WO2018209918A1 - 使用语音输入进行验证的方法和系统 - Google Patents

使用语音输入进行验证的方法和系统 Download PDF

Info

Publication number
WO2018209918A1
WO2018209918A1 PCT/CN2017/112143 CN2017112143W WO2018209918A1 WO 2018209918 A1 WO2018209918 A1 WO 2018209918A1 CN 2017112143 W CN2017112143 W CN 2017112143W WO 2018209918 A1 WO2018209918 A1 WO 2018209918A1
Authority
WO
WIPO (PCT)
Prior art keywords
verification
voice
code
user
consistent
Prior art date
Application number
PCT/CN2017/112143
Other languages
English (en)
French (fr)
Inventor
刘光明
Original Assignee
刘光明
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 刘光明 filed Critical 刘光明
Publication of WO2018209918A1 publication Critical patent/WO2018209918A1/zh

Links

Images

Classifications

    • 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
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • H04L9/3231—Biological data, e.g. fingerprint, voice or retina

Definitions

  • the present invention relates to user identity verification, and more particularly to a method and system for verifying using voice input.
  • One of the security issues is determining the identity of users who use applications and services, especially in applications and services that involve finance, payment, privacy, or other security-critical applications. Identifying user identity is an important part.
  • a verification code may be fixed password verification or random password verification.
  • random passwords are typically sent to a user-specified device, such as to a user's mobile phone.
  • a user device such as a mobile phone. If the user's mobile phone is stolen, or the mobile phone is controlled by someone else, the password will be obtained by the current holder of the mobile phone, and the holder can use the password sent to the mobile phone to complete the identity required for the application and service. Verification, thereby acting as a secure user to endanger user property or privacy (eg, transactions, etc.). In this case, the so-called security is gone.
  • applications and services are used to prevent malicious attacks or improper use of applications and services (such as multiple logins using computer programs, multiple submissions, multiple comments, brushing, praise, etc.) Additional verification code to verify. For example, by using a picture to display regular or irregular numbers, Chinese characters, letters, or other characters, the user is required to enter these characters for verification.
  • the currently common password is a sequence of numbers (for example, 4 or 6 digits).
  • the digital password is relatively easy to be cracked or leaked, and the digital verification code in the picture is easily recognized and lost. Go to the meaning of its verification.
  • the present invention provides a method and system for verifying using voice input.
  • the user needs to input the password or verification code by voice, that is, read the password or verification code, and the application or service verifies the input password or verification code through voice recognition.
  • Verification is divided into two aspects: on the one hand, the verification of the code; on the other hand, the verification of the voice, that is, the voice needs to be consistent with the voice of the user. This avoids the insecure situation in which others use the user's identity to enter a password or verification code.
  • the security of applications and services is further enhanced by increasing the security of voice recognition.
  • a method for verifying using voice input comprising: when a verification request is made, a user inputs the acquired code for verification by voice; recognizes the input voice, and extracts and recognizes a voice feature and a recognized code; determining whether the recognized voice feature is consistent with a predetermined voice feature; determining whether the identified code is consistent with a preset verification code; In the case of "consistent", user authentication is passed.
  • the code may be a character that can be read by voice.
  • the code can be one or a combination of letters, numbers, and Chinese characters.
  • the predetermined voice features can be pre-stored on the user device. In another aspect, the predetermined voice features can be pre-stored in a server or cloud.
  • the pre-set verification code can be generated locally by the user equipment.
  • the pre-set verification code can be generated by the server or the cloud and sent to the user.
  • a system for verifying using voice input comprising: a voice input device for causing a user to acquire a code for verification when a verification request is made Input by voice; a voice recognition device for recognizing the input voice, extracting the recognized voice feature and the recognized code; and a voice feature determination device for determining whether the recognized voice feature is consistent with the predetermined voice feature a code judging means for judging whether the recognized code is consistent with a pre-set verification code; and the verifying means is configured to output the verification if the judgment results of the two judging means are "consistent" instruction.
  • a computer readable storage medium for recording instructions executable by a processor, the instructions, when executed by a processor, causing a processor to perform a method of verifying using a voice input, including
  • the user inputs the acquired code for verification by voice; recognizes the input voice, extracts the recognized voice feature and the recognized code; and determines whether the recognized voice feature is predetermined
  • the voice features are consistent; whether the identified code is consistent with the preset verification code; if both of the determination results are "consistent", the user verification passes.
  • One advantage of the present invention is that in the case where the user's mobile phone is held by another person, since the voice input of another person cannot match the voice of the user itself, the verification fails, thereby protecting the security of the user.
  • the voice recognition link is added to further avoid malicious or abnormal access, thereby ensuring the authenticity and security of the transaction activity.
  • FIG. 1 is a schematic diagram illustrating a system for verifying using voice input, in accordance with an embodiment of the present invention.
  • FIG. 2 is a flow chart illustrating a method of verifying using voice input, in accordance with an embodiment of the present invention.
  • a character code for verification such as a password or a verification code may be collectively referred to as a verification code or code.
  • FIG. 1 is a schematic diagram illustrating a system for verifying using voice input, in accordance with an embodiment of the present invention.
  • a system 100 for verification using voice input includes a voice input device 101, a voice recognition device 102, a voice feature determination device 103, a code determination device 104, and a verification device 105.
  • the corresponding application or service may require the user to verify.
  • the payment application may ask the user to enter a user password and/or a random verification code.
  • the user password can be set in advance by the user and stored in advance by the application for future verification; the user password can be stored on the user device for easy inspection, or stored in the cloud or server, and checked when calling the service on the cloud or the server. .
  • the random verification code can then be sent by the backend server of the application or service to the user-reserved or currently designated mobile device.
  • the random verification code can also be provided to the user in the form of a webpage picture by the local user equipment or the backend server. For example, our common website graphical verification code is to hide the verification code (code) in the picture, identify it by the user, and then enter it into the box of the verification code.
  • the voice input device 101 causes the user to input the acquired code for verification by voice when the authentication request is made, for example, by an application or a service.
  • the code for verification (referred to as the verification code) obtained by the user may be set in advance, or may be temporarily and randomly set to be sent to the user equipment.
  • the user equipment may be a device used by the user to perform an application or a service, or may be another device.
  • the code is a character that can be read by voice.
  • the code can be one or a combination of letters, numbers, and Chinese characters.
  • the verification code acquired by the user is "123456"
  • the user Voice input is performed by reading “1", “2", “3", “4", "5", "6” in order.
  • the voice recognition device 102 recognizes the voice input through the voice input device 101, and extracts the recognized voice feature and the recognized code.
  • the user's voice can be input into the user device running the application or service for identification, or can be input to the third-party device for identification, and the third-party device can notify the user device after making the judgment result described below, or can also be input.
  • the user equipment is forwarded by the user equipment to the third party device for identification processing.
  • the voice feature may be a specific voice or voice segment, or may be a feature parameter of the voice.
  • the speech features used in the present invention are used to distinguish between different users. For example, the voices of different users will present different pitches, fundamental frequencies, harmonics, and the sound of unvoiced and voiced sounds will have different characteristics. The characteristics of these sounds can also be called "soundprints". Those skilled in the art should understand that different speech features can be selected for different users according to different speech recognition algorithms. The present invention includes all of these speech features and is not limited to any of the speech features in practical applications.
  • the speech recognition device 102 In addition to recognizing the speech features, the speech recognition device 102 also needs to identify a specific code (verification code). Those skilled in the art should understand that in practical applications, a suitable speech recognition algorithm may be selected to identify the code that the user inputs by voice.
  • the voice feature judging means 103 judges whether or not the voice feature recognized by the voice recognition device 102 coincides with a predetermined voice feature.
  • the speech feature is used to distinguish between different users. Therefore, a specific user, such as a user or owner of the user equipment, can predetermine his or her own voice features, such as recording some voices through a predetermined program to train to get their own voice features, or, for example, pre-recording some of the possible verification codes.
  • the speech of a specific character (such as letters, numbers, a number of Chinese characters within a specified range, or some phonological elements such as initials, finals, etc.).
  • the speech feature judging device 103 can call such predetermined speech features so as to be able to compare with the speech features recognized from the input speech. If the comparison results are consistent, it indicates that the user who inputs the voice is the user who predetermines the voice feature, that is, the same user.
  • the predetermined speech feature may be pre-stored for On the user device that receives the voice.
  • the user performs voice training in advance on the mobile phone to store his or her voice features on the mobile phone for future verification.
  • the predetermined voice features may also be pre-stored in the server or the cloud.
  • the training result that is, the extracted voice feature, is transferred to the server or the cloud, so that the user can perform verification on different user devices in the future.
  • the code judging means 104 judges whether or not the code recognized by the voice recognition means 102 coincides with the pre-set verification code.
  • the verification code may be preset by an authorized user, or may be preset and provided or presented to the user by an application or service, a user device, a cloud or a server according to the verified request.
  • the "pre-" setting described here is relative to the user's input and speech recognition, that is, after the verification code is set in advance, the subsequent verification is discussed.
  • the code judging means 104 can call such a pre-set verification code so that it can be compared with the code recognized from the input speech for verification purposes.
  • the preset verification code may be generated locally by the user equipment, or may be generated by the server or the cloud and sent to the user.
  • the verification means 105 outputs an instruction to pass the verification.
  • the verification means 105 can output an instruction or instruction that the user verification has failed.
  • the frame of the verification device 105 is drawn into an AND gate to reflect its logic function.
  • An application scenario can be envisaged: the user needs to pay using a payment tool (application or service) on the mobile phone or computer.
  • the payment instrument requires the user to authenticate before the payment transaction occurs.
  • the payment instrument can require the user to provide a personal account number and/or password; on the other hand, the backend server of the payment instrument can send a message to the user's mobile device (eg, a mobile phone), the message including the verification code, the user You need to enter the received verification code for double verification.
  • the user's mobile device eg, a mobile phone
  • the verification code the user You need to enter the received verification code for double verification.
  • Such a verification scheme is to ensure that the above transaction occurs with the knowledge and permission of the user.
  • a prerequisite for this verification scheme is that the user's mobile device must be owned by the user. Back As described in the technology, if the user's mobile device is stolen or controlled by others, the above verification scheme will lose its meaning.
  • the user needs to perform voice input. That is to say, in addition to the verification verification of the verification code itself, it is also necessary to perform voice recognition on the person who inputs the verification code to determine whether the person is the user himself or herself.
  • voice recognition in addition to speech recognition, may also be identification of other accompanying biometrics, such as iris, fingerprint, palm print, and the like.
  • the present invention is characterized in that the verification code is combined with voice, the input carrier is voice, and the input content is code.
  • speech recognition it can not only verify the voice features (the user's identity verification), but also realize the verification of character codes such as letters, numbers, Chinese characters (as long as they are readable, that can be expressed and distinguished by voice). Verification code verification).
  • the voice feature of the input voice is found to be inconsistent with the voice feature of the user, so that the transaction can be rejected.
  • the voice input is used and the voice features are recognized and verified, the abnormal behavior such as repeated login, brushing, and praise is eliminated by using a machine or a computer program, thereby further enhancing the security of the application or service.
  • FIG. 2 is a flow chart illustrating a method of verifying using voice input, in accordance with an embodiment of the present invention.
  • the method 200 for verifying using voice input begins in step S201, in which, when a verification request is made, the user inputs the acquired code for verification by voice.
  • the code is a character that can be read by voice.
  • the code can be one or a combination of letters, numbers, and Chinese characters.
  • step S203 the input voice is recognized, and the recognized voice feature and the recognized code are extracted.
  • step S205 it is determined whether the recognized speech feature is consistent with a predetermined speech feature.
  • the predetermined voice feature may be pre-stored on a user equipment for receiving voice, or may be pre-stored in a server or a cloud.
  • step S207 it is judged whether or not the recognized code coincides with the previously set verification code.
  • the preset verification code may be generated locally by the user equipment, or may be generated by the server or the cloud and sent to the user.
  • the pre-set verification code may also be preset by the user himself and saved or memorized by the user himself.
  • Steps S205 and S207 may be performed one after the other, or may be performed simultaneously in parallel. Even in the case of being performed one after the other, step S205 is not necessarily performed before or after step S207. That is, although steps S205 and S207 are performed in order according to FIG. 2, the illustration is only an example, and it is not desirable to define such an order.
  • step S209 in a case where the determination results of the above two steps S205 and S207 are both "consistent", the user verification passes.
  • Non-transitory computer readable media include various types of tangible storage media.
  • non-transitory computer readable medium examples include magnetic recording media (such as floppy disks, magnetic tapes, and hard disk drives), magneto-optical recording media (such as magneto-optical disks), CD-ROM (Compact Disc Read Only Memory), CD-R, CD-R /W And semiconductor memories such as ROM, PROM (Programmable ROM), EPROM (Rewritable PROM), Flash ROM, and RAM (Random Access Memory).
  • these programs can be provided to a computer by using various types of transient computer readable media.
  • Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves.
  • the transitory computer readable medium can be used to provide a program to a computer via a wired communication path such as a wire and an optical fiber or a wireless communication path.
  • a computer program or a computer readable storage medium for recording instructions executable by a processor when executed by a processor, causes the processor to perform speech input using
  • the verification method comprises: when the verification request is filed, the user inputs the acquired code for verification by voice; recognizes the input voice, extracts the recognized voice feature and the recognized code; and determines the recognized voice feature Whether it is consistent with a predetermined voice feature; determining whether the identified code is consistent with a preset verification code; in the case where both of the determination results are "consistent", the user verification passes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)
  • Telephone Function (AREA)

Abstract

本公开提供一种使用语音输入进行验证的方法和系统(100)。在提出验证请求时，语音输入装置(101)使用户将所获取的用于验证的代码通过语音进行输入。语音识别装置(102)识别输入的语音，提取识别出的语音特征和识别出的代码。语音特征判断装置(103)判断识别出的语音特征是否与预先确定的语音特征相一致。代码判断装置(104)判断识别出的代码是否与预先设置的验证码相一致。验证装置(105)在上述两个判断装置的判断结果均为"相一致"的情况下，输出验证通过的指令。本发明避免了他人冒用用户身份输入密码或验证码的不安全情形。同时，通过增加语音识别的安全手段，进一步提升了应用和服务的安全性。

Description

使用语音输入进行验证的方法和系统 技术领域
本发明涉及用户身份验证，更具体涉及使用语音输入进行验证的方法和系统。
背景技术
随着在电脑或移动设备上安装的应用和服务的数量越来越多，这些应用和服务的安全问题引起了人们的注意。安全问题之一是确定使用应用和服务的用户身份，特别是在一些涉及财务、支付、涉及个人隐私或其他对安全要求很严格的应用和服务中，确定用户身份是很重要的一个环节。
现有的应用和服务进行用户身份验证的手段一般是使用验证码。具体地说，可以是固定密码验证、随机密码验证。例如，作为随机密码验证的一个步骤，随机密码一般会发送到用户指定的设备上，例如发送到用户手机上。但是，这样的场景的安全性是基于一个前提的，即用户自己持有用户设备，例如手机。如果用户手机被盗，或者手机被其他人所控制，那么密码就会被手机当前的持有者所获得，则该持有者可以利用发送到手机上的密码来完成应用和服务所需的身份验证，从而以安全用户的身份进行危害用户财产或隐私安全的行为(例如交易等)。在这种情况下，所谓的安全性荡然无存。
除了密码之外，为了防止对应用和服务的恶意攻击或不正常使用(例如使用计算机程序多次登录、多次提交信息、多次评论、刷票、刷好评等等)，应用和服务还会使用额外的验证码来进行验证。例如，通过用图片来显示规则或不规则的数字、汉字、字母或其他字符，要求用户输入这些字符来进行验证。
目前常见的密码为数字序列(例如4位或6位数字)。但是数字密码相对来说是容易被破解或被泄露，图片中的数字验证码也容易被识别，从而失 去其验证的意义。随着人工智能的不断发展，即使使用字母和/或汉字等其他字符来作为密码或者验证码，其安全性也还是有局限性的。
发明内容
为了解决上述问题，本发明提供一种使用语音输入进行验证的方法和系统。用户需要用语音的方式输入密码或验证码，即朗读出密码或验证码，应用或服务通过语音识别来验证输入的密码或验证码。验证分为两个方面：一方面是代码的验证；另一方面则是语音的验证，即语音需要与用户的语音相一致。这样避免了他人冒用用户身份输入密码或验证码的不安全情形。同时，通过增加语音识别的安全手段，进一步提升了应用和服务的安全性。
根据本发明的第一方面，提供一种使用语音输入进行验证的方法，包括：当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入；识别输入的语音，提取识别出的语音特征和识别出的代码；判断识别出的语音特征是否与预先确定的语音特征相一致；判断识别出的代码是否与预先设置的验证码相一致；在上述两个判断结果均为“相一致”的情况下，用户验证通过。
在两个判断结果中任何一个为“不一致”的情况下，用户验证失败。
优选地，所述代码可以是可用语音读出的字符。所述代码可以是字母、数字和汉字中的一种或组合。
一方面，所述的预先确定的语音特征可以预先存储在用户设备上。另一方面，所述的预先确定的语音特征可以预先存储在服务器或云端。
一方面，所述的预先设置的验证码可以由用户设备在本地生成。另一方面，所述的预先设置的验证码可以由服务器或云端生成并发送给用户。
根据本发明的第二方面，提供一种使用语音输入进行验证的系统，包括：语音输入装置，用于在提出验证请求时，使用户将所获取的用于验证的代码 通过语音进行输入；语音识别装置，用于识别输入的语音，提取识别出的语音特征和识别出的代码；语音特征判断装置，用于判断识别出的语音特征是否与预先确定的语音特征相一致；代码判断装置，用于判断识别出的代码是否与预先设置的验证码相一致；验证装置，用于在上述两个判断装置的判断结果均为“相一致”的情况下，输出验证通过的指令。
根据本发明的第三方面，提供一种计算机可读存储介质，用于记录可由处理器执行的指令，所述指令在被处理器执行时，使得处理器执行使用语音输入进行验证的方法，包括：当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入；识别输入的语音，提取识别出的语音特征和识别出的代码；判断识别出的语音特征是否与预先确定的语音特征相一致；判断识别出的代码是否与预先设置的验证码相一致；在上述两个判断结果均为“相一致”的情况下，用户验证通过。
本发明的一个优势在于，在用户手机被他人持有的情况下，由于他人的语音输入无法与用户自身的语音相匹配，会造成验证失败，从而保护了用户的安全。
而且，在要求使用图片中的验证码进行输入时，通过增加语音识别环节，进一步避免了恶意或不正常访问，从而保证交易活动的真实性和安全性。
附图说明
下面参考附图结合实施例说明本发明。在附图中：
图1是图示说明根据本发明的实施例的使用语音输入进行验证的系统的示意图。
图2是图示说明根据本发明的实施例的使用语音输入进行验证的方法的流程图。
具体实施方式
下面将结合附图来详细解释本发明的具体实施例。
在下文中，密码或验证码等用于验证的字符型代码可以被统一称为验证码或代码。
图1是图示说明根据本发明的实施例的使用语音输入进行验证的系统的示意图。
如图1中所示，根据本发明的使用语音输入进行验证的系统100包括：语音输入装置101、语音识别装置102、语音特征判断装置103、代码判断装置104和验证装置105。
在运行一些应用或接入一些服务时，相应的应用或服务可能会要求用户进行验证。例如，当我们通过桌面电脑或移动设备上的付款应用进行支付时，付款应用可能会要求使用者输入用户密码和/或随机验证码。用户密码可以是用户提前设置好，由应用进行预先存储以便今后检验；用户密码可以存储在用户设备上以方便查验，也可以存储在云端或服务器上，在调用云端或服务器上的服务时进行查验。随机验证码则可以由应用或服务的后端服务器发送到用户预留或当前指定的移动设备上。随机验证码也可以由本地用户设备或者后端服务器以网页图片的形式提供给用户。例如，我们常见的网站图形验证码是将验证码(代码)隐藏在图片中，由用户进行识别，然后输入到验证码的方框中。
根据本发明的实施例，在例如由应用或服务提出验证请求时，语音输入装置101使用户将所获取的用于验证的代码通过语音进行输入。如前面所述，用户获取的用于验证的代码(简称为验证码)可以是提前设置好的，也可以是临时、随机设置从而发送给用户设备的。这里需要注意的是，用户设备可以是用户用来进行应用或服务的设备，也可以是另外的设备。
根据本发明的实施例，所述的代码是可用语音读出的字符。例如，所述代码可以是字母、数字和汉字中的一种或组合。
根据本发明的实施例，例如，用户获取的验证码是“123456”，则用户 通过按顺序朗读“1”、“2”、“3”、“4”、“5”、“6”来进行语音输入。
语音识别装置102识别通过语音输入装置101输入的语音，提取识别出的语音特征和识别出的代码。用户的语音可以输入到运行应用或服务的用户设备中进行识别，也可以输入到第三方设备中进行识别，在第三方设备做出下文所述的判断结果后通知用户设备，或者也可以是输入到用户设备，由用户设备转发到第三方设备进行识别处理。
所述的语音特征可以是具体的语音或语音片段，也可以是语音的特征参数。本发明所使用的语音特征是用于区分不同用户的。例如，不同的用户的语音会呈现不同的基音、基频、谐波，并且清音和浊音的发声都会有不同的特点。这些声音的特点也可以被称作“声纹”。本领域技术人员应该理解，根据不同的语音识别算法，可以选取不同的语音特征来用于区分不同用户。本发明包括所有这些语音特征，并且在实际应用中不局限于其中任何一种语音特征。
除了识别语音特征，语音识别装置102还需要识别出具体的代码(验证码)。本领域技术人员应当理解，在实际应用中，可以选用合适的语音识别算法来识别用户通过语音输入的代码。
语音特征判断装置103判断语音识别装置102识别出的语音特征是否与预先确定的语音特征相一致。如前所述，语音特征是用于区分不同用户的。所以，特定的用户，例如用户设备的使用者或主人可以预先确定好自己的语音特征，例如通过预定的程序录制一些语音以训练得到自己的语音特征，或者例如预先录制一些可能用于验证码的特定字符的语音(诸如字母、数字、规定范围内的若干汉字、或者一些声母、韵母等发音元素)。总之，语音特征判断装置103可以调用到这样的预先确定的语音特征，从而可以与从输入的语音中识别出的语音特征进行比较。如果比较结果相一致，则说明当前输入语音的用户就是预先确定语音特征的用户，即相同用户。
根据本发明的实施例，所述的预先确定的语音特征可以预先存储在用于 接收语音的用户设备上。例如，用户直接在手机上预先进行语音训练，从而将自己的语音特征存储在手机上，以便今后的验证。另一方面，所述的预先确定的语音特征也可以预先存储在服务器或云端。例如，用户在用户设备上进行了语音训练之后，将训练结果，即提炼出的语音特征转存到服务器或云端上，以便今后用户在不同用户设备上都能进行验证。
代码判断装置104判断语音识别装置102识别出的代码是否与预先设置的验证码相一致。如前所述，验证码可以是授权用户预先设置的，也可以是由应用或服务、用户设备、云端或服务器根据验证的请求而预先设置并提供或呈现给用户的。这里所述的“预先”设置，是相对于用户的输入与语音识别而言的，即，验证码在预先设置好之后，才谈得上以后的验证这一环节。总之，代码判断装置104可以调用到这样的预先设置的验证码，从而可以与从输入的语音中识别出的代码进行比较，以达到验证的目的。
根据本发明的实施例，所述的预先设置的验证码可以由用户设备在本地生成，也可以由服务器或云端生成并发送给用户。
在上述两个判断装置的判断结果均为“相一致”的情况下，验证装置105输出验证通过的指令。
另一方面，在两个判断结果中任何一个为“不一致”的情况下，验证装置105可以输出用户验证失败的指示或指令。因此，在图1中，将验证装置105的框绘制成了一个与门(AND gate)的形态，以反映其逻辑功能。
可以设想这样一种应用场景：用户需要使用手机或电脑上的支付工具(应用或服务)进行支付。该支付工具在支付交易发生前，要求用户进行身份验证。一方面，该支付工具可以要求用户提供个人账号和/或密码；另一方面，该支付工具的后台服务器可以向该用户的移动设备(例如手机)发送一条消息，该消息中包括验证码，用户需要输入接收到的验证码以进行双重校验。这样的验证方案是为了保证上述交易是在用户知情并允许的情况下发生的。该验证方案的一个前提是用户的移动设备一定是用户自己持有的。如背 景技术中所述，如果用户的移动设备被盗或被他人控制，则上述的验证方案将会失去意义。
根据本发明，在同样的应用场景中，用户需要进行语音输入。也就是说，除了对验证码本身进行比对验证之外，还需要对输入验证码的人进行语音识别，以判断这个人是否就是用户本人。本领域技术人员应该可以想到，这样的识别除了语音识别之外，还可以是其他的附带生物特征的识别，比如虹膜、指纹、掌纹等识别。但是，本发明的特点在于，将验证码与语音相结合，输入的载体是语音，输入的内容是代码。通过语音识别，既可以实现语音特征的验证(用户本人身份的验证)，也可以实现字母、数字、汉字等字符代码(只要它们是可读的，即可以使用语音来表示和区分)的验证(验证码的验证)。
在这样的场景中，如果是他人冒用用户的身份进行交易，在语音识别之后，会发现输入的语音的语音特征与用户的语音特征不相符，从而可以拒绝交易。另外，因为采用了语音输入且识别、验证语音特征的方式，杜绝了使用机器或计算机程序进行重复登录、刷票、刷好评等不正常行为，从而进一步加强了应用或服务的安全性。
图2是图示说明根据本发明的实施例的使用语音输入进行验证的方法的流程图。
如图2中所示，根据本发明的使用语音输入进行验证的方法200开始于步骤S201，在该步骤，当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入。
根据本发明的实施例，所述代码是可用语音读出的字符。例如，所述代码可以是字母、数字和汉字中的一种或组合。
在步骤S203，识别输入的语音，提取识别出的语音特征和识别出的代码。
在步骤S205，判断识别出的语音特征是否与预先确定的语音特征相一致。
根据本发明的实施例，所述的预先确定的语音特征可以预先存储在用于接收语音的用户设备上，也可以预先存储在服务器或云端。
在步骤S207，判断识别出的代码是否与预先设置的验证码相一致。
根据本发明的实施例，所述的预先设置的验证码可以由用户设备在本地生成，也可以由服务器或云端生成并发送给用户。另外，所述的预先设置的验证码还可以是用户自己来预先设置的，并由用户自己来保存或记忆。
步骤S205和S207可以是一前一后进行，也可以并行同时进行。即使是一前一后进行的情况，步骤S205也并不必然在步骤S207之前或之后进行。也就是说，尽管根据图2中所示，步骤S205和S207是按顺序进行的，但该图示只是一个示例，并不希望限定这样的次序。
在步骤S209，在上述两个步骤S205和S207的判断结果均为“相一致”的情况下，用户验证通过。
另一方面，在两个判断结果中任何一个为“不一致”的情况下，用户验证失败。
本领域普通技术人员应该认识到，本发明的方法和系统可以实现为计算机程序。如上结合图1和2所述，根据上述实施例的方法和系统可以执行一个或多个程序，包括指令来使得计算机或处理器执行结合附图所述的算法。这些程序可以使用各种类型的非瞬时计算机可读介质存储并提供给计算机或处理器。非瞬时计算机可读介质包括各种类型的有形存贮介质。非瞬时计算机可读介质的示例包括磁性记录介质(诸如软盘、磁带和硬盘驱动器)、磁光记录介质(诸如磁光盘)、CD-ROM(紧凑盘只读存储器)、CD-R、CD-R/W 以及半导体存储器(诸如ROM、PROM(可编程ROM)、EPROM(可擦写PROM)、闪存ROM和RAM(随机存取存储器))。进一步，这些程序可以通过使用各种类型的瞬时计算机可读介质而提供给计算机。瞬时计算机可读介质的示例包括电信号、光信号和电磁波。瞬时计算机可读介质可以用于通过诸如电线和光纤的有线通信路径或无线通信路径提供程序给计算机。
因此，根据本发明，还可以提供一种计算机程序或一种计算机可读存储介质，用于记录可由处理器执行的指令，所述指令在被处理器执行时，使得处理器执行使用语音输入进行验证的方法，包括：当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入；识别输入的语音，提取识别出的语音特征和识别出的代码；判断识别出的语音特征是否与预先确定的语音特征相一致；判断识别出的代码是否与预先设置的验证码相一致；在上述两个判断结果均为“相一致”的情况下，用户验证通过。
上面已经描述了本发明的各种实施例和实施情形。但是，本发明的精神和范围不限于此。本领域技术人员将能够根据本发明的教导而做出更多的应用，而这些应用都在本发明的范围之内。

Claims (10)

  1. 一种使用语音输入进行验证的方法，包括：
    当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入；
    识别输入的语音，提取识别出的语音特征和识别出的代码；
    判断识别出的语音特征是否与预先确定的语音特征相一致；
    判断识别出的代码是否与预先设置的验证码相一致；
    在上述两个判断结果均为“相一致”的情况下，用户验证通过。
  2. 根据权利要求1所述的方法，其中，在两个判断结果中任何一个为“不一致”的情况下，用户验证失败。
  3. 根据权利要求1所述的方法，其中，所述代码是可用语音读出的字符。
  4. 根据权利要求3所述的方法，其中，所述代码是字母、数字和汉字中的一种或组合。
  5. 根据权利要求1所述的方法，其中，所述的预先确定的语音特征预先存储在用于接收语音的用户设备上。
  6. 根据权利要求1所述的方法，其中，所述的预先确定的语音特征预先存储在服务器或云端。
  7. 根据权利要求1所述的方法，其中，所述的预先设置的验证码由用户设备在本地生成。
  8. 根据权利要求1所述的方法，其中，所述的预先设置的验证码由服务器或云端生成并发送给用户。
  9. 一种使用语音输入进行验证的系统，包括：
    语音输入装置，用于在提出验证请求时，使用户将所获取的用于验证的代码通过语音进行输入；
    语音识别装置，用于识别输入的语音，提取识别出的语音特征和识别出的代码；
    语音特征判断装置，用于判断识别出的语音特征是否与预先确定的语音特征相一致；
    代码判断装置，用于判断识别出的代码是否与预先设置的验证码相一致；
    验证装置，用于在上述两个判断装置的判断结果均为“相一致”的情况下，输出验证通过的指令。
  10. 一种计算机可读存储介质，用于记录可由处理器执行的指令，所述指令在被处理器执行时，使得处理器执行使用语音输入进行验证的方法，包括：
    当提出验证请求时，用户将所获取的用于验证的代码通过语音进行输入；
    识别输入的语音，提取识别出的语音特征和识别出的代码；
    判断识别出的语音特征是否与预先确定的语音特征相一致；
    判断识别出的代码是否与预先设置的验证码相一致；
    在上述两个判断结果均为“相一致”的情况下，用户验证通过。
PCT/CN2017/112143 2017-05-17 2017-11-21 使用语音输入进行验证的方法和系统 WO2018209918A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710346554.0A CN107147499A (zh) 2017-05-17 2017-05-17 使用语音输入进行验证的方法和系统
CN201710346554.0 2017-05-17

Publications (1)

Publication Number Publication Date
WO2018209918A1 true WO2018209918A1 (zh) 2018-11-22

Family

ID=59778572

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/112143 WO2018209918A1 (zh) 2017-05-17 2017-11-21 使用语音输入进行验证的方法和系统

Country Status (2)

Country Link
CN (1) CN107147499A (zh)
WO (1) WO2018209918A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107147499A (zh) * 2017-05-17 2017-09-08 刘光明 使用语音输入进行验证的方法和系统
CN108391005A (zh) * 2018-02-07 2018-08-10 宁夏凯速德科技有限公司 终端app的打开方法和装置
CN109087647B (zh) * 2018-08-03 2023-06-13 平安科技（深圳）有限公司 声纹识别处理方法、装置、电子设备及存储介质
CN109493872B (zh) * 2018-12-13 2021-12-14 北京三快在线科技有限公司 语音信息验证方法及装置、电子设备、存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101685635A (zh) * 2008-09-23 2010-03-31 吕共欣 身份验证系统及方法
CN102543084A (zh) * 2010-12-29 2012-07-04 盛乐信息技术（上海）有限公司 在线声纹认证系统及其实现方法
CN102916815A (zh) * 2012-11-07 2013-02-06 华为终端有限公司 用户身份验证的方法和装置
CN103546622A (zh) * 2012-07-12 2014-01-29 百度在线网络技术（北京）有限公司 基于声纹的识别登录控制方法、装置及系统
CN104660413A (zh) * 2015-01-28 2015-05-27 中国科学院数据与通信保护研究教育中心 一种声纹口令认证方法和装置
CN107147499A (zh) * 2017-05-17 2017-09-08 刘光明 使用语音输入进行验证的方法和系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102254559A (zh) * 2010-05-20 2011-11-23 盛乐信息技术（上海）有限公司 基于声纹的身份认证系统及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101685635A (zh) * 2008-09-23 2010-03-31 吕共欣 身份验证系统及方法
CN102543084A (zh) * 2010-12-29 2012-07-04 盛乐信息技术（上海）有限公司 在线声纹认证系统及其实现方法
CN103546622A (zh) * 2012-07-12 2014-01-29 百度在线网络技术（北京）有限公司 基于声纹的识别登录控制方法、装置及系统
CN102916815A (zh) * 2012-11-07 2013-02-06 华为终端有限公司 用户身份验证的方法和装置
CN104660413A (zh) * 2015-01-28 2015-05-27 中国科学院数据与通信保护研究教育中心 一种声纹口令认证方法和装置
CN107147499A (zh) * 2017-05-17 2017-09-08 刘光明 使用语音输入进行验证的方法和系统

Also Published As

Publication number Publication date
CN107147499A (zh) 2017-09-08

Similar Documents

Publication Publication Date Title
JP7182924B2 (ja) モバイルセキュリティ対策
CN110647730B (zh) 经由单独的处理路径进行单通道输入多因素认证
US11461781B2 (en) Pro-active identity verification for authentication of transaction initiated via non-voice channel
US9571490B2 (en) Method and system for distinguishing humans from machines
US9544308B2 (en) Compliant authentication based on dynamically-updated credentials
US20200244650A1 (en) Multi-factor secure operation authentication
US20210089635A1 (en) Biometric identity verification and protection software solution
WO2018209918A1 (zh) 使用语音输入进行验证的方法和系统
AU2013205396B2 (en) Methods and Systems for Conducting Smart Card Transactions
US20080270132A1 (en) Method and system to improve speaker verification accuracy by detecting repeat imposters
US11902275B2 (en) Context-based authentication of a user
US11665153B2 (en) Voice biometric authentication in a virtual assistant
US11663306B2 (en) System and method for confirming a person's identity
BR112021009895A2 (pt) método, e, dispositivo de assistente digital
US20190166130A1 (en) Enhanced Security Using Wearable Device with Authentication System
US10939291B1 (en) Systems and methods for photo recognition-based identity authentication
US20200327310A1 (en) Method and apparatus for facial verification
Mondal et al. Transaction authorization from Know Your Customer (KYC) information in online banking
KR102633314B1 (ko) 인증 정보 처리 방법 및 장치와 인증 정보 처리 방법 장치를 포함한 사용자 단말
KR20160112856A (ko) 화자 인증을 이용한 금융 보안 시스템 및 그 방법
US20230325481A1 (en) Method and System for Authentication of a Subject by a Trusted Contact
KR20140029990A (ko) 생체정보를 이용한 본인인증 시스템 및 방법
KR102459974B1 (ko) 인증 시스템 및 방법
US20230130024A1 (en) System and method for storing encryption keys for processing a secured transaction on a blockchain
Felker et al. Voice input for authentication

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: 17910392

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17910392

Country of ref document: EP

Kind code of ref document: A1