JP2007240588A - Voice authentication system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a voice authentication system in which dishonest act is hard, even when a registered data which is registered for authentication is leaked. <P>SOLUTION: Question information of a text form and a voice data which is an answer to the question are related and stored in an IC card, and when the IC card is read, a list of the plurality of questions is displayed (S2). When the answer to the selected question is input by voice (S3), a voice data is created by recording the voice, and it is transmitted to the IC card (S4). In the IC card, the received voice data is collated with the registered voice data (S5), and it is determined whether the authentication is successful or unsuccessful (S6 and S7). <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a personal authentication system, and more particularly to a system for authenticating an individual by voice.

In recent years, financial institutions have come to adopt biometric information such as fingerprints, voiceprints, and irises in order to increase the accuracy of personal authentication. Further, along with the spread of the Internet, authentication using biometric information is also performed in settlement of electronic commerce (for example, see Patent Document 1).
JP 2003-256787 A

  Among biometric information, voiceprints are particularly suitable for authentication when making electronic payments from a personal computer because the device is relatively inexpensive. However, when voiceprint information used for authentication is leaked, there is a problem that spoofing is easily performed.

  Therefore, an object of the present invention is to provide a voice authentication system in which it is difficult to perform fraud even when registration data registered for authentication leaks.

  In order to solve the above-described problem, in the first aspect of the present invention, data storage means for storing question information that is a question for a user and voice data that is answer content corresponding to the question in association with each other, and the data storage Display means for displaying the question information stored in the means, voice data acquisition means for recording and digitizing voice that is an answer to the displayed question information, the acquired voice data, and the displayed question A voice authentication system having voice data collating means for collating voice data corresponding to the above is provided.

  According to a second aspect of the present invention, in the voice authentication system according to the first aspect of the present invention, the data storage means stores a plurality of pieces of question information, and the display means displays the plurality of pieces of question information. The voice data collating means collates the voice data corresponding to the question selected by the user among the displayed questions.

  According to the first aspect of the present invention, the question information and the voice data that is the answer content are stored in association with each other, and the voice that is the answer to the displayed question information is recorded and digitized to obtain the voice data. Since the acquired voice data and the stored voice data are collated, it is difficult to perform fraud even if the registered data registered for authentication leaks. .

  According to the second aspect of the present invention, a plurality of pieces of question information are stored, a plurality of questions are displayed at the time of authentication, and collation with voice data corresponding to the question selected by the user is performed. Therefore, even if the registered voice data is leaked, if the selected question is different, it is difficult to impersonate and it is difficult to perform fraud.

DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.
(1. System configuration)
First, the configuration of the voice authentication system according to the present invention will be described. FIG. 1 is a functional block diagram of a voice authentication system according to the present invention. In FIG. 1, 10 is a data storage unit, 20 is a voice data collating unit, 30 is a display unit, and 40 is a voice data obtaining unit.

  The data storage means 10 is a storage area in the IC card 200 and stores question information and audio data. The voice data collating unit 20 has a function of collating the voice data acquired by the voice data acquiring unit 40 with the voice data stored in the data storage unit 10. The display unit 30 has a function of displaying information processed by the PC 100, and particularly has a function of displaying question information. The voice data acquisition unit 40 has a function of recording and digitizing voice from the outside, and plays a role of acquiring a response from the user to the displayed question as voice data.

  The PC 100 has a function of a general-purpose personal computer, and the display means 30 and the voice data acquisition means 40 are typical constituent elements. Therefore, the PC 100 can perform various processes other than the display unit 30 and the audio data acquisition unit 40 including the Internet connection function.

  Here, the IC card used in this embodiment will be described. FIG. 2 is a diagram showing a hardware structure of the IC chip 210 mounted on the IC card 200 of this embodiment. On the IC chip 210, a CPU 211, a ROM 212, a RAM 213 as a volatile memory, an EEPROM 214 as a rewritable memory, and an I / O circuit 215 for data communication with the PC 100 are connected to the BUS 216. Of these, the EEPROM 214 serves as the data storage means 10 and stores question information and voice data. A program for realizing the voice data collating unit 20 is installed in the ROM 212, and the CPU 211 reads and executes the program, thereby realizing the function as the voice data collating unit 20.

(2. Data registration to IC card)
First, the user registers data in the IC card 200. An example of data registered in the data storage processing means 10 in the IC card 200 is shown in FIG. As shown in FIG. 3, the data storage processing means 10 stores a question in the form of text data and an answer in the form of voice data corresponding thereto, and an ID is assigned to each combination of question and answer. ing.

  Data registration to the IC card 200 is performed by a dedicated data registration device. This data registration apparatus is obtained by connecting an IC card writer to a computer having a voice recording function, and a dedicated program for data registration is installed in the computer. Such a data registration apparatus is installed in a card issuing company, a financial institution, or the like, and data registration is performed when the card is issued.

  First, a question is created, and an answer to the question is answered by a user toward a microphone connected to the computer. Then, the user's voice is digitized in the computer and becomes voice data. Various types of audio data can be used. Since the audio data is for later use in collation, it is desirable that the audio data be in a format that can be collated at high speed. In the present embodiment, voice feature data is extracted from voice features. In other words, it is patterned voice feature data that is not actually reproducible. Since the voice feature data expresses the features of the voiceprint, it has a feature of being different for each individual. In addition, since the voice feature data in the present embodiment is not only a voice print, but also in the form of an answer to a question, the content of the answer varies depending on each individual.

  Although the number of questions can be set arbitrarily, in the present embodiment, the number is five. The user answers each of the five questions by voice and registers the voice feature data in the data storage processing means 10 in the IC card 200 in association with the question data.

(3. Processing operation)
Next, the processing operation of the system shown in FIG. 1 will be described using the flowchart of FIG. Here, a case where the user connects to the Internet from the home and performs electronic payment will be described as an example. When a user connects to an electronic payment site on the Internet, the electronic payment site requests authentication. In accordance with this request, the PC 100 activates the authentication program. Thereafter, the PC 100 performs an authentication process by the function of the authentication program.

  First, the PC 100 requests insertion of the IC card 200 (S1). When the user inserts the IC card 200 into the IC card reader, the PC 100 recognizes that the IC card 200 has been inserted. Then, the PC 100 acquires all IDs and questions from the data storage means 10 in the IC card 200 and displays them on the display means 30 (S2). As a result, five questions are displayed in a list format on the screen of the display means 30.

  The PC 100 displays the five questions in a list format and requests the user to select one of them. This may be selected by clicking with the mouse or the like among the five questions displayed on the screen. When the user clicks and selects a question, the PC 100 recognizes an ID corresponding to the selected question. Then, the PC 100 requests the user to answer the question (S3).

  The user answers an answer to the selected question toward the microphone connected to the PC 100. The PC 100 records the user's voice and digitizes it in the PC 100 to obtain voice data. This process is the same as that performed when registering data in the IC card 200. The format of the audio data must also be the same as that at the time of data registration. That is, in this embodiment, the voice feature data is processed into the extracted voice feature data. Then, the voice data and the ID recognized in S3 are associated with each other and transmitted to the IC card 200 (S4).

  When receiving the ID and voice data from the PC 100, the IC card 200 identifies information in the data storage means 10 with the received ID, extracts voice data registered in association with the same ID, and receives the received voice data. (S5). The collation is performed by a method corresponding to the format of the audio data. Various known methods can be used for collating voice data, including the case where voice feature data is employed. Note that the collation of voice data in the present invention is not a simple voiceprint collation, but a collation of the contents of words in addition to the voiceprint collation. That is, a double check of the voiceprint and the content of the word that is the answer is performed. This answer may differ depending on the person even if the question is the same, so if the person who registered the voice data does not answer, the answer often does not match the registered contents. Therefore, the user needs to answer while remembering his / her answer when registering data.

  The collation is basically performed according to the degree of matching regardless of the method used. As a result of the collation, if the difference between the two is less than a predetermined value, it is determined that the authentication is successful. On the other hand, if the difference between the two is greater than or equal to a predetermined value, it is determined that the authentication has failed. In any case, the IC card 200 transmits the authentication result to the PC 100.

  When the PC 100 receives the authentication result from the IC card 200, the PC 100 performs processing corresponding to the content. If the authentication is successful, the display means 30 is displayed on the display means 30 to notify that the authentication is successful (S6). And it sets to the state which can transmit the information to an electronic payment site. That is, the PC 100 itself shifts to a state where it can access the electronic payment site.

  On the other hand, if the authentication result received from the IC card 200 is an authentication failure, the PC 100 causes the display means 30 to display a content notifying that the authentication has failed (S7). Then, the transmission of information to the electronic settlement site is set to an impossible state. For example, a screen for accessing the Internet cannot be displayed.

  The preferred embodiments of the present invention have been described above, but the present invention is not limited to the above-described embodiments, and various modifications can be made. For example, in the above embodiment, the voice data matching unit 20 is provided in the IC card 200, but may be provided in the PC 100.

  Further, not only the voice data collating means 20 but also the data storage means 10 can be provided in the PC 100. In this case, similar to the processing in S3 and S4, the PC 100 acquires audio data and registers the audio data in the data storage means 10 such as a hard disk. In this case, the IC card 200 is unnecessary.

  Further, in the above-described embodiment, the description has been made on the assumption that the transaction is in a financial institution or the like and the settlement of electronic commerce, but the present invention can be used in all other Web accesses. For example, when performing simple login or personal authentication, authentication can be performed according to the present invention.

  As described above, according to the present invention, not only the voiceprint but also the contents of words are registered as voice data. Therefore, by changing the voice data, the authentication pattern can be changed infinitely.

It is a functional block diagram of the voice authentication system according to the present invention. It is a figure which shows the hardware structure of IC chip 210 mounted in IC card 200 of this embodiment. 4 is a diagram showing an example of data registered in data storage processing means 10 in the IC card 200. FIG. It is a flowchart which shows the processing operation of the voice authentication system which concerns on this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Data storage means 20 ... Audio | voice data collation means 30 ... Display means 40 ... Audio | voice data acquisition means 100 ... PC
200 ... IC card 210 ... IC chip 211 ... CPU
212 ... ROM
213 ... RAM
214 ... EEPROM
215 ... I / O
216 ... BUS

Claims (3)

Data storage means for associating and storing question information that is a question for the user and voice data that is the answer content corresponding to the question;
Display means for displaying the question information stored in the data storage means;
Voice data acquisition means for recording and digitizing voice that is an answer to the displayed question information;
Voice data collating means for collating the acquired voice data with voice data corresponding to the displayed question;
A voice authentication system comprising: The data storage means stores a plurality of pieces of question information,
The display means displays the plurality of pieces of question information;
2. The voice authentication system according to claim 1, wherein the voice data collating unit performs collation with voice data corresponding to a question selected by a user among the displayed questions. The data storage means and the voice collation means are mounted in an IC card,
3. The display device according to claim 1, wherein the display unit and the audio data acquisition unit are mounted in a computer connected to an IC card reader / writer that reads and writes the IC card. Voice authentication system.

Images