CN110827453A - Fingerprint and voiceprint double authentication method and authentication system - Google Patents
Fingerprint and voiceprint double authentication method and authentication system Download PDFInfo
- Publication number
- CN110827453A CN110827453A CN201911124141.3A CN201911124141A CN110827453A CN 110827453 A CN110827453 A CN 110827453A CN 201911124141 A CN201911124141 A CN 201911124141A CN 110827453 A CN110827453 A CN 110827453A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- voiceprint
- verification
- voice
- module
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00571—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated by interacting with a central unit
Abstract
A fingerprint and voiceprint dual authentication method comprises fingerprint authentication and voiceprint authentication, wherein the voiceprint authentication mode is specifically that a central control module displays authentication words to an authenticator through an interactive interface, the authenticator repeatedly pronounces the authentication words for more than two times, similarity calculation is conducted on an input voiceprint feature and registered voiceprint features stored by all registered users, if the obtained highest similarity is higher than a set voiceprint threshold value, the registered voiceprint feature user corresponding to the highest similarity is judged to be the authenticator of the input voiceprint feature, otherwise, the authentication fails, after the voiceprint authentication mode judges the authenticator, the user is compared with the authenticator judged by the fingerprint authentication to determine whether the user is the same registered user, if so, the authentication succeeds, and otherwise, the authentication fails. The invention also discloses a fingerprint and voiceprint dual authentication system. The invention avoids the false claiming possibly caused by single verification of the voiceprint lock and the fingerprint lock through dual registration of the fingerprint and the voiceprint and dual verification mode.
Description
Technical Field
The invention belongs to the technical field of safety, relates to an authentication technology, and particularly relates to a fingerprint and voiceprint dual authentication method and an authentication system.
Background
The fingerprint lock is widely applied to public security criminal investigation systems and office anti-theft systems as a coded lock, and gradually enters common people along with the development of smart home. Fingerprints are uneven lines on the skin on the front face of the tail end of a finger, and the lines have proved to contain a large number of characteristics in medicine and are unique and permanent. Fingerprint features are therefore important evidence of identity. Common fingerprint identification is realized by reading a fingerprint image, extracting characteristics, storing data and comparing the data with an algorithm to memorize, verify and identify identities. But current fingerprinting still has some vulnerabilities: 1. the recognition rate is poor due to the influence of various factors such as noise of fingerprint images, nonlinear deformation caused by skin elasticity, pollution indicated by a collector and the like; 2. criminals can still take the impersonation by means of fingerprint impressions left on the surface of the collector or by means of illegal means such as stealing fingerprint characteristic information and the like.
Another coded lock similar to a fingerprint lock is a voiceprint lock, and the voice tone of different people is distinguished through a voiceprint recognition technology to achieve identity recognition. Voiceprint locks are commonly used in access control systems and are commonly used in countries such as japan. With the advent of the intelligent era and the continuous improvement of voiceprint recognition technology, voiceprint locks are gradually entering the home of common people. Voiceprint recognition technologies are classified into text-related technologies, text-unrelated technologies, text prompting technologies and the like. Voiceprint locks are generally based on text correlation or text prompt, and users and impostors can be distinguished only by reciting a short sentence of password specified or self-defined by a system. Common voiceprint recognition algorithms include traditional Dynamic Time Warping (DTW), as well as deep learning based methods. Currently, voiceprint recognition still has some problems: 1. in a noisy environment, the recognition performance is greatly influenced; 2. voiceprint recognition systems still have difficulty avoiding the occurrence of misidentifications. This creates conditions for impersonation.
Disclosure of Invention
In order to overcome the technical defects in the prior art, the invention discloses a fingerprint and voiceprint double authentication method and an authentication system.
The invention is as described
According to the invention, through double registration of the fingerprint and the voiceprint, the verifier can judge that the identification is passed only through two identification processes of voiceprint identification and fingerprint identification at the same time during identification. Therefore, through the double verification mode, the fake collar possibly caused by single verification of the voiceprint lock and the fingerprint lock is avoided.
Drawings
FIG. 1 is a flow chart illustrating a registration process of the method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating an embodiment of an identification process in the method of the present invention;
FIG. 3 is a flowchart illustrating a deletion process in the method according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating an embodiment of the authentication system according to the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
The invention relates to a fingerprint and voiceprint double authentication method, which comprises the following steps:
fingerprint verification and voiceprint verification;
in the fingerprint verification, a verifier carries out similarity calculation on the input fingerprint characteristics and the fingerprint characteristics stored by all registered users, if the obtained highest similarity is higher than a set fingerprint threshold, the fingerprint characteristic user corresponding to the highest similarity is judged as the verifier of the input fingerprint characteristics, otherwise, the verifier fails to judge
The voiceprint verification method specifically comprises the following steps:
the central control module displays a verification language to the verifier through the interactive interface;
after each pronunciation, the voice feature extraction module extracts fbank feature information of the section of voice, and the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice;
voiceprint recognition employs text-dependent voiceprint recognition techniques. The recognition rate of the text related voiceprint recognition is relatively high, the error recognition rate is relatively low, and the requirement on the confidentiality of the coded lock can be met. The voiceprint model corresponding to the text-related voiceprint recognition technology is a deep neural network model (D-vector) and is obtained by training thousands of hours of Chinese corpora, and the method has strong noise immunity and robustness.
If the obtained highest similarity is higher than a set voiceprint threshold value, the registered voiceprint characteristic user corresponding to the highest similarity is judged as a verifier of the voiceprint characteristic input;
and after the verifier is judged by the voiceprint verification mode, the voiceprint verification mode is compared with the verifier judged by the fingerprint verification to judge whether the verifier is the same registered user, if so, the verification is successful, and otherwise, the judgment is failed.
Specifically, as shown in fig. 2, during the identification process, the user first needs to pass the fingerprint verification. In fingerprint verification, a user places a finger, which enters a fingerprint during registration, on a fingerprint collector. Then the fingerprint feature extraction module carries out extraction calculation on the fingerprint features and sends the fingerprint features into the fingerprint identification module. On the other hand, the central processing module reads the fingerprint information of all registered users in the storage unit and sends the fingerprint information to the fingerprint identification module. And then, the fingerprint identification module carries out similarity calculation on the input fingerprint characteristics and the fingerprint characteristics of all users. If the obtained highest similarity is higher than the set fingerprint identification threshold, judging that the fingerprint matches the user corresponding to the highest similarity, and prompting that the fingerprint passes the verification by the voice broadcast module to start voiceprint verification. Otherwise, judging that the user is not matched with any user, and prompting that the verification fails by the voice broadcast module.
After the fingerprint verification is passed, the voiceprint verification can be carried out, and when the voiceprint verification is started, the central control module still displays a verification word to a user through the interaction module. And the voice broadcasting module is used for sounding or the interaction module is used for displaying and prompting the verifier to repeat the verification language.
Every time the voice is repeated, the voice feature extraction module extracts fbank feature information of the voice, the voiceprint recognition module takes the voice feature information fbank as the input of a voiceprint model and outputs the voiceprint feature information to a voiceprint feature d-vector of the voice, and the voice broadcasting module prompts that the input is successful.
After the voice input is finished for many times, averaging the voiceprint characteristics of all the d-vectors to obtain the voiceprint characteristics of the verification, and carrying out similarity calculation on the voiceprint characteristics of all registered users in the storage unit and the current input characteristics by the central processing module. And if the obtained highest similarity is higher than the set voiceprint threshold, judging that the voiceprint matches the user corresponding to the highest similarity. If the highest similarity is lower than the set voiceprint threshold, the voice broadcasting module prompts that the verification fails.
If the fingerprint verification and the voiceprint verification are both successfully matched, comparing whether the matched users are the same registered user, if so, prompting that the verification is successful by the voice broadcasting module, and sending an unlocking command by the central processing module; if not, the voice broadcast module prompts that the verification fails.
Before the system performs authentication, the user needs to register the personal fingerprint and the voiceprint information first, as shown in fig. 1, the registration process before the authentication may specifically be:
the system enters a registration state; prompting the registered user to input identity information;
the system can sound to prompt the user to input the information related to the identity of the user, such as the name, the ID number and the like, through the interaction module.
Fingerprint registration is carried out;
prompting the user to place a finger on the fingerprint collector to collect fingerprint features. Then the fingerprint feature extraction module extracts and calculates the relevant fingerprint features, and the central processing module stores the identity information of the user and the fingerprint features in a storage unit together. Subsequently, the voice broadcast module prompts the user to enter the fingerprint information again to confirm the identity. Similarly, the fingerprint feature extraction module extracts fingerprint related features and sends the fingerprint related features to the fingerprint identification module; on the other hand, the central processing module reads out the fingerprint characteristics stored for the first time from the storage unit and puts the fingerprint characteristics into the fingerprint identification module; the fingerprint identification module calculates the similarity of the two fingerprint characteristics.
If the similarity is lower than a preset fingerprint storage threshold value, the fingerprints recorded twice are judged not to belong to the same person, the fingerprint features stored for the first time and the identity features are deleted simultaneously by the central processing module, and the voice broadcast module prompts that the fingerprint registration fails. If the similarity is higher than a preset fingerprint storage threshold, the voice broadcasting module prompts that the fingerprint registration is successful, and then the voice print registration is started.
The process of voiceprint registration is that the central control module displays the registration words when registering to the user through an interactive interface; the registered user pronounces the registered words for more than two times, the voice feature extraction module extracts fbank feature information of the section of voice after pronouncing each time, the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice, and finally the average value of the voiceprint features of the d-vector obtained by pronouncing each time is used as the registered voiceprint features sent by the registered user.
During voiceprint registration, the central control module displays a sentence which needs to be recited during registration to the verifier through the interaction module, wherein the interaction module is generally a touch screen. Taking three-time repeated pronunciation as an example, the voice broadcasting module prompts the user to read the sentence for three times. After each sentence is enunciated, the voice feature extraction module extracts feature information (fbank, FilterBank feature, namely, Mel frequency cepstrum coefficient without discrete cosine transform operation), the voiceprint recognition module takes the voice feature information fbank as the input of a voiceprint model, the voice feature information is output as the voiceprint feature d-vector of the voice, and then the voice broadcasting module prompts that the recording is successful. And after the three times of voice input, averaging the voiceprints of the three d-vectors to obtain the voiceprint characteristic of the user. The central processing module stores the voiceprint characteristics into a storage unit corresponding to the user identity. And then the voice broadcast module prompts the successful registration. The system exits the registration state and enters the identification state.
A user may perform a deletion operation on personal information stored in the system through a voice command or an interaction module, as shown in fig. 3, where the deletion operation specifically includes:
the user speaks a delete command word; after the voice feature extraction module identifies the deletion command, the system enters a deletion state;
the user performs fingerprint verification and voice print verification;
the voiceprint verification method specifically comprises the following steps:
the central control module displays a verification language to the verifier through the interactive interface;
after each pronunciation, the voice feature extraction module extracts fbank feature information of the section of voice, and the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice;
if the obtained highest similarity is higher than a set voiceprint threshold value, the registered voiceprint characteristic user corresponding to the highest similarity is judged as a verifier of the voiceprint characteristic input;
after the voice print verification mode judges the verifier, the verifier is compared with the verifier judged by the fingerprint verification to judge whether the verifier is the same registered user, if so, the verification is successful, the user can delete the information of the user, otherwise, the judgment is failed.
The authentication method of the invention can be based on the following fingerprint and voiceprint dual authentication system, as shown in fig. 4, comprising a central processing module, an interactive interface connected with the central processing module, a voice broadcasting module and a storage unit, and further comprising a voiceprint recognition unit and a fingerprint recognition unit which are connected with the central processing module, wherein the voiceprint recognition unit comprises a voiceprint feature extraction module and a voiceprint recognition module which is connected with the voiceprint feature extraction module, and the voiceprint recognition module is connected with the central processing module; the fingerprint identification unit comprises a fingerprint feature extraction module and a fingerprint identification module connected with the fingerprint feature extraction module, and the fingerprint identification module is connected with the central processing unit; the system also comprises an ASR module connected with the voiceprint feature extraction module, and the ASR module is connected with the voice feature extraction module.
According to the invention, through double registration of the fingerprint and the voiceprint, the verifier can judge that the identification is passed only through two identification processes of voiceprint identification and fingerprint identification at the same time during identification. The method avoids the possible false positive caused by single verification of the voiceprint lock and the fingerprint lock through a double verification mode, and improves the reliability and the anti-interference performance of the verification by adopting a deep neural network model (D-vector) with text characteristics.
The foregoing is directed to preferred embodiments of the present invention, wherein the preferred embodiments are not obviously contradictory or subject to any particular embodiment, and any combination of the preferred embodiments may be combined in any overlapping manner, and the specific parameters in the embodiments and examples are only for the purpose of clearly illustrating the inventor's invention verification process and are not intended to limit the scope of the invention, which is defined by the claims and the equivalent structural changes made by the description and drawings of the present invention are also intended to be included in the scope of the present invention.
Claims (5)
1. A fingerprint and voiceprint double authentication method is characterized by comprising the following steps:
fingerprint verification and voiceprint verification;
in the fingerprint verification, a verifier carries out similarity calculation on the input fingerprint characteristics and the fingerprint characteristics stored by all registered users, if the obtained highest similarity is higher than a set fingerprint threshold, the fingerprint characteristic user corresponding to the highest similarity is judged as the verifier of the input fingerprint characteristics, otherwise, the verifier fails to judge
The voiceprint verification method specifically comprises the following steps:
the central control module displays a verification language to the verifier through the interactive interface;
after each pronunciation, the voice feature extraction module extracts fbank feature information of the section of voice, and the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice;
if the obtained highest similarity is higher than a set voiceprint threshold value, the registered voiceprint characteristic user corresponding to the highest similarity is judged as a verifier of the voiceprint characteristic input;
and after the verifier is judged by the voiceprint verification mode, the voiceprint verification mode is compared with the verifier judged by the fingerprint verification to judge whether the verifier is the same registered user, if so, the verification is successful, and otherwise, the judgment is failed.
2. The fingerprint and voiceprint dual authentication method according to claim 1, wherein the authentication method further comprises a registration process before verification, and the registration process specifically comprises:
the system enters a registration state; prompting registered user to input identity information
Fingerprint registration is carried out;
and (3) carrying out voiceprint registration: the central control module displays the registration words during registration to the user through an interactive interface; the registered user pronounces the registered words for more than two times, the voice feature extraction module extracts fbank feature information of the section of voice after pronouncing each time, the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice, and finally the average value of the voiceprint features of the d-vector obtained by pronouncing each time is used as the registered voiceprint features sent by the registered user.
3. The fingerprint and voiceprint dual authentication method according to claim 2, wherein the fingerprint registration specifically is:
a registered user places a finger on a fingerprint collector to collect fingerprint characteristics;
the fingerprint feature extraction module extracts the calculated fingerprint features,
the system prompts the user to input fingerprint information again, the registered user puts the finger on the fingerprint collector again to collect fingerprint characteristics, and the fingerprint characteristic extraction module extracts and calculates the fingerprint characteristics again;
the fingerprint identification module calculates the similarity of the fingerprint characteristics obtained by the two times of extraction; if the similarity is lower than a preset fingerprint storage threshold, judging that the fingerprints input twice do not belong to the same person, and simultaneously deleting the fingerprint characteristics and the identity information by the central processing module and prompting that the fingerprint registration fails; otherwise, prompting that the fingerprint registration is successful.
4. The fingerprint and voiceprint dual authentication method according to claim 1, further comprising a deletion operation after the registration is successful, wherein the deletion operation specifically comprises:
the user speaks a delete command word; after the voice feature extraction module identifies the deletion command, the system enters a deletion state;
the user performs fingerprint verification and voice print verification;
the voiceprint verification method specifically comprises the following steps:
the central control module displays a verification language to the verifier through the interactive interface;
after each pronunciation, the voice feature extraction module extracts fbank feature information of the section of voice, and the voiceprint recognition module converts the fbank feature information into d-vector voiceprint features of the section of voice;
if the obtained highest similarity is higher than a set voiceprint threshold value, the registered voiceprint characteristic user corresponding to the highest similarity is judged as a verifier of the voiceprint characteristic input;
after the voice print verification mode judges the verifier, the verifier is compared with the verifier judged by the fingerprint verification to judge whether the verifier is the same registered user, if so, the verification is successful, the user can delete the information of the user, otherwise, the judgment is failed.
5. Fingerprint and voiceprint dual authentication system, its characterized in that: the voice print recognition system comprises a central processing module, an interactive interface connected with the central processing module, a voice broadcast module, a storage unit, a voiceprint recognition unit and a fingerprint recognition unit, wherein the voiceprint recognition unit and the fingerprint recognition unit are connected with the central processing module; the fingerprint identification unit comprises a fingerprint feature extraction module and a fingerprint identification module connected with the fingerprint feature extraction module, and the fingerprint identification module is connected with the central processing unit; the system also comprises an ASR module connected with the voiceprint feature extraction module, and the ASR module is connected with the voice feature extraction module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911124141.3A CN110827453A (en) | 2019-11-18 | 2019-11-18 | Fingerprint and voiceprint double authentication method and authentication system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911124141.3A CN110827453A (en) | 2019-11-18 | 2019-11-18 | Fingerprint and voiceprint double authentication method and authentication system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110827453A true CN110827453A (en) | 2020-02-21 |
Family
ID=69555894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911124141.3A Pending CN110827453A (en) | 2019-11-18 | 2019-11-18 | Fingerprint and voiceprint double authentication method and authentication system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827453A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445909A (en) * | 2020-03-24 | 2020-07-24 | 多玛凯拔科技有限公司 | Intelligent lock with voice control function and control method thereof |
| CN111477234A (en) * | 2020-03-05 | 2020-07-31 | 厦门快商通科技股份有限公司 | Voiceprint data registration method, device and equipment |
| CN111915766A (en) * | 2020-06-06 | 2020-11-10 | 安徽中科昊音智能科技有限公司 | Voiceprint control lock and voiceprint identification method and system |
| CN112435673A (en) * | 2020-12-15 | 2021-03-02 | 北京声智科技有限公司 | Model training method and electronic terminal |
| CN112600843A (en) * | 2020-12-15 | 2021-04-02 | 深圳康佳电子科技有限公司 | Authentication method, storage medium and gateway |
| CN113356692A (en) * | 2020-03-02 | 2021-09-07 | 深圳市凌度汽车电子有限公司 | Intelligent door lock and control method |
| CN114185304A (en) * | 2021-12-07 | 2022-03-15 | 城市花园(北京)环境科技有限公司 | Intelligent device opening and closing system based on voiceprint control |
| CN115100776A (en) * | 2022-05-30 | 2022-09-23 | 厦门快商通科技股份有限公司 | Access control authentication method, system and storage medium based on voice recognition |
| CN116563984A (en) * | 2023-07-10 | 2023-08-08 | 深圳市旭子科技有限公司 | Unlocking method and system based on Internet of things |
| CN112435673B (en) * | 2020-12-15 | 2024-05-14 | 北京声智科技有限公司 | Model training method and electronic terminal |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1359514A (en) * | 1999-07-06 | 2002-07-17 | 摩托罗拉公司 | Multimodal data input device |
| US8380637B2 (en) * | 2011-01-16 | 2013-02-19 | Yerucham Levovitz | Variable fractions of multiple biometrics with multi-layer authentication of mobile transactions |
| CN104331652A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Dynamic cipher generation method for electronic equipment for fingerprint and voice recognition |
| CN104331651A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Fingerprint- and voice recognition-based control system and equipment |
| CN105869644A (en) * | 2016-05-25 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Deep learning based voiceprint authentication method and device |
| CN106022780A (en) * | 2016-05-20 | 2016-10-12 | 廖建强 | Electronic payment method and device based on fingerprint information |
| CN107018228A (en) * | 2016-01-28 | 2017-08-04 | 中兴通讯股份有限公司 | A kind of speech control system, method of speech processing and terminal device |
| CN108082124A (en) * | 2017-12-18 | 2018-05-29 | 奇瑞汽车股份有限公司 | A kind of method and apparatus using bio-identification control vehicle |
| CN108429619A (en) * | 2018-01-18 | 2018-08-21 | 北京捷通华声科技股份有限公司 | Identity identifying method and system |
| CN110363886A (en) * | 2018-04-11 | 2019-10-22 | 中兴通讯股份有限公司 | Function realizing method, device and its relevant device of smart lock |
-
2019
- 2019-11-18 CN CN201911124141.3A patent/CN110827453A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1359514A (en) * | 1999-07-06 | 2002-07-17 | 摩托罗拉公司 | Multimodal data input device |
| US8380637B2 (en) * | 2011-01-16 | 2013-02-19 | Yerucham Levovitz | Variable fractions of multiple biometrics with multi-layer authentication of mobile transactions |
| CN104331652A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Dynamic cipher generation method for electronic equipment for fingerprint and voice recognition |
| CN104331651A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Fingerprint- and voice recognition-based control system and equipment |
| CN107018228A (en) * | 2016-01-28 | 2017-08-04 | 中兴通讯股份有限公司 | A kind of speech control system, method of speech processing and terminal device |
| CN106022780A (en) * | 2016-05-20 | 2016-10-12 | 廖建强 | Electronic payment method and device based on fingerprint information |
| CN105869644A (en) * | 2016-05-25 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Deep learning based voiceprint authentication method and device |
| CN108082124A (en) * | 2017-12-18 | 2018-05-29 | 奇瑞汽车股份有限公司 | A kind of method and apparatus using bio-identification control vehicle |
| CN108429619A (en) * | 2018-01-18 | 2018-08-21 | 北京捷通华声科技股份有限公司 | Identity identifying method and system |
| CN110363886A (en) * | 2018-04-11 | 2019-10-22 | 中兴通讯股份有限公司 | Function realizing method, device and its relevant device of smart lock |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113356692A (en) * | 2020-03-02 | 2021-09-07 | 深圳市凌度汽车电子有限公司 | Intelligent door lock and control method |
| CN113356692B (en) * | 2020-03-02 | 2022-07-05 | 深圳市凌度汽车电子有限公司 | Intelligent door lock and control method |
| CN111477234A (en) * | 2020-03-05 | 2020-07-31 | 厦门快商通科技股份有限公司 | Voiceprint data registration method, device and equipment |
| CN111445909A (en) * | 2020-03-24 | 2020-07-24 | 多玛凯拔科技有限公司 | Intelligent lock with voice control function and control method thereof |
| CN111915766A (en) * | 2020-06-06 | 2020-11-10 | 安徽中科昊音智能科技有限公司 | Voiceprint control lock and voiceprint identification method and system |
| CN112600843B (en) * | 2020-12-15 | 2022-10-04 | 深圳康佳电子科技有限公司 | Authentication method, storage medium and gateway |
| CN112600843A (en) * | 2020-12-15 | 2021-04-02 | 深圳康佳电子科技有限公司 | Authentication method, storage medium and gateway |
| CN112435673A (en) * | 2020-12-15 | 2021-03-02 | 北京声智科技有限公司 | Model training method and electronic terminal |
| CN112435673B (en) * | 2020-12-15 | 2024-05-14 | 北京声智科技有限公司 | Model training method and electronic terminal |
| CN114185304A (en) * | 2021-12-07 | 2022-03-15 | 城市花园(北京)环境科技有限公司 | Intelligent device opening and closing system based on voiceprint control |
| CN115100776A (en) * | 2022-05-30 | 2022-09-23 | 厦门快商通科技股份有限公司 | Access control authentication method, system and storage medium based on voice recognition |
| CN115100776B (en) * | 2022-05-30 | 2023-12-26 | 厦门快商通科技股份有限公司 | Entrance guard authentication method, system and storage medium based on voice recognition |
| CN116563984A (en) * | 2023-07-10 | 2023-08-08 | 深圳市旭子科技有限公司 | Unlocking method and system based on Internet of things |
| CN116563984B (en) * | 2023-07-10 | 2023-09-22 | 深圳市旭子科技有限公司 | Unlocking method and system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110827453A (en) | Fingerprint and voiceprint double authentication method and authentication system | |
| US6107935A (en) | Systems and methods for access filtering employing relaxed recognition constraints | |
| WO2017198014A1 (en) | Identity authentication method and apparatus | |
| US7386448B1 (en) | Biometric voice authentication | |
| US6510415B1 (en) | Voice authentication method and system utilizing same | |
| US6219639B1 (en) | Method and apparatus for recognizing identity of individuals employing synchronized biometrics | |
| US20080270132A1 (en) | Method and system to improve speaker verification accuracy by detecting repeat imposters | |
| WO2017197953A1 (en) | Voiceprint-based identity recognition method and device | |
| US7949535B2 (en) | User authentication system, fraudulent user determination method and computer program product | |
| WO2010047816A1 (en) | Speaker verification methods and apparatus | |
| WO2010047817A1 (en) | Speaker verification methods and systems | |
| CN102543084A (en) | Online voiceprint recognition system and implementation method thereof | |
| CN102737634A (en) | Authentication method and device based on voice | |
| WO2004038639A2 (en) | Verification of identity and continued presence of computer users | |
| CN111275858B (en) | Credit granting method and system for voiceprint recognition | |
| CN111611568A (en) | Face voiceprint rechecking terminal and identity authentication method thereof | |
| CN107481736A (en) | A kind of vocal print identification authentication system and its certification and optimization method and system | |
| Hazen et al. | Multi-modal face and speaker identification on a handheld device | |
| US6161094A (en) | Method of comparing utterances for security control | |
| KR102604319B1 (en) | Speaker authentication system and method | |
| CN112417412A (en) | Bank account balance inquiry method, device and system | |
| JP3999983B2 (en) | Operator monitoring device | |
| KR20010019772A (en) | User Password Verification System and Method by Speech for Reinforced Security | |
| JP2003302999A (en) | Individual authentication system by voice | |
| WO2000058947A1 (en) | User authentication for consumer electronics |
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: 20200221 |