CN112164404A - Remote identity authentication method and system based on voiceprint recognition technology - Google Patents
Remote identity authentication method and system based on voiceprint recognition technology Download PDFInfo
- Publication number
- CN112164404A CN112164404A CN202011173448.5A CN202011173448A CN112164404A CN 112164404 A CN112164404 A CN 112164404A CN 202011173448 A CN202011173448 A CN 202011173448A CN 112164404 A CN112164404 A CN 112164404A
- Authority
- CN
- China
- Prior art keywords
- personal
- personnel
- voiceprint
- information
- identity information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/04—Training, enrolment or model building
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/12—Score normalisation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/18—Artificial neural networks; Connectionist approaches
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
Abstract
The invention discloses a remote identity authentication method and a system based on voiceprint recognition technology, wherein the remote identity authentication method comprises the following steps: collecting personal voice samples and personal identity information of related personnel; generating a personal recognition model by using the personal voice sample; associating the personal identification model with the personal identity information; collecting a plurality of personal identification models and a plurality of personal identity information to generate a related personnel identification model library; collecting personal voiceprint information of an identified person; primarily confirming the personal identity information of the identified personnel in a related personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method; secondly, confirming the personal identity information of the identified personnel by using the personal voiceprint information and adopting a voiceprint confirmation method; and matching the personal identity information of the verification and identification personnel with the qualified personnel list. In the embodiment of the invention, the remote identity authentication method and the remote identity authentication system can ensure that the opposite side is qualified personnel in percentage, ensure that the service skills of the opposite side reach the standard and avoid potential safety hazards.
Description
Technical Field
The invention relates to the technical field of identity authentication, in particular to a remote identity authentication method and system based on voiceprint recognition technology.
Background
The safety of the power grid is regulated, and a work ticket issuer, a work responsible person and a work licensor (called three persons for short) need to take a qualification test of three persons every year and publish the qualification test in a form of a letter after the qualification test is passed; in addition, the on-duty dispatcher and the on-duty personnel of the operation units who are in scheduling business connection with the upper-level scheduling mechanism must pass the certification training and the qualification assessment of the scheduling mechanism organization and acquire the qualification; the dispatching business confirms the identity in a self-reporting name mode through telephone contact, so if the opposite side does not pass the qualification examination of 'three persons' and does not have the qualification, the work is carried out in a mode of misrepresenting the names of qualified personnel, and due to insufficient safety consciousness and weak business skills, great potential safety hazards exist.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a remote identity authentication method and a remote identity authentication system based on voiceprint recognition technology.
Correspondingly, the embodiment of the invention provides a remote identity authentication method based on voiceprint recognition technology, which is characterized by comprising the following steps:
collecting personal voice samples and personal identity information of related personnel;
generating a personal recognition model using the personal voice sample;
associating the personal identification model with the personal identity information;
collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
collecting personal voiceprint information of an identified person;
preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
secondly, confirming the personal identity information of the identified personnel by using the personal voiceprint information and a voiceprint confirmation method;
and matching and checking the personal identity information of the identified personnel and the qualified personnel list.
In an alternative embodiment, the generating a personal recognition model using the personal voice sample includes:
extracting a personal voice MFCC feature of the personal voice sample;
and training the MFCC characteristics of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
In an optional embodiment, the preliminarily confirming the personal identity information of the identified person in the relevant person identification model library by using the personal voiceprint information and using a voiceprint recognition method includes:
comparing the personal voiceprint information with the relevant person identification model base, and obtaining a similarity score of the personal model in the relevant person model base by combining a probability model method;
and carrying out similarity scoring judgment on the similarity scoring, and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
In an optional embodiment, the probability model is obtained based on a gaussian mixture algorithm and by weighting with M multi-bit gaussian distributions.
In an optional embodiment, the secondarily confirming the personal identity information of the identified person by using the personal voiceprint information and using a voiceprint confirmation method includes:
recognizing the voiceprint identity information in the personal voiceprint information by utilizing a voice recognition technology;
carrying out consistency judgment on the voiceprint identity information and the personal identity information of the identified personnel to obtain a consistency judgment result;
and confirming the personal identity information of the identified personnel secondarily according to the consistency judgment result.
In an optional embodiment, the matching and verifying the individual identity information of the identified person and the qualified person list includes:
inputting a qualified personnel list;
judging whether the personal identity information of the identified personnel is in the qualified personnel list;
and if the personal identity information of the identified personnel is not in the qualified personnel list, generating a voice alarm signal.
In addition, an embodiment of the present invention further provides a remote identity authentication system, where the remote identity authentication system includes:
a sample collection module: the system is used for collecting personal voice samples and personal identity information of related personnel;
a model generation module: for generating a personal recognition model using the personal speech sample;
a correlation module: for associating the personal identification model with the personal identity information;
a model library generation module: the system is used for collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
the voiceprint acquisition module: the system is used for collecting personal voiceprint information of an identified person;
a voiceprint recognition module: the system is used for preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
a voiceprint confirmation module: the voice print confirmation method is used for secondarily confirming the personal identity information of the identified personnel by utilizing the personal voice print information;
a matching and checking module: and the personal identity information of the identified personnel is matched and verified with the qualified personnel list.
In an optional embodiment, the model generation module comprises:
a feature extraction unit: a personal speech MFCC feature for extracting the personal speech sample;
a model generation unit: the voice recognition system is used for training the MFCC features of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
In an alternative embodiment, the voiceprint recognition module comprises:
an alignment unit: the system is used for comparing the personal voiceprint information with the relevant personnel identification model base and obtaining the similarity score of the personal model in the relevant personnel model base by combining a probability model method;
a confirmation unit: and the system is used for carrying out similarity scoring judgment on the similarity scoring and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
In an optional embodiment, the voiceprint confirmation module comprises:
an identification unit: the voice print identification information is used for identifying voice print identity information in the personal voice print information by utilizing a voice recognition technology;
a consistency determination unit: the voice print identification information is used for carrying out consistency judgment on the voice print identification information and the personal identification information of the identified personnel to obtain a consistency judgment result;
a secondary confirmation unit: and the personal identity information of the identified personnel is secondarily confirmed according to the consistency judgment result.
The embodiment of the invention provides a remote identity authentication method and a remote identity authentication system based on a voiceprint recognition technology, when a dispatching service is developed, the remote identity authentication method and the remote identity authentication system can be combined with the voiceprint recognition identity authentication technology and a voice recognition identity authentication technology to intelligently identify whether an opposite side is qualified personnel, if the personal identity information of the identified personnel is not in a qualified personnel list, a voice alarm signal is generated, a dispatcher can be reminded of paying attention to the identity of the identified personnel in a voice alarm mode, a blind spot that the dispatching telephone service cannot identify the identity of the opposite side is eliminated, the identity of the opposite side is confirmed in percentage, the opposite side is ensured to be qualified personnel, the service skill of the opposite side is ensured to reach the standard, and potential safety hazards are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a remote identity authentication method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of S12 according to the embodiment of the present invention;
FIG. 3 is a flowchart illustrating a detailed process of S16 according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a detailed process of S17 according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating the detailed process of S18 according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a remote identity authentication system according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of the components of a model generation module in an embodiment of the invention;
FIG. 8 is a block diagram of a voiceprint recognition module according to an embodiment of the present invention;
FIG. 9 is a block diagram of a voiceprint validation module in accordance with an embodiment of the present invention;
fig. 10 is a schematic diagram of the matching check module according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart illustrating a remote identity authentication method according to an embodiment of the present invention.
The embodiment of the invention provides a remote identity authentication method based on a voiceprint recognition technology, which comprises the following steps:
s11: collecting personal voice samples and personal identity information of related personnel;
firstly, the personal voice sample and the personal identity information of the relevant person need to be collected, in the embodiment of the invention, the relevant person refers to an on-duty dispatcher who performs dispatching business contact with a superior dispatching mechanism or an on-duty person of an operation unit, and the like, and the sufficient personal voice sample of the relevant person needs to be collected in sequence, and meanwhile, the personal identity information of the relevant person, namely the name of the relevant person, is collected.
S12: generating a personal recognition model using the personal voice sample;
fig. 2 is a schematic diagram of a specific flow of S12 in the embodiment of the present invention.
In the embodiment of the present invention, generating a personal recognition model by using the personal voice sample specifically includes:
s121: extracting a personal voice MFCC feature of the personal voice sample;
it should be noted that MFCC is an abbreviation of Mel-frequency cepstrum coefficient, Mel frequency is extracted based on human auditory characteristics, and is in nonlinear correspondence with Hz frequency, MFCC is Hz spectrum feature calculated by using the relationship between them.
Extracting the MFCC features of the personal voice sample, which specifically comprises the following steps:
pre-filtering: the bandwidth of the front end of the CODEC is 300-3400 Hz;
A/D conversion: sampling frequency of 8kHz, linear quantization precision of 12 bit;
pre-emphasis: the frequency spectrum of the signal becomes flat through a first-order finite excitation response high-pass filter, and the influence of finite word length effect is not easy to affect;
framing: according to the short-time stable characteristic of voice, a personal voice sample can be processed by taking a frame as a unit, the length of a specifically selected voice frame is 32ms, and the frame stacking is 16 ms;
windowing: windowing a frame of speech by using a Hamming window to reduce the effect of the Gibbs effect;
fast Fourier transform: transforming the time domain signal into a power spectrum of the signal;
triangular window filtering: filtering the power spectrum of the signal by using a group of triangular window filters (24 triangular window filters in total) which are linearly distributed on the Mel frequency scale, wherein the coverage range of each triangular window filter is similar to a critical bandwidth of a human ear, so as to simulate the masking effect of the human ear;
logarithm calculation: the logarithm is solved from the output of the triangular window filter group, and the result similar to homomorphic transformation can be obtained.
Discrete cosine transform: dividing the correlation among signals of all dimensions, and mapping the signals to a low-dimensional space;
spectral weighting: because the low-order parameters of the cepstrum are easily influenced by speaker characteristics, channel characteristics and the like, and the resolution capability of the high-order parameters is low, the spectrum weighting is needed to suppress the low-order and high-order parameters;
difference parameters: the volume experiment shows that the identification performance of the system can be improved by adding the differential parameter representing the dynamic characteristic of the voice into the voice characteristic, and specifically, the first-order differential parameter and the second-order differential parameter of the MFCC parameter are added;
short-time energy: the short-time energy of the voice is also an important characteristic parameter, and the short-time normalized logarithmic energy of the voice and first-order difference and second-order difference parameters thereof are adopted in the system.
S122: and training the MFCC characteristics of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
After the personal voice MFCC features are extracted, the personal voice MFCC features are trained by utilizing a neural network algorithm to generate a personal recognition model.
S13: associating the personal identification model with the personal identity information;
in the embodiment of the present invention, the personal identification model is associated with the personal identity information, so that the personal identification model and the personal identity information generate a binding relationship, that is, the personal identification model and the names of the related persons are associated, so that the personal identification model and the names of the related persons generate a binding relationship.
S14: collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
in the embodiment of the present invention, a plurality of personal identification models of all related persons and a plurality of associated personal identity information are aggregated to generate a related person identification model library, that is, a plurality of personal identification models of all related persons and a plurality of associated names are aggregated to generate a related person identification model library.
S15: collecting personal voiceprint information of an identified person;
when the dispatching service is carried out, personal voiceprint information of the identified personnel is collected in real time through the telephone.
S16: preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
the voiceprint recognition is a process of selecting one from more than one, namely judging which person in the relevant person identification model library the voiceprint information to be tested belongs to; the voiceprint recognition comprises open set recognition and closed set recognition, the open set recognition means that the voiceprint information to be tested does not belong to any bit in the relevant personnel recognition model base, and the closed set recognition means that the voiceprint information to be tested does not necessarily belong to any bit in the relevant personnel recognition model base.
Fig. 3 is a schematic diagram of a specific flow of S16 in the embodiment of the present invention.
In an embodiment of the present invention, the preliminarily confirming the personal identity information of the identified person in the relevant person identification model library by using the personal voiceprint information and using a voiceprint recognition method specifically includes:
s161: comparing the personal voiceprint information with the relevant person identification model base, and obtaining a similarity score of the personal model in the relevant person model base by combining a probability model method;
preferably, the probability model method is obtained by weighting M multi-bit Gaussian distributions based on a Gaussian mixture algorithm, and the accuracy of similarity scoring can be effectively improved.
S162: and carrying out similarity scoring judgment on the similarity scoring, and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
Judging similarity score, namely judging that the personal voiceprint information belongs to a personal identification model when the similarity score between the personal voiceprint information and a personal identification model in the related personnel identification model base is higher than a preset value, and confirming the personal identity information of the identification personnel according to the incidence relation of the personal identification model, namely confirming the name of the identification personnel; and when the similarity score between the personal voiceprint information and the personal identification model in the related person identification model library is lower than a preset value, judging that the identified person is not a qualified person.
S17: secondly, confirming the personal identity information of the identified personnel by using the personal voiceprint information and a voiceprint confirmation method;
voiceprint validation, which is the determination of whether the voiceprint information to be tested is from the target person, is a "one-to-one" decision problem.
Fig. 4 is a schematic diagram of a specific flow of S17 in the embodiment of the present invention.
The secondary confirmation of the personal identity information of the identified person by using the personal voiceprint information and a voiceprint confirmation method specifically comprises the following steps:
s171: recognizing the voiceprint identity information in the personal voiceprint information by utilizing a voice recognition technology;
in order to improve voiceprint confirmation efficiency, in the embodiment of the present invention, a text-related manner used for voiceprint confirmation is a text-related manner that an identification person must pronounce according to a text content specified in advance, and in a specific implementation, the identification person needs to self-report a name, and a voice recognition technology is used to identify voiceprint identity information in the personal voiceprint information, that is, to identify a name included in the personal voiceprint information.
S172: carrying out consistency judgment on the voiceprint identity information and the personal identity information of the identified personnel to obtain a consistency judgment result;
in the embodiment of the present invention, the name of the self-reported person is recognized, and at the same time, the name of the recognition person is preliminarily confirmed in step S16, and the consistency between the voiceprint identity information and the personal identity information of the recognition person is determined to obtain a consistency determination result, that is, the consistency between the name of the self-reported person and the name of the recognition person preliminarily confirmed in step S16 is determined to obtain a consistency determination result.
S173: and confirming the personal identity information of the identified personnel secondarily according to the consistency judgment result.
In the embodiment of the present invention, when the consistency determination result is consistent, the personal identity information of the identifier may be secondarily confirmed, and when the consistency determination result is inconsistent, it is determined that the identifier is not a qualified person for the sake of safety.
S18: matching and checking the personal identity information of the identified personnel with a qualified personnel list;
fig. 5 is a schematic diagram of a specific flow of S18 in the embodiment of the present invention.
In the embodiment of the present invention, the matching and checking the personal identity information of the identified person and the qualified person list specifically includes:
s181: inputting a qualified personnel list;
s182: judging whether the personal identity information of the identified personnel is in the qualified personnel list;
s183: if the personal identity information of the identified personnel is not in the qualified personnel list, generating a voice alarm signal;
in the embodiment of the invention, firstly, a qualified personnel list is required to be input, wherein the qualified personnel refer to personnel who pass a qualification test of 'three people' and obtain an ordered qualification, and the qualified personnel list comprises names of the qualified personnel; then, judging whether the personal identity information of the identified personnel is in the qualified personnel list, if so, ensuring that the opposite party is qualified personnel and carrying out scheduling service; if the personal identity information of the identified personnel is not in the qualified personnel list, a voice alarm signal is generated, and a dispatcher can be reminded of paying attention to the identity of the identified personnel in a voice alarm mode.
Fig. 6 is a schematic diagram of a specific configuration of a remote identity authentication system according to an embodiment of the present invention.
In addition, an embodiment of the present invention provides a remote identity authentication system based on a voiceprint recognition technology, where the remote identity authentication system includes:
a sample collection module: the system is used for collecting personal voice samples and personal identity information of related personnel;
a model generation module: for generating a personal recognition model using the personal speech sample;
FIG. 7 is a schematic diagram of a model generation module according to an embodiment of the present invention.
Specifically, the model generation module includes:
a feature extraction unit: a personal speech MFCC feature for extracting the personal speech sample;
a model generation unit: the voice recognition system is used for training the MFCC features of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
A correlation module: for associating the personal identification model with the personal identity information;
a model library generation module: the system is used for collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
the voiceprint acquisition module: the system is used for collecting personal voiceprint information of an identified person;
a voiceprint recognition module: the system is used for preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
FIG. 8 is a block diagram of a voiceprint recognition module according to an embodiment of the invention.
Specifically, the voiceprint recognition module includes:
an alignment unit: the system is used for comparing the personal voiceprint information with the relevant personnel identification model base and obtaining the similarity score of the personal model in the relevant personnel model base by combining a probability model method;
a confirmation unit: and the system is used for carrying out similarity scoring judgment on the similarity scoring and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
A voiceprint confirmation module: the voice print confirmation method is used for secondarily confirming the personal identity information of the identified personnel by utilizing the personal voice print information;
FIG. 9 is a block diagram of a voiceprint validation module according to an embodiment of the present invention.
Specifically, the voiceprint confirmation module includes:
an identification unit: the voice print identification information is used for identifying voice print identity information in the personal voice print information by utilizing a voice recognition technology;
a consistency determination unit: the voice print identification information is used for carrying out consistency judgment on the voice print identification information and the personal identification information of the identified personnel to obtain a consistency judgment result;
a secondary confirmation unit: and the personal identity information of the identified personnel is secondarily confirmed according to the consistency judgment result.
A matching and checking module: and the personal identity information of the identified personnel is matched and verified with the qualified personnel list.
Fig. 10 is a schematic diagram of the matching check module according to the embodiment of the present invention.
Specifically, the matching check module includes:
an entry unit: the system is used for inputting a qualified personnel list;
a list judgment unit: the personal identity information of the identified personnel is judged whether to be in the qualified personnel list or not;
a voice alarm unit: for generating a voice alarm signal;
the embodiment of the invention provides a remote identity authentication method and a remote identity authentication system based on a voiceprint recognition technology, when a dispatching service is developed, the remote identity authentication method and the remote identity authentication system can be combined with the voiceprint recognition identity authentication technology and a voice recognition identity authentication technology to intelligently identify whether an opposite side is qualified personnel, if the personal identity information of the identified personnel is not in a qualified personnel list, a voice alarm signal is generated, a dispatcher can be reminded of paying attention to the identity of the identified personnel in a voice alarm mode, a blind spot that the dispatching telephone service cannot identify the identity of the opposite side is eliminated, the identity of the opposite side is confirmed in percentage, the opposite side is ensured to be qualified personnel, the service skill of the opposite side is ensured to reach the standard, and potential safety hazards are avoided.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
In addition, the above detailed description is given to a remote identity authentication method and system based on voiceprint recognition technology according to the embodiments of the present invention, and a specific example should be adopted herein to explain the principle and implementation manner of the present invention, and the description of the above embodiment is only used to help understanding the method and core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A remote identity authentication method based on voiceprint recognition technology is characterized by comprising the following steps:
collecting personal voice samples and personal identity information of related personnel;
generating a personal recognition model using the personal voice sample;
associating the personal identification model with the personal identity information;
collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
collecting personal voiceprint information of an identified person;
preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
secondly, confirming the personal identity information of the identified personnel by using the personal voiceprint information and a voiceprint confirmation method;
and matching and checking the personal identity information of the identified personnel and the qualified personnel list.
2. The remote identity authentication method of claim 1, wherein the generating a personal recognition model using the personal voice sample comprises:
extracting a personal voice MFCC feature of the personal voice sample;
and training the MFCC characteristics of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
3. The remote identity authentication method according to claim 1, wherein the preliminarily confirming the personal identity information of the identified person in the relevant person identification model library by using the personal voiceprint information and a voiceprint recognition method comprises:
comparing the personal voiceprint information with the relevant person identification model base, and obtaining a similarity score of the personal model in the relevant person model base by combining a probability model method;
and carrying out similarity scoring judgment on the similarity scoring, and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
4. The remote identity authentication method of claim 3, wherein the probabilistic model is based on a Gaussian mixture algorithm and is weighted using M multi-bit Gaussian distributions.
5. The remote identity authentication method of claim 1, wherein the secondarily confirming the personal identity information of the identified person by using the personal voiceprint information and a voiceprint confirmation method comprises:
recognizing the voiceprint identity information in the personal voiceprint information by utilizing a voice recognition technology;
carrying out consistency judgment on the voiceprint identity information and the personal identity information of the identified personnel to obtain a consistency judgment result;
and confirming the personal identity information of the identified personnel secondarily according to the consistency judgment result.
6. The remote identity authentication method of claim 1, wherein the matching verifies the individual identity information of the identified person against a list of qualified persons, comprising:
inputting a qualified personnel list;
judging whether the personal identity information of the identified personnel is in the qualified personnel list;
and if the personal identity information of the identified personnel is not in the qualified personnel list, generating a voice alarm signal.
7. A remote identity authentication system based on voiceprint recognition technology, the remote identity authentication system comprising:
a sample collection module: the system is used for collecting personal voice samples and personal identity information of related personnel;
a model generation module: for generating a personal recognition model using the personal speech sample;
a correlation module: for associating the personal identification model with the personal identity information;
a model library generation module: the system is used for collecting a plurality of personal identification models and associated personal identity information to generate a related personnel identification model library;
the voiceprint acquisition module: the system is used for collecting personal voiceprint information of an identified person;
a voiceprint recognition module: the system is used for preliminarily confirming the personal identity information of the identified personnel in the relevant personnel identification model library by utilizing the personal voiceprint information and adopting a voiceprint recognition method;
a voiceprint confirmation module: the voice print confirmation method is used for secondarily confirming the personal identity information of the identified personnel by utilizing the personal voice print information;
a matching and checking module: and the personal identity information of the identified personnel is matched and verified with the qualified personnel list.
8. The remote identity authentication system of claim 7, wherein the model generation module comprises:
a feature extraction unit: a personal speech MFCC feature for extracting the personal speech sample;
a model generation unit: the voice recognition system is used for training the MFCC features of the personal voice by utilizing a neural network algorithm to generate a personal recognition model.
9. The remote identity authentication system of claim 7, wherein the voiceprint recognition module comprises:
an alignment unit: the system is used for comparing the personal voiceprint information with the relevant personnel identification model base and obtaining the similarity score of the personal model in the relevant personnel model base by combining a probability model method;
a confirmation unit: and the system is used for carrying out similarity scoring judgment on the similarity scoring and preliminarily confirming the personal identity information of the identification personnel according to the similarity scoring judgment.
10. The remote identity authentication system of claim 7, wherein the voiceprint validation module comprises:
an identification unit: the voice print identification information is used for identifying voice print identity information in the personal voice print information by utilizing a voice recognition technology;
a consistency determination unit: the voice print identification information is used for carrying out consistency judgment on the voice print identification information and the personal identification information of the identified personnel to obtain a consistency judgment result;
a secondary confirmation unit: and the personal identity information of the identified personnel is secondarily confirmed according to the consistency judgment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011173448.5A CN112164404A (en) | 2020-10-28 | 2020-10-28 | Remote identity authentication method and system based on voiceprint recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011173448.5A CN112164404A (en) | 2020-10-28 | 2020-10-28 | Remote identity authentication method and system based on voiceprint recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112164404A true CN112164404A (en) | 2021-01-01 |
Family
ID=73865064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011173448.5A Pending CN112164404A (en) | 2020-10-28 | 2020-10-28 | Remote identity authentication method and system based on voiceprint recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112164404A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992156A (en) * | 2021-02-05 | 2021-06-18 | 浙江浙达能源科技有限公司 | Power distribution network dispatching identity authentication system based on voiceprint authentication |
| CN113488061A (en) * | 2021-08-05 | 2021-10-08 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
| CN116612762A (en) * | 2023-05-05 | 2023-08-18 | 中山大学附属第六医院 | Voiceprint recognition-based doctor-patient identity verification method, system and device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324232A (en) * | 2011-09-12 | 2012-01-18 | 辽宁工业大学 | Method for recognizing sound-groove and system based on gauss hybrid models |
| CN102780706A (en) * | 2012-08-14 | 2012-11-14 | 俞琳 | User authentication method based on power system service |
| CN103106717A (en) * | 2013-01-25 | 2013-05-15 | 上海第二工业大学 | Intelligent warehouse voice control doorkeeper system based on voiceprint recognition and identity authentication method thereof |
| CN103313249A (en) * | 2013-05-07 | 2013-09-18 | 百度在线网络技术（北京）有限公司 | Reminding method and reminding system for terminal and server |
| CN103971690A (en) * | 2013-01-28 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Voiceprint recognition method and device |
| CN109243465A (en) * | 2018-12-06 | 2019-01-18 | 平安科技（深圳）有限公司 | Voiceprint authentication method, device, computer equipment and storage medium |
| CN110310647A (en) * | 2017-09-29 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of speech identity feature extractor, classifier training method and relevant device |
-
2020
- 2020-10-28 CN CN202011173448.5A patent/CN112164404A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324232A (en) * | 2011-09-12 | 2012-01-18 | 辽宁工业大学 | Method for recognizing sound-groove and system based on gauss hybrid models |
| CN102780706A (en) * | 2012-08-14 | 2012-11-14 | 俞琳 | User authentication method based on power system service |
| CN103106717A (en) * | 2013-01-25 | 2013-05-15 | 上海第二工业大学 | Intelligent warehouse voice control doorkeeper system based on voiceprint recognition and identity authentication method thereof |
| CN103971690A (en) * | 2013-01-28 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Voiceprint recognition method and device |
| CN103313249A (en) * | 2013-05-07 | 2013-09-18 | 百度在线网络技术（北京）有限公司 | Reminding method and reminding system for terminal and server |
| CN110310647A (en) * | 2017-09-29 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of speech identity feature extractor, classifier training method and relevant device |
| CN109243465A (en) * | 2018-12-06 | 2019-01-18 | 平安科技（深圳）有限公司 | Voiceprint authentication method, device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992156A (en) * | 2021-02-05 | 2021-06-18 | 浙江浙达能源科技有限公司 | Power distribution network dispatching identity authentication system based on voiceprint authentication |
| CN113488061A (en) * | 2021-08-05 | 2021-10-08 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
| CN113488061B (en) * | 2021-08-05 | 2024-02-23 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
| CN116612762A (en) * | 2023-05-05 | 2023-08-18 | 中山大学附属第六医院 | Voiceprint recognition-based doctor-patient identity verification method, system and device and storage medium |
| CN116612762B (en) * | 2023-05-05 | 2023-12-26 | 中山大学附属第六医院 | Voiceprint recognition-based doctor-patient identity verification method, system and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112164404A (en) | Remote identity authentication method and system based on voiceprint recognition technology | |
| Sithara et al. | Study of MFCC and IHC feature extraction methods with probabilistic acoustic models for speaker biometric applications | |
| Asda et al. | Development of Quran reciter identification system using MFCC and neural network | |
| CN102496366B (en) | Speaker identification method irrelevant with text | |
| Sekkate et al. | Speaker identification for OFDM-based aeronautical communication system | |
| Mary et al. | Analysis and detection of mimicked speech based on prosodic features | |
| Pati et al. | Speaker information from subband energies of linear prediction residual | |
| Al-Karawi et al. | Using combined features to improve speaker verification in the face of limited reverberant data | |
| Nagaraja et al. | Multilingual speaker identification with the constraint of limited data using multitaper MFCC | |
| Moinuddin et al. | Speaker Identification based on GFCC using GMM | |
| Nagakrishnan et al. | Generic speech based person authentication system with genuine and spoofed utterances: different feature sets and models | |
| Mansour et al. | A comparative study in emotional speaker recognition in noisy environment | |
| Bashar et al. | Text-independent speaker identification system using average pitch and formant analysis | |
| Ranjan | Speaker Recognition and Performance Comparison based on Machine Learning | |
| Al-Qaisi | Arabic word dependent speaker identification system using artificial neural network | |
| Islam | Modified mel-frequency cepstral coefficients (MMFCC) in robust text-dependent speaker identification | |
| Chelali et al. | MFCC and vector quantization for Arabic fricatives speech/speaker recognition | |
| Nguyen et al. | Vietnamese speaker authentication using deep models | |
| Zouhir et al. | Robust speaker recognition based on biologically inspired features | |
| Chaudhari et al. | Effect of varying MFCC filters for speaker recognition | |
| Bora et al. | Speaker identification for biometric access control using hybrid features | |
| Corsi | Speaker recognition: A survey | |
| Iwok et al. | Evaluation of Machine Learning Algorithms using Combined Feature Extraction Techniques for Speaker Identification | |
| CN113823293B (en) | Speaker recognition method and system based on voice enhancement | |
| Badji et al. | Automatic Speaker Recognition (ASR) Application in the monitoring of PLHIV in the cross-border area between the Gambia, Guinea-Bissau and Senegal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210101 |