Individual verification apparatus

• US 4,653,097 A
• Filed: 05/23/1986
• Issued: 03/24/1987
• Est. Priority Date: 01/29/1982
• Status: Expired due to Fees

• Current Assignee: Tokyo Shibaura Denki Kabushiki Kaisha
• Original Assignee: Tokyo Shibaura Denki Kabushiki Kaisha
• Inventors: Watanabe, Sadakazu, Shinoda, Hidenori
• Primary Examiner(s): Kemeny, E. S. Matt
• Application Number:
  US06/870,309
• Time in Patent Office: 305 Days
• Field of Search: 381/41-43, 340/825.33, 340/825.34
• US Class Current: 704/272
• CPC Class Codes: G07C 9/33 by means of a password
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G07F 7/10 together with a coded signal , e.g. in the form of personal identification information, like personal identification number [PIN] or biometric data

Abstract

Speaker verification is tested in a sequence of steps: speech recognition of the spoken identification code (key code) is followed by speaker verification using the sounds of the spoken identification code. If verification fails, the speaker is urged by a speech synthesizer to utter his or her name for speaker verification.

Claims

1. An individual verification apparatus comprising:

a verification data file in which key codes set by customers, speech reference data file in which key codes set by customers, speech reference data for the key codes spoken by the customers and name speech reference data for names of the customers spoken by themselves are registered;

speech input means for providing speech data including key code data in response to an input speech from a customer;

memory means coupled to said speech input means for storing key code data spoken by the customer and provided by said speed input means;

key code recognition means coupled to said memory means for recognizing the key code of the customer on the basis of the key code data spoken by the customer and stored in said memory means through said speech input means; and

speaker verifying means coupled to said verification data file, said speech input means and said memory means for verifying the customer by comparing the key-code speech data stored in said memory means wth the key-code speech reference data of customers hvaing the key code recognized by said speech recognition means and previously registered in said verification data file, said speaker verifying means being arranged to, when the key code of the customer is recognized by said speech recognition means but the customer cannot be verified by the key-code speech data, verify the customer by comparing name speech data spoken by the customer and stored in said memory means through said speech input means with the name speech reference data of the customers having the key code which has been recognized by said speech recognition means and previously registered in said verification data file.

2. An apparatus according to claim 1 further comprising:

speech responding means coupled to said speech recognition means and said speaker verfification means for audibly indicating to the customer the key code recognized by said speech recognition means and a result of the speaker verification performed by said speaker verification means.

3. In an individual verification apparatus comprising a verification data file;

a speech input section;

a data memory;

a speech recognition unit;

a speaker verification unit; and

a speech response section, a method for verifying a speaker comprising the steps of;

storing input speech data of the key code spoke by a speaker into said data memory through said speech input section;

recognizing the key code of the speaker by said speech recognition unit on the basis of the input speech data of the key code stored in said data memory;

verifying the speaker by said speaker verification unit, after the key code of the speaker has been recognized by comparing the key code speech data of the speaker stored in said data memory with key code reference speech data of customers, having the same key code which has been recognized by said speech recognition unit, previously registered in said verification data file;

urging, when the speaker cannot be verified on the basis of the key code speech data, the speaker to state his or her name by said speech response section;

storing, when the key code of the speaker is recognized by said speech recognition unit (40) but the speaker cannot be verified by said speaker verification unit on the basis of the key-code speech data, the name speech data spoken by the speaker into said data memory through said speech input section; and

verifying the speaker by said speaker verification unit by comparing the name speech data stored in said data memory with name speech reference data of customers previously registered in said verification data file.

4. An individual verification apparatus comprising:

a verification data file in which identification codes set by customers, speech reference data for the identification codes uttered by the customers and name speech reference data for names of the customers spoken by themselves are registered;

speech input means for providing speech data including identification code data in response to an input speech from a customer;

memory means coupled to said speech input means for storing identification code data uttered by the customer and provided by said speech input means;

identification code recognition means coupled to said memory means for recognizing the identification code of the customer on the basis of the identification code data uttered by the customer and stored in said memory means through said speech input means; and

speaker verifying means coupled to said verification data file, said speech input means and said memory means for verifying the customer by comparing the identification speech data stored in said memory means with the identification code speech reference data of customers having the identification code recognized by said speech recognition means and previously registered in said verification data file, said speaker verifying means being arranged to, when the identification code of the customer is recognized by said speech recognition means but the customer cannot be verified by the identification code speech data, verify the customer by comparing name speech data spoken by the customer and stored in said memory means through said speech input means with the name speech reference data of the customers having the identification code which has been recognized by said speech recognition means and previously registered in said verification data file.

5. An apparatus according to claim 4 further comprising

speech responding means coupled to said speech recognition means and said speaker verification means for audibly indicating to the customer the identification code recognized by said speech recognition means and a result of the speaker verification performed by said speaker verification means.

6. In an individual apparatus comprising a verification data file;

a speech input section;

a data memory;

a speech recognition unit;

a speaker verification unit; and

a speech response section, a method for verifying a speaker comprising the steps of;

storing input speech data of the identification code spoken by a speaker into said data memory through said speech input section;

recognizing the identification code of the speaker by said speech recognition unit on the basis of the inputted speech data of the identification code stored in said data memory;

verifying the speaker by said speaker verification unit, after the key code of the speaker has been recognized by comparing the identification code speech data of the speaker stored in said data memory with identification code reference speech data of customers, having the same identification code which has been recognized by said speech recognition unit, previously registered in said verification data file;

urging, when the speaker cannot be verified on the basis of the key code speech data, the speaker to state his or her name by said speech response section;

storing, when the identification code of the speaker is recognized by said speech recognition unit but the speaker cannot be verified by said speaker verification unit on the basis of the identification code speech data, the name speech data spoken by the speaker into said data memory through said speech input section; and

verifying the speaker by said speaker verification unit by comparing the name speech data stored in said data memory with name speech reference data of customers previously registered in said verification data file.