6 sound frame and the third state comprises the 7th to 10 sound frame.

Fig. 6 is the equal partial frame synoptic diagram of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.With reference to Fig. 6, three sample voice are in the originate mode of three states, the distribution after it is adopted and divides equally.After each sample voice of first sample voice is divided equally three sound frames, remain two sound frames and divide configuration first state and second state respectively.Each sample voice of second sample voice is divided equally four sound frames.After each sample voice of the 3rd sample voice is divided equally three sound frames, remain a sound frame and divide configuration first state respectively.After calculating, its maximal phase is 2156 like probability.

Fig. 7 is for redistributing sound frame synoptic diagram the first time of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.With reference to Fig. 7, after redistributing the sound frame for the first time, its maximal phase rises to 3171 like probability.

Fig. 8 is for redistributing sound frame synoptic diagram the second time of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.With reference to Fig. 8, after redistributing the sound frame for the second time, its maximal phase rises to 3571 like probability.

Fig. 9 is the optimal allocation sound frame synoptic diagram of the vocal print verification system of preferred embodiment vocal-print puzzle lock system employing of the present invention.With reference to Fig. 9, after repeatedly redistributing the sound frame, its maximal phase no longer rises like probability 3571, therefore regards it as optimal allocation sound frame.Calculate the expectation value of each state and variance as model parameter, this model parameter can form voiceprint data shelves, can be for being stored in data bank with these vocal print feature shelves.

With reference to Fig. 1, when entering this training system 10 and carry out the voice training operation, machine equation (1) to (9) obtains effective training utterance feature.Then utilize the Viterbi algorithm to obtain the most similar path.Then calculate the expectation value of each state and variance as model parameter, promptly finish the voice training operation.On voice training, its maximal phase, can't and finish the training operation by voice training, thereby must operate this vocal print verification system 1 again during less than a predetermined reference value like probability; Otherwise its maximal phase is like probability during greater than this predetermined reference value, by voice training, thereby model parameter is set at vocal print feature shelves, the general golden key of this vocal print feature shelves utilization encrypted (encryption), and be stored in this vocal print verification system 1.

With reference to Fig. 1, same, when entering this test macro 20 and carry out the tone testing operation, machine equation (1) to (9) obtains the Validity Test phonetic feature.Simultaneously, this vocal print feature document is decrypted (decryption), so that this vocal print verification system 1 carries out vocal print checking operation.

With reference to Fig. 1, then, similar probability between the model parameter of tested speech feature and vocal print feature shelves is carried out computing so that export an identification result.In speech recognition, its minimum similar probability by speech recognition, thereby can enter this vocal print verification system 1 during greater than predetermined reference value; Otherwise its minimum similar probability can't and finish test jobs by speech recognition, thereby must leave this vocal print verification system 1 during less than this predetermined reference value.

The process flow diagram that Figure 10 utilizes fixed vocal-print puzzle lock to encrypt and decipher for the present invention's first preferred embodiment vocal-print puzzle lock system.With reference to Figure 10, the present invention's first preferred embodiment vocal-print puzzle lock system 3 belongs to fixed vocal-print puzzle lock, and it comprises a vocal print key Kc.This vocal print key Kc is in order to encrypt an electronic bits of data or decrypt operation, to constitute this fixed vocal-print puzzle lock.This fixed vocal-print puzzle lock is applicable to personal computer (PC), notes computer (NB), personal digital assistant (PDA) or mobile phone (Mobile Phone) etc.

With reference to Fig. 1 and Figure 10, vocal-print puzzle lock system 3 of the present invention adopts the training system 10 of vocal print verification system 1.This vocal print verification system 1 is in order to produce a vocal print eigenwert, and this vocal print eigenwert is chosen this vocal print key Kc certainly.This training system 10 can provide vocal print feature shelves 31, and it is preferable to capture 32 bytes (byte) by these vocal print feature shelves.Storage end that so-called vocal print key is an electronic bits of data and acquisition end all need to import identical vocal print feature.When the stored electrons data, can utilize the training operation of the training system 10 of this vocal print verification system 1 to obtain this vocal print key Kc in advance.At this moment, this vocal print key Kc is in order to carrying out cryptographic calculation with electronic bits of data shelves 32, and encrypted electronic data shelves have been stored in ad-hoc location, promptly finishes electronic bits of data and encrypts operation.Preferable employing advanced encryption standard of the present invention (Advanced Encryption Standard, AES) and symmetrical expression enciphered method carry out cryptographic calculation.

With reference to Fig. 1 and Figure 10, when the acquisition electronic bits of data, at first utilize general golden key K to be decrypted computing these vocal print feature shelves 31.Then, utilize the test macro 20 of this vocal print verification system 1 to carry out the tone testing operation, so that these vocal print feature shelves 31 are compared with sound import.If when the error of these vocal print feature shelves 31 and sound import is lower than a preset value, look it by the tone testing operation.In case during by the tone testing operation, can allow to open these electronic bits of data shelves 32.Otherwise,, look it not by the tone testing operation if when the error of this vocal print feature shelves 31 and sound import is higher than a preset value.In case during not by the tone testing operation, promptly need leave this vocal-print puzzle lock system 3, and not allow to open these electronic bits of data shelves 32.

The process flow diagram that Figure 11 utilizes the Portable vocal-print puzzle lock to encrypt and decipher for the present invention's second preferred embodiment vocal-print puzzle lock system.With reference to Figure 11, the present invention's second preferred embodiment vocal-print puzzle lock system 4 belongs to the Portable vocal-print puzzle lock.This vocal print key Kc is in order to encrypt an electronic bits of data or decrypt operation, to constitute this Portable vocal-print puzzle lock.This Portable vocal-print puzzle lock is applicable to CD (CD), floppy disk (Floppy Disk), carry-on dish (Flash Disk), magneto-optic disk (MO Disk) or Network Transmission etc.

With reference to Fig. 1 and Figure 11, vocal-print puzzle lock system 4 of the present invention adopts the training system 10 of vocal print verification system 1, and this training system 10 can provide vocal print feature shelves 41.This vocal print verification system 1 is in order to produce a vocal print eigenwert, and this vocal print eigenwert is chosen this vocal print key Kc certainly.When the stored electrons data, can utilize the training operation of the training system 10 of this vocal print verification system 1 to obtain this vocal print key Kc in advance.At this moment, these vocal print feature shelves 41 are embedded these electronic bits of data shelves 42, promptly these vocal print feature shelves 41 only account for 2K to the 6K byte of these electronic bits of data shelves 42.Utilize this vocal print key Kc that these electronic bits of data shelves 42 are carried out cryptographic calculation, to produce encrypted electronic data shelves; Utilize general golden key K that these vocal print feature shelves 41 are carried out cryptographic calculation simultaneously, produce encrypting vocal print feature shelves, and should encrypt vocal print feature shelves and encrypted electronic data shelves are connected, connect grades 40 to obtain one.In addition, this is encrypted the series connection shelves 40 of vocal print feature shelves and encrypted electronic data shelves through message authentication code generation mechanism generation message authentication code.The spuious algorithm of the preferable employing safety of the present invention (Secure Hash Algorithm is called for short SHA) produces the message authentication code, and utilizes general golden key K that this message authentication code is carried out cryptographic calculation, to produce the scrambled message authentication code.These encrypted electronic data shelves, encryption vocal print feature shelves and scrambled message authentication code form Portable archives, promptly finish electronic bits of data and encrypt operation, and it can transmit via network or recording medium.

With reference to Fig. 1 and Figure 11, when computer system acquisition electronic bits of data, at first should encrypt the general golden key K of vocal print feature shelves and the utilization of scrambled message authentication code and be decrypted computing, to obtain this vocal print feature shelves 41 and message authentication code.Then, utilize the test macro 20 of this vocal print verification system 1 to carry out the tone testing operation, so that these vocal print feature shelves 41 are compared with sound import.If when the error of these vocal print feature shelves 41 and sound import is lower than a preset value, look it by the tone testing operation.In case during by the tone testing operation, can allow to open this electronic bits of data shelves 42 by this vocal print key Kc.Otherwise,, look it not by the tone testing operation if when the error of this vocal print feature shelves 41 and sound import is higher than a preset value.In case during not by the tone testing operation, promptly need leave this vocal-print puzzle lock system 4, and not allow to open these electronic bits of data shelves 42.

With reference to Figure 11, last, these vocal print feature shelves 41 and electronic bits of data shelves 42 are carried out the authentication code comparison with the message authentication code.If when these vocal print feature shelves 41 and electronic bits of data shelves 42 met the message authentication code, these electronic bits of data shelves 42 can be shown in this computer system.Otherwise when if these vocal print feature shelves 41 and electronic bits of data shelves 42 do not meet the message authentication code, these electronic bits of data shelves 42 can't be shown in this computer system, and need leave this vocal-print puzzle lock system 4.

Above-mentioned embodiment describes the present invention with preferred embodiment, but the example of this imagery of just lifting for the ease of understanding should not be considered to be limitation of the scope of the invention.Equally, according to the description of technical scheme of the present invention and preferred embodiment thereof, can make various possible being equal to and change or replacement, and all these changes or replacement all should belong to the protection domain of claim of the present invention.

Claims (9)

1, a kind of vocal-print puzzle lock system is characterized in that, described vocal-print puzzle lock system belongs to the Portable vocal-print puzzle lock, and this system comprises:

The vocal print key is in order to encrypt electronic data and decrypt operation, to constitute vocal-print puzzle lock; And

Vocal print feature shelves, in order to produce the vocal print eigenwert, this vocal print eigenwert is chosen described vocal print key certainly;

Utilize a gold medal key that these vocal print feature shelves are carried out cryptographic calculation, utilize this vocal print key that this electronic data is carried out cryptographic calculation again, and will encrypt vocal print feature shelves and the encrypted electronic data are connected, to obtain series connection shelves;

Wherein when the error of described vocal print feature shelves and sound import is lower than default value, be considered as, in case during by the tone testing operation, promptly allow to open this electronic data by the tone testing operation;

Wherein when the error of described vocal print feature shelves and sound import is higher than this default value, be considered as, in case during not by the tone testing operation, promptly need leave this vocal-print puzzle lock system, and not allow to open this electronic data not by the tone testing operation.

2, vocal-print puzzle lock system as claimed in claim 1 is characterized in that, utilizes golden key that described vocal print feature shelves are carried out cryptographic calculation, and encrypting this vocal print feature shelves, and described golden key is also in order to be decrypted computing with these vocal print feature shelves.

3, vocal-print puzzle lock system as claimed in claim 1, it is characterized in that, utilize message authentication code generation mechanism that the series connection shelves of described encryption vocal print feature shelves and encrypted electronic data are produced the message authentication code, when deciphering, described message authentication code and this vocal print feature shelves and electronic data carry out the authentication code comparison.

4, vocal-print puzzle lock system as claimed in claim 3 is characterized in that, utilizes golden key that the message authentication code of described series connection shelves is carried out cryptographic calculation, and encrypting this message authentication code, and described golden key is also in order to be decrypted computing with described message authentication code.

5, vocal-print puzzle lock system as claimed in claim 1 is characterized in that, described vocal-print puzzle lock system adopts the vocal print verification system, in order to vocal print feature shelves to be provided.

6, vocal-print puzzle lock system as claimed in claim 5 is characterized in that, described vocal print verification system comprises:

Front-end processing portion in order to carrying out the original input speech data of the described vocal print verification system of front-end processing, thereby finishes and distinguishes efficient voice information and invalid voice messaging, captures efficient voice information again;

Feature acquisition portion is in order to capture the phonetic feature of efficient voice information;

Reservoir is stored this phonetic feature; And

Operational part is with this store voice feature and the in addition computing of input phonetic feature.

7, vocal-print puzzle lock system as claimed in claim 6 is characterized in that, wherein this vocal print verification system comprises a training system in addition and uses this front-end processing portion and feature acquisition portion, to obtain the model parameter of original input speech data.

8, vocal-print puzzle lock system as claimed in claim 7 is characterized in that, wherein this training system utilizes viterbi algorithm to obtain the most similar path in addition, so that the computation model parameter is for storing.

9, vocal-print puzzle lock system as claimed in claim 6 is characterized in that, wherein this vocal print verification system comprises a test macro in addition and uses this front-end processing portion and feature acquisition portion, to obtain the phonetic feature of original input speech data.

Images