KR20130022638A - The method and apparatus for security using voice - Google Patents
The method and apparatus for security using voice Download PDFInfo
- Publication number
- KR20130022638A KR20130022638A KR1020110085371A KR20110085371A KR20130022638A KR 20130022638 A KR20130022638 A KR 20130022638A KR 1020110085371 A KR1020110085371 A KR 1020110085371A KR 20110085371 A KR20110085371 A KR 20110085371A KR 20130022638 A KR20130022638 A KR 20130022638A
- Authority
- KR
- South Korea
- Prior art keywords
- input
- voice
- pattern information
- length
- inputs
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
Abstract
A security method using voice is disclosed. In the security method using the voice, the counter circuit calculates an input duration of each of the plurality of voice inputs inputted at a time difference through the voice input unit, and the input pattern extraction module calculates each of the plurality of voice inputs. (B) extracting first pattern information according to the length of the input duration with respect to, and a comparing module compares the extracted first pattern information with the second pattern information stored in a memory, and determines a host according to the comparison result. (C) controlling.
Description
An embodiment according to the concept of the present invention relates to a security method using a voice. In particular, in the case of extracting pattern information of a plurality of voice inputs inputted with a time difference, comparing the extracted pattern information with pattern information stored in a memory and matching the same It relates to a method for maintaining security by only allowing a specific operation and apparatuses using the method.
There are various kinds of techniques used to maintain security. For example, a method of receiving a password using a combination of letters and numbers, storing fingerprint information with unique characteristics for each person, and authenticating it through fingerprint recognition, and unique characteristics for each person. The iris information stored in the memory is stored in memory and authenticated through iris recognition.
In addition, there is a method of authenticating through voice recognition. Speech recognition is to identify linguistic meaning contents from speech by automatic means. Specifically, speech recognition is a process of inputting a speech waveform to identify a word or word string and extracting meaning based on the identification result.
Speech recognition is classified into five categories: speech analysis, phoneme recognition, word recognition, sentence interpretation, and meaning extraction, and narrowly, speech analysis, phoneme recognition, and word recognition. Speech recognition is mainly used for bank balance inquiry, telephone price inquiry, mail order application, credit card inquiry, hotel or aircraft seat reservation by telephone.
The technical problem to be achieved by the present invention is to calculate the input duration of each of the plurality of voice inputs input with a time difference and to extract the pattern information according to the length of the input duration for each of the calculated plurality of voice inputs The present invention provides a method and apparatus for maintaining security by allowing a specific operation only when the extracted pattern information and the pattern information stored in the memory are matched and matched.
In the security method using a voice according to an embodiment of the present invention (a) the counter circuit calculates the input duration of each of a plurality of voice inputs inputted with a time difference through the voice input unit, the input pattern extraction module is calculated (B) extracting first pattern information according to the length of the input duration for each of a plurality of voice inputs, and comparing the extracted first pattern information with second pattern information stored in a memory; (C) controlling the host according to the comparison result.
According to an embodiment, the security method using the voice may further include (d) calculating, before the step (a), the counter circuit to calculate an input duration of each of a plurality of button inputs inputted at a time interval through a password input button. (E) extracting second pattern information according to the length of the input duration for each of the plurality of button inputs calculated by the input pattern extraction module and storing the extracted second pattern information in the memory; It may further include.
In the step (b), the input pattern extraction module compares the length of the input duration and the length of the reference time for each of the plurality of voice inputs, and has a length greater than the length of the reference time. The first pattern information may be extracted by distinguishing each of the plurality of voice inputs into long voice inputs and voice inputs having a length shorter than the length of the reference time.
According to an embodiment, the security method using the voice may further include the step (f) of outputting a sound during the reference time between the steps (e) and (a).
According to an embodiment, the security method using the voice may include the counter circuit, the input pattern extraction module, or, after the step (c), when the comparison result output from the comparison module is inconsistent for a limited number of times. The comparison module may further include the step (g) of not processing the input during the input prohibition time.
In the security method using the voice according to an embodiment of the present invention (a) the counter circuit calculates the input duration for each of the plurality of voice inputs inputted with a time difference through the voice input unit, and the input pattern extraction module (B) extracting the pattern information according to the length of the input duration for each of the calculated plurality of voice inputs and storing the extracted pattern information in a memory, wherein the counter circuit inputs the time difference through the voice input unit (C) calculating the input duration for each of the plurality of voice inputs, wherein the input pattern extraction module extracts the pattern information according to the length of the input duration for each of the calculated plurality of voice inputs. (D) extracting, and comparing module compares the extracted pattern information with the pattern information stored in the memory, It may comprise (e) controlling the host la.
According to an embodiment of the present invention, a security device using a voice may include a counter circuit that calculates an input duration of each of a plurality of voice inputs that are input at a time difference through a voice input unit, and the input for each of the calculated plurality of voice inputs. The input pattern extraction module extracts the first pattern information according to the length of the duration, and the comparison module compares the extracted first pattern information with the second pattern information stored in the memory.
According to an embodiment, the security apparatus using the voice may further include a password registration unit for registering the second pattern information.
According to an embodiment, the security apparatus using the voice may further include a control module controlling a host according to a comparison result of the comparison module.
Method and device according to an embodiment of the present invention is to receive a password through voice, and to control the specific operation according to whether or not the input password is stored in advance by the effective input through the voice if it is difficult to input by hand There is a possible effect.
In addition, since the method and the apparatus according to the embodiment of the present invention use the pattern of the voice, the recognition error is less than that of the content of the voice, and there is an effect that the language is not used.
In addition, the method and the device according to an embodiment of the present invention is advantageous in that it is advantageous to apply to a small device because a small number of keys are required when a password is input through a button.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to more fully understand the drawings recited in the detailed description of the present invention, a detailed description of each drawing is provided.
1 is a plan view of a security device using voice according to an embodiment of the present invention.
FIG. 2 is a block diagram of an embodiment of a security device using a voice shown in FIG. 1.
FIG. 3A is a graph illustrating an exemplary embodiment of a reference input that is a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
3B is a graph illustrating an embodiment of a voice input that may be input to the voice input unit illustrated in FIG. 2.
FIG. 4A is a graph illustrating another embodiment of a reference input as a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
FIG. 4B is a graph illustrating another embodiment of a reference input serving as a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
4C is a graph illustrating another embodiment of a voice input that may be input to the voice input unit illustrated in FIG. 2.
5 is a flowchart illustrating a security method using voice according to an embodiment of the present invention.
6 is a flowchart illustrating a security method using voice according to another embodiment of the present invention.
7 is a flowchart illustrating a security method using voice according to another embodiment of the present invention.
It is to be understood that the specific structural or functional descriptions of embodiments of the present invention disclosed herein are only for the purpose of illustrating embodiments of the inventive concept, But may be embodied in many different forms and is not limited to the embodiments set forth herein.
Embodiments in accordance with the concepts of the present invention are capable of various modifications and may take various forms, so that the embodiments are illustrated in the drawings and described in detail herein. It should be understood, however, that it is not intended to limit the embodiments according to the concepts of the present invention to the particular forms disclosed, but includes all modifications, equivalents, or alternatives falling within the spirit and scope of the invention.
The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are intended to distinguish one element from another, for example, without departing from the scope of the invention in accordance with the concepts of the present invention, the first element may be termed the second element, The second component may also be referred to as a first component.
When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between. Other expressions describing the relationship between components, such as "between" and "immediately between," or "neighboring to," and "directly neighboring to" should be interpreted as well.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, the terms "comprises ", or" having ", or the like, specify that there is a stated feature, number, step, operation, , Steps, operations, components, parts, or combinations thereof, as a matter of principle.
Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.
BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, the present invention will be described in detail with reference to the preferred embodiments of the present invention with reference to the accompanying drawings.
1 is a plan view of a security device using voice according to an embodiment of the present invention.
Referring to FIG. 1, the
The
In FIG. 1, although the
The voice input unit 20-1 receives a voice input from the user. According to an embodiment, the user may input a voice in a password registration step and a password authentication step.
According to an embodiment, the speaker 20-2 may output a sound for a predetermined time before a user inputs a voice. According to an embodiment, the constant time may be a reference time. The reference time is described in detail in FIGS. 3A, 4A, and 4B.
The
In FIG. 1, for convenience of description, the
According to an embodiment, the
According to an embodiment, when the
In this case, the
FIG. 2 is a block diagram of an embodiment of a security device using a voice shown in FIG. 1.
Referring to FIG. 2, the
Since the
The
When a plurality of inputs are inputted to the
The input
The
In addition, the
In FIG. 2, the
The
According to an embodiment, the
The
The
2 illustrates an example in which the
FIG. 3A is a graph illustrating an exemplary embodiment of a reference input that is a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
Referring to FIG. 3A, the reference input may include at least one of information about a reference time TIref and information about a reference voice volume dB1.
The reference time TIref is a reference time when the input
The reference voice loudness dB1 is a voice loudness that is a reference for preventing noise from occurring when the voice input is input with noise. According to an embodiment, the voice input unit 20-1 of FIG. 2 may accept only an input of a voice that is equal to or larger than the reference voice size dB1.
According to an embodiment, the information about the reference time TIref and the reference voice loudness dB1 of the reference input may be stored in the
3B is a graph illustrating an embodiment of a voice input that may be input to the voice input unit illustrated in FIG. 2.
Referring to FIG. 3B, a graph according to an exemplary embodiment in which five voice inputs are input with a time difference is illustrated.
For convenience of description, the input pattern extraction module (32 in FIG. 2) sets the voice input having a length shorter than the reference time TIref to "0", and the voice input having a length equal to or longer than the reference time TIref is set to "1". Assume it is patterned.
In the first input section TI1, a voice input is input during a section in which the time t is from 1 second to 4 seconds, so that the input duration is 3 seconds. When the length of the first input section TI1 is compared with 2 seconds, which is the reference time TIref, since the length of the first input section TI1 is longer, the first input input to the first input section TI1 is "1." Patterned as ".
In the second input section TI2, a voice input is input during a section in which the time t is 6 to 7 seconds, so that the input duration is 1 second. When the length of the second input section TI2 is compared with 2 seconds, which is the reference time TIref, the second input input to the second input section TI2 is 0 because the length of the second input section TI2 is shorter. Patterned with ".
In the third input section TI3, a voice input is input during a section in which time t is 8 seconds to 9.5 seconds, so that the input duration is 1.5 seconds. When the length of the third input section TI3 is compared with 2 seconds, which is the reference time TIref, the third input input to the third input section TI3 is 0 because the length of the third input section TI1 is shorter. Patterned with ".
In the fourth input section TI4, a voice input is input during a section in which time t is 11 seconds to 13.5 seconds, so that the input duration is 2.5 seconds. When the length of the fourth input section TI4 is longer than that of the reference time TIref of 2 seconds, the fourth input section TI4 is longer than the first input section TI4 because the length of the fourth input section TI4 is longer. Patterned as ".
In the fifth input section TI5, a voice input is input during a section in which time t is 15 seconds to 16 seconds, so that the input duration is 1 second. When the length of the fifth input section TI5 is compared with 2 seconds, which is the reference time TIref, the fifth input input to the fifth input section TI5 is 0 because the length of the fifth input section TI5 is shorter. Patterned with ".
Therefore, the voice inputs according to the exemplary embodiment illustrated in FIG. 3B may be patterned as “10010”.
4A is a graph according to another exemplary embodiment of a reference input, which is a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
4A and 4B, a first reference input when two reference inputs are shown is shown.
The first reference time TIref1 is a time when the input
Since the reference voice loudness dB2 has substantially the same meaning as the reference voice loudness dB1 of FIG. 3A, description thereof is omitted.
According to an embodiment, the information about the first reference time TIref1 and the reference voice volume dB2 of the first reference input may be stored in the
FIG. 4B is a graph illustrating another embodiment of a reference input serving as a reference when the input pattern extraction module illustrated in FIG. 2 extracts pattern information from a voice input.
4A and 4B, a second reference input when two reference inputs are shown is shown.
The second reference time TIref2 is a reference time when the input
Since the reference voice loudness dB2 has substantially the same meaning as the reference voice loudness dB1 of FIG. 3A, description thereof is omitted.
According to an embodiment, the information about the second reference time TIref2 and the reference voice loudness dB2 of the second reference input may be stored in the
4C is a graph according to another exemplary embodiment of a voice input that may be input to the voice input unit illustrated in FIG. 2.
Referring to FIG. 4C, a graph according to an exemplary embodiment in which six voice inputs are input with a time difference is shown.
For convenience of description, the input
According to an exemplary embodiment, a voice input having a length equal to or longer than the second reference time TIref2 may be patterned with a binary code “10”.
In the first input section TI1, a voice input is input during a section in which the time t is from 1 second to 2 seconds, so that the input duration is 1 second. Since the length of the first input section TI1 is shorter than the length of the first reference time TIref1, the first input input to the first input section TI1 is patterned as “0”.
In the second input section TI2, a voice input is input during a section in which the time t is 4 to 7 seconds, so that the input duration is 3 seconds. Since the length of the second input section TI2 is longer than the length of the first reference time TIref1 and shorter than the length of the second reference time TIref2, the second input input to the second input section TI2 is " Patterned to 1 ".
In the third input section TI3, a voice input is input during a section in which the time t is 8 seconds to 11.5 seconds, so that the input duration is 3.5 seconds. Since the length of the third input section TI3 is longer than the length of the first reference time TIref1 and shorter than the length of the second reference time TIref2, the third input input to the third input section TI3 is ". Patterned to 1 ".
In the fourth input section TI4, a voice input is input during a section in which the time t is 13 seconds to 14 seconds, so that the input duration is 1 second. Since the length of the fourth input section TI4 is shorter than the length of the first reference time TIref1, the fourth input input to the fourth input section TI4 is patterned as “0”.
In the fifth input section TI5, a voice input is input during a section in which time t is 15 seconds to 21 seconds, so that the input duration is 6 seconds. Since the length of the fifth input section TI5 is longer than the length of the second reference time TIref2, the fifth input input to the fifth input section TI5 is patterned as “2”. According to an embodiment, the fifth input may be patterned into a binary code “10”.
In the sixth input section TI6, a voice input is input during a section in which the time t is 22 seconds to 23.5 seconds, so that the input duration is 1.5 seconds. Since the length of the sixth input section TI6 is shorter than the length of the first reference time TIref1, the sixth input input to the sixth input section TI6 is patterned as “0”.
Accordingly, voice inputs according to the exemplary embodiment illustrated in FIG. 4C are patterned as “011020”.
3A to 4C illustrate an exemplary embodiment in which each of the voice inputs is patterned compared to the reference input. The case where the button inputs are patterned is similar to the case where the voice inputs are patterned, but the portion corresponding to the voice size of the reference input may vary.
5 is a flowchart illustrating a security method using voice according to an embodiment of the present invention.
2 to 5, the
The input
The extracted pattern information is stored in the
The voice input unit 20-1 may receive voice inputs for authentication from the user (S16).
The input
The
When the
When the
According to an embodiment, when the
6 is a flowchart illustrating a security method using voice according to another embodiment of the present invention.
FIG. 6 is a flow chart according to an embodiment of a process in which an input is limited to three times, and the input is limited when three or more inputs are wrong for convenience of description, and is not limited to the limited number.
2 and 6, the voice input unit 20-1 may receive voice inputs for authentication according to an embodiment (S30).
The input
The
When the
When the
Since steps S42 to S58 are substantially repetitions of steps S30 to S38, description thereof is omitted.
The voice input unit 20-1 receives a voice input for authentication again from the user (S60). The
The step of not processing the input (S62) is to enhance the security by preventing the continuous password input when the password is not mismatched by mistake. The input prohibition time may be 5 minutes according to one embodiment, but is not limited thereto.
7 is a flowchart illustrating a security method using voice according to another embodiment of the present invention.
1, 2, and 7, the speaker 20-2 outputs a sound for a reference time when the input
The step (S70) is to allow the user to know the length of the reference time that is a reference when the user inputs the pattern through voice input, according to an embodiment when the reference time is two or more You can output (音).
The voice input unit 20-1 may receive voice input for password registration according to an embodiment (S72).
The input
The extracted pattern information is stored in the
Since step S78 is substantially the same as step S70, the description is omitted.
The voice input unit 20-1 may receive voice inputs for password authentication from the user (S80).
The input
The
When the
Although the present invention has been described with reference to one embodiment shown in the drawings, this is merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.
10: enter button
20-1: voice input unit
20-2: Speaker
25: host
30: circuit
32, 36, 38: module
100: security device
Claims (9)
(B) extracting, by the input pattern extraction module, first pattern information according to the length of the input duration for each of the calculated plurality of voice inputs; And
And comparing (c) the extracted first pattern information with the second pattern information stored in the memory, and controlling the host according to the comparison result.
(D) before the step (a), the counter circuit calculates an input duration of each of a plurality of button inputs inputted with a time difference through an encryption input button; And
(E) extracting, by the input pattern extraction module, second pattern information according to the length of the input duration for each of the calculated plurality of button inputs and storing the extracted second pattern information in the memory. Security method using voice.
The input pattern extraction module compares the length of the input duration and the length of the reference time for each of the plurality of voice inputs, and the voice inputs longer than the length of the reference time and the length of the reference time. The voice method of extracting the first pattern information by dividing each of the plurality of voice inputs into shorter voice inputs.
And (f) outputting a sound during the reference time between steps (e) and (a).
After the step (c), if the comparison result outputted from the comparison module is inconsistent for a limited number of times continuously, the counter circuit, the input pattern extraction module, or the comparison module does not process the input during the input prohibition time. Security method using the voice further comprising the step (g).
(B) extracting, by the input pattern extraction module, pattern information according to the length of the input duration for each of the calculated plurality of voice inputs and storing the extracted pattern information in a memory;
(C) calculating, by the counter circuit, the input duration of each of the plurality of voice inputs inputted at a time difference through the voice input unit;
(D) extracting, by the input pattern extraction module, the pattern information according to the length of the input duration for each of the calculated plurality of voice inputs; And
And (e) comparing, by the comparison module, the extracted pattern information with the pattern information stored in the memory, and controlling the host according to the comparison result.
An input pattern extraction module for extracting first pattern information according to the length of the input duration for each of the calculated plurality of voice inputs; And
And a comparison module for comparing the extracted first pattern information with the second pattern information stored in the memory.
And a password registration unit for registering the second pattern information.
And a control module for controlling the host according to the comparison result of the comparison module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020110085371A KR20130022638A (en) | 2011-08-25 | 2011-08-25 | The method and apparatus for security using voice |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020110085371A KR20130022638A (en) | 2011-08-25 | 2011-08-25 | The method and apparatus for security using voice |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20130022638A true KR20130022638A (en) | 2013-03-07 |
Family
ID=48175239
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020110085371A KR20130022638A (en) | 2011-08-25 | 2011-08-25 | The method and apparatus for security using voice |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20130022638A (en) |
-
2011
- 2011-08-25 KR KR1020110085371A patent/KR20130022638A/en not_active Application Discontinuation
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106373575B (en) | User voiceprint model construction method, device and system | |
US10650379B2 (en) | Method and system for validating personalized account identifiers using biometric authentication and self-learning algorithms | |
US9311546B2 (en) | Biometric identity verification for access control using a trained statistical classifier | |
JP4213716B2 (en) | Voice authentication system | |
WO2017045414A1 (en) | Account login method and apparatus | |
US20080208580A1 (en) | Method and Dialog System for User Authentication | |
CN110169014A (en) | Device, method and computer program product for certification | |
KR100297833B1 (en) | Speaker verification system using continuous digits with flexible figures and method thereof | |
WO2016015687A1 (en) | Voiceprint verification method and device | |
CN112216281A (en) | Display apparatus and method for registering user command | |
CN103177238B (en) | Terminal and user identification method | |
CN107886958A (en) | A kind of express delivery cabinet pickup method and device based on vocal print | |
CN101231737A (en) | Method and system for enhancing internet bank trade security | |
CN104331652A (en) | Dynamic cipher generation method for electronic equipment for fingerprint and voice recognition | |
CN107533598B (en) | Input method and device of login password of application program and terminal | |
CN104269170B (en) | A kind of ERP authorities audio recognition method | |
JP2017057070A (en) | Authentication device of elevator user, and authentication method of the same | |
CN117953900A (en) | Database generation method, database generation device, and recording medium | |
JP2017120576A (en) | User authentication system, user authentication method, and program | |
CN109544745A (en) | A kind of intelligent door lock control method, apparatus and system | |
KR20130059999A (en) | Authentication system and method based by voice | |
KR102604319B1 (en) | Speaker authentication system and method | |
CN107615299A (en) | For assessing the method and system of fingerprint template | |
KR20130022638A (en) | The method and apparatus for security using voice | |
US11929077B2 (en) | Multi-stage speaker enrollment in voice authentication and identification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E601 | Decision to refuse application |