WO2021162584A1 - Procédé de vérification de données biométriques vocales - Google Patents

Procédé de vérification de données biométriques vocales Download PDF

Info

Publication number
WO2021162584A1
WO2021162584A1 PCT/RU2021/000064 RU2021000064W WO2021162584A1 WO 2021162584 A1 WO2021162584 A1 WO 2021162584A1 RU 2021000064 W RU2021000064 W RU 2021000064W WO 2021162584 A1 WO2021162584 A1 WO 2021162584A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice biometric
biometric data
user
computer
resonance
Prior art date
Application number
PCT/RU2021/000064
Other languages
English (en)
Russian (ru)
Inventor
Илья Владимирович РЕДКОКАШИН
Original Assignee
Илья Владимирович РЕДКОКАШИН
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Илья Владимирович РЕДКОКАШИН filed Critical Илья Владимирович РЕДКОКАШИН
Publication of WO2021162584A1 publication Critical patent/WO2021162584A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies

Definitions

  • the invention relates to the field of computer networks, in particular to user verification technologies. More specifically, the invention relates to methods for verifying users using voice biometric data.
  • This method is convenient for user authentication, but it has a significant drawback.
  • Features describing user verification, which is part of the authentication process, do not provide sufficient verification security.
  • the biometric data used in the known method can be falsified.
  • Voice biometric data can be tampered with using sound-producing devices. For example, voice biometric data can be recorded on a dictaphone.
  • Algorithms can also be used that, based on a voice template, falsify voice biometrics.
  • the task set by the developer of a method for verifying voice biometric data is to develop a method that, in comparison with analogs, would increase the security of user verification.
  • the technical result of the proposed method for verifying voice biometric data is to improve the security of verification of voice biometric data, protection against falsification of voice biometric data.
  • the essence of the method for verifying voice biometric data consists in the fact that the user is first asked for his voice biometric data using a computer. Then, during the reception of voice biometric data, a signal is reproduced with the help of a computer, which creates a resonance in the devices that reproduce sounds. After that, the requested data is sent to at least one server and the received data is compared with the data of the voice biometric information stored in the database on the server. And also check the presence of resonance in the received data. At the same time, they can also authenticate the user by checking the credentials associated with the information requested from the user, and provide access to the user to network resources. Also, to improve the accuracy of verification, the user may be prompted for at least one keyword.
  • a user Before verification, a user can be registered by requesting the user's voice biometric data using a computer, and storing the voice biometric data in the database, or storing the voice biometric data in the database, linking them with the credentials.
  • the requested information can be encrypted, or the information obtained on the basis of the requested information can be used.
  • the credentials can be installed on the user's computer. If necessary, they can save information about which users, from which devices transmit voice biometric data. To improve accuracy and security, the user may be prompted for additional information that is used to authenticate the user.
  • the signal can create resonance that is invisible to humans, and the presence of resonance can be checked using a computer algorithm.
  • the computer can also use different signals and receive different resonances, as well as compare the loudness of the resonance with the loudness of the voice biometric data and analyze the approximate distance from the microphone to the sound source. If the computer, with the help of which the voice biometric data is requested from the user, has the ability to reproduce sounds, then the resonance reproduced by this computer may not be taken into account when analyzing the voice biometric data, or it may create a signal for this computer that compensates for the resonance.
  • the claimed method for verifying voice biometric data is as follows.
  • the user is first registered by requesting the user's voice biometric data using a computer, and the requested data is associated with the credentials.
  • voice biometric data are voice timbre and other voice parameters.
  • Credentials can be created for the user, or they can use the previously created credentials.
  • the database stores the user's credentials and biometric data.
  • the database can be located on a server, or it can be on multiple servers, and each server can store different data. For verification purposes, they can register a user without using credentials, storing only his voice biometric data.
  • the user After the user is registered, the user can be verified using his voice biometric data.
  • the user's voice biometric data is requested from the user using a computer.
  • Mobile devices such as cellular devices can be used as a computer. phones, tablets, laptops, etc., as well as any other devices capable of performing similar functions.
  • the computer must be equipped with a microphone to receive voice biometric data.
  • a signal is reproduced with the help of the user's computer, which creates a resonance in the devices that reproduce sounds.
  • This signal can be a cellular base station signal, or any other signal that resonates with speakers that produce sounds.
  • the requested data is sent to the server.
  • the invention contemplates that multiple servers can be used.
  • the obtained data is compared with the data of the voice biometric information stored in the database on the server and the presence of resonance in the received data is checked.
  • the presence of resonance may mean that the voice biometric data is forged and technical devices that reproduce sounds were used to reproduce them. It should also be taken into account that in the context of the present invention, the interference generated by the signal must also be considered as a resonance.
  • After verifying the user they can authenticate the user by checking the credentials associated with the information requested from the user and grant the user access to network resources. The user may be prompted for at least one keyword. Keywords can be used as an additional way to verify users. Keywords can be used in such a way that each new registered keyword or combination of words is not repeated with already registered keywords or combinations of words.
  • the credentials are installed on the user's computer as needed. For safety, they can save information about which users from which devices are transmitting data. For example, they may remember that John often uses verification using a device with a specific serial number or mobile phone number, etc. The user may be prompted for additional information that is used to user authentication or verification, such as device data or any other data.
  • the created resonance may not be noticeable to a person, and the presence of resonance is checked using a computer algorithm.
  • the computer algorithm may be artificial intelligence that is trained to accurately recognize resonances.
  • the server analyzes the presence of a specific resonance that corresponds to the signal generated when the request was sent. They also compare the loudness of the resonance with the loudness of the voice biometric data and analyze the approximate distance from the micron to the sound sources. This comparison helps to improve the accuracy of the verification, since sometimes users may be near the devices playing sounds. For example, if the user is near the speakers, the speakers can create resonance. To understand that it is not the speakers that create voice biometric data, you need to analyze the distance to sound sources or apply other well-known methods for determining sound characteristics.
  • the resonance reproduced by this computer is not taken into account when analyzing the voice biometric data, or a signal is generated for this computer, which compensates for the resonance.
  • the mobile phone for example, can receive software commands from the server that compensate for the resonance, or modify it, which highlights the resonance reproduced by the speaker of a particular device.
  • the server can thus distinguish the resonance reproduced by the computer with which the voice biometric data is requested from the resonance reproduced by other devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

L'invention se rapporte au domaine des techniques informatiques et concerne notamment des techniques de vérification d'utilisateurs. Le résultat technique consiste en une augmentation de la sécurité de vérification des données biométriques vocales et en une protection contre des données biométriques vocales falsifiées. Ce résultat technique est atteint grâce à un procédé de vérification de données biométriques vocales qui consiste à: demander, à l'aide d'un ordinateur au niveau d'un utilisateur, ses données biométriques vocales; pendant la réception des données biométriques vocales et à l'aide de l'ordinateur, reproduire un signal qui génère une résonance au niveau des dispositifs reproduisant un son; envoyer les données demandées vers au moins un serveur; comparer les données obtenues avec des données d'informations biométriques vocales stockées dans une base de données sur le serveur; vérifier la présence de résonance dans les données obtenues.
PCT/RU2021/000064 2020-02-15 2021-02-15 Procédé de vérification de données biométriques vocales WO2021162584A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
RU2020107059 2020-02-15
RU2020107059A RU2723902C1 (ru) 2020-02-15 2020-02-15 Способ верификации голосовых биометрических данных

Publications (1)

Publication Number Publication Date
WO2021162584A1 true WO2021162584A1 (fr) 2021-08-19

Family

ID=71096236

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2021/000064 WO2021162584A1 (fr) 2020-02-15 2021-02-15 Procédé de vérification de données biométriques vocales

Country Status (2)

Country Link
RU (1) RU2723902C1 (fr)
WO (1) WO2021162584A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080091425A1 (en) * 2006-06-15 2008-04-17 Kane James A Voice print recognition software system for voice identification and matching
US20120245941A1 (en) * 2011-03-21 2012-09-27 Cheyer Adam J Device Access Using Voice Authentication
US20150187359A1 (en) * 2011-03-30 2015-07-02 Ack3 Bionetics Pte Limited Digital voice signature of transactions
US20160071521A1 (en) * 2010-02-25 2016-03-10 Apple Inc. User profiling for voice input processing
RU2697736C1 (ru) * 2016-07-15 2019-08-19 ГУГЛ ЭлЭлСи Верификация говорящего

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080091425A1 (en) * 2006-06-15 2008-04-17 Kane James A Voice print recognition software system for voice identification and matching
US20160071521A1 (en) * 2010-02-25 2016-03-10 Apple Inc. User profiling for voice input processing
US20120245941A1 (en) * 2011-03-21 2012-09-27 Cheyer Adam J Device Access Using Voice Authentication
US20150187359A1 (en) * 2011-03-30 2015-07-02 Ack3 Bionetics Pte Limited Digital voice signature of transactions
RU2697736C1 (ru) * 2016-07-15 2019-08-19 ГУГЛ ЭлЭлСи Верификация говорящего

Also Published As

Publication number Publication date
RU2723902C1 (ru) 2020-06-18

Similar Documents

Publication Publication Date Title
US9444816B2 (en) Continuous voice authentication for a mobile device
CN106330850B (zh) 一种基于生物特征的安全校验方法及客户端、服务器
CN113114624B (zh) 基于生物特征的身份认证方法和装置
JP3552648B2 (ja) アドホック無線通信用データ送受システム及びアドホック無線通信用データ送受方法
US9118488B2 (en) System and method for controlling access to network services using biometric authentication
US11444940B2 (en) User authentication of smart speaker system
EP3248188B1 (fr) Procédé d'authentification
US9461987B2 (en) Audio authentication system
CN108737971B (zh) 身份认证方法、设备及存储介质
WO2020186802A1 (fr) Procédé et appareil de publication de paquet de mise à jour de version, dispositif informatique et support de stockage
WO2019008383A1 (fr) Transfert de données audio
WO2021190197A1 (fr) Procédé et appareil d'authentification de dispositif de paiement biométrique, dispositif informatique et support d'informations
CN110784395B (zh) 一种基于fido认证的邮件安全登录方法及系统
Das et al. Fingerprinting smart devices through embedded acoustic components
Alattar et al. Privacy‐preserving hands‐free voice authentication leveraging edge technology
CN114071418A (zh) 一种基于机密计算的车联网认证协议方法
RU2723902C1 (ru) Способ верификации голосовых биометрических данных
US10601820B2 (en) Method and apparatus to identify and authorize caller via ultrasound
Phipps et al. Your password is music to my ears: Cloud based authentication using sound
Phipps et al. Enhancing cyber security using audio techniques: a public key infrastructure for sound
RU2527731C2 (ru) Способ формирования электронного документа
TW202101299A (zh) 多因子動態快速反應碼認證系統及方法
CN114978552B (zh) 邮箱验证码的安全管理方法、装置、设备及介质
US20060190735A1 (en) Method of entering a security code for a network apparatus
RU2009101311A (ru) Установление подлинности операций с использованием сети

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21753775

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03.02.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21753775

Country of ref document: EP

Kind code of ref document: A1