WO2014013513A1

WO2014013513A1 - Method and system for verifying identity of a person

Info

Publication number: WO2014013513A1
Application number: PCT/IN2013/000449
Authority: WO
Inventors: Himanshu Aggarwal; Varun Aggarwal
Original assignee: Himanshu Aggarwal
Priority date: 2012-07-20
Filing date: 2013-07-19
Publication date: 2014-01-23

Abstract

A method and system for verifying the identity of person using the voice of person have been provided. The system includes a recording unit, a memory device, a comparison unit and an output unit. The voice samples of the person appearing for an evaluation test of a selection process are recorded at the two separate instances and then compared using the comparison unit to check the identity of the person. The result of the comparison unit is then displayed on the output unit. A method of using the person verification system has also been disclosed.

Description

METHOD AND SYSTEM FOR VERIFYING IDENTITY OF A PERSON BACKGROUND Field of the invention

The present invention relates to a method and a system for verifying the identity of a person. More particularly, the present invention relates to the method and system for verifying the identity of the person in a process using voice recognition.

Description of the related art

The selection of a right candidate for a particular job or selection of a right person for a university/organization is always given as high importance. The selection involves multiple rounds of test/interviews. Sometimes, it is not always feasible for the candidate/person to physically present for the interview, test or the selection process. With the evolvement of the technology, a telephone based interviews, assessments (telephone based and otherwise) in remote locations and selection process have become common these days. The telephone based method has been used by organizatioris/colleges/universities frequently for hiring the right candidates. In addition to above scenario, there are various organizations/universities, outsource the hiring of their right candidate/person, preferably, for initial level shortlisting of the candidates. The general process includes, the outsourcing agency conducts the multiple level of examination of the person based on the requirement of the organization. They shortlist the candidates and send them to organizations/universities for further rounds of interviews/selection process. In yet another scenario, an assessment test is taken remotely for the evaluation for a course. This includes telephone-based tests taken at homes or computer based tests taken remotely for MOOCs (massively online Open Courseware)

Few cases have been observed in the past, when the person who gave the interview over the telephone or taken the test at a remote location is different from the person who appeared for physical selection process or who was actually, designated to take the test. The organization also wants to make sure that the person who has been shortlisted by the outsourcing agency is the same person who appeared for the selection process. Thus a need exists to remotely check the;- identity of the person over a communications network. It needs to be checked that the same person who has appeared for the telephonic interview or test is finally joining the organization.

Few methods and systems have been used , in the past to check the identity of the person. For example, many user identification systems comprise simple password systems, where the user provides a password, or keypunches in a multi-character alphanumeric code to obtain access to the system. In another example, photo based verifying techniques have also been used, but they are not reliable. While various other techniques have been used in the past, there is still room for the development and innovation. Thus a need persists for the further contributions in this field of the technology.

SUMMARY An object of the present invention is to provide a system and method for verifying the identity of a person based on a speaker recognition system

Another object of the present invention is to provide a system and method to compare and assess the voice samples of the person recorded at separate instances of a process.

Embodiments of the invention provide a system for verifying the identity of a person. The system includes a recording unit for recording a first sample of voice of the person at a first instance, a memory unit for storing the voice recorded at the first instance, a comparison unit and an output unit. The first instance is an instance at which the person appears for an evaluation test in a process for the first time. The comparison unit compares a second sample of voice recorded at a second instance with the first sample of voice recorded at the first instance to provide a result on the output unit.

BRIEF DESCRIPTION OF DRAWINGS The features of the present invention, which are believed to be novel, are set forth with particularity in the appended claims. Embodiments of the present invention will hereinafter be described in conjunction with the appended drawings provided to illustrate and not to limit the scope of the claims, wherein like designations denote like elements, and in which:

Fig. 1 shows a block diagram of a system for verifying the identity of a person, in accordance with various embodiments of the present invention; and Fig. 2 is a flowchart showing the steps involved in verifying the identity of the person using the system described in Fig. 1 in accordance with various embodiments of the present invention. DETAILED DESCRIPTION OF EMBODIMENTS

As used in the specification and claims, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise. For example, the term "an article" may include a plurality of articles unless the context clearly dictates otherwise.

There may be additional components described in the foregoing application that are not depicted on one of the described drawings. In the event such a component is described, but not depicted in a drawing, the absence of such a drawing should not be considered as an omission of such design from the specification.

As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which can be embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention in virtually any appropriately detailed structure. Further, the terms and phrases used herein are not intended to be limiting but rather to provide an understandable description of the invention.

A block diagram of a system 10 for verifying the identity of a person is shown in Fig. 1 , in accordance with various embodiments of the present invention. The system 0 is configured to verify the identity of the person if an interview, a selection process or a test requires the involvement of the person more than once. The system 10 is also configured to verify that the same person is joining the organization/university who has gone through the selection process. The person appearing for the process may be a student taking a test from a remote location, a candidate for job application, a student for entry in the institute/university or any other person which needs to be verified for any process.

The system 10 includes a recording unit 12, a memory unit 14, a comparison unit16 and an output unit 18as shown in Fig. 1 . It should be appreciated that the system 10 is not limited only to the components which are described herein. The system 10 may include more or less components in various other embodiments of the present invention. The recording unit 12 is configured to record a first voice sample of the person appearing for an evaluation test of a selection process. The first instance is defined as an instance at which the person is appeared for the evaluation test for the first time. At the first instance, the person is asked to provide one or more voice samples.

The input of the voice sample is provided through at least one of a microphone, a landline telephone, a mobile phone or any other similar communication devices. The voice samples may be recorded at regular intervals or recorded continuously.

The voice samples in each instance can be recorded by at least one or combination of the following means: reading a given text provided to the person and speaking it; listening the speech by an evaluator and repeating it by the person; speaking anything by the person as per his/her wish; speaking on a particular topic given by the evaluator; or any other topic chosen by the person himself/herself or voice samples captured during an evaluation test.

At the first instance, the person is asked to go through the evaluation test. The evaluation test at the first instance is at least one of the following: a computer based test, a paper-pencil based subjective test, a multiple choice based test, a simulation based test, an interview, a simulation, a voice based test activated from a computer, and an IVR based test or a mix of above mentioned tests. The evaluation test can be performed either before the recording of the first sample of voice at the first instance, after the recording of the first sample of voice at the first instance or simultaneously with the recording of the first sample of voice at the first instance. The first sample of voice recorded at the first instance is stored in the memory unit 14. A particular reference number is given corresponding to the particular person appearing for the selection process. The reference number is used for future reference for the person. A database is created inside the memory unit 14 of the system. The database contains the voice samples of everyone who has appeared for the selection process.

The recording unit 12 is also used to record a second sample of voice of the person at a second instance. It should be appreciated that a separate recording unit may also be used at the second instance in an embodiment of the disclosure. The second instance is an instance at which the person reappears for the selection process. In an example, the second instance is defined as the person appears for 2^nd or 3^rd or further evaluations as a part of the selection process. In another example, the second instance is referred as the person is going to join an organization/university after successfully qualifying the evaluation test taken by an outsourcing agency. The evaluation test was conducted by the outsourcing agency at the first instance.

The comparison unit 16 receives input from the memory unit 14 and the recording unit 12. The comparison unit 16 is configured to compare the second sample of voice recorded at the second instance with the first sample of voice stored in the memory unit 14. The output of the comparison unit 16 is given to the output unit 18. In an embodiment of the disclosure, the output unit 18 is provided as at least one of a display device 20, a visual indicator 22, an IVR based indicator (automated or manual call), through an SMS, through an -MIS on the internet or an audio alarm 24. The output unit 8 indicates the Result of comparison performed by the comparison unit 16. The visual indicator 22 may include lights of various colour representing different outputs.

The output unit 18indicat.es 'YES' if the voice sample recorded at the second instance matches with the voice sample recorded at the first instance. The output unit 18indicat.es 'NO', if the voice sample recorded at the second instance does not match with the voice sample recorded at the first instance. The output unit 18 indicates 'MORE SAMPLE NEEDED if the comparison unit 16is not able to compare the voice samples recorded at the first instance and the second instance. In any other possibilities, the output unit 18 can also indicate 'CAN'T SAY'. In the visual indicator 22, colour codes are defined to indicate 'YES', 'NO', 'MORE SAMPLE NEEDED' and 'CAN'T SAY, for example, Green for 'YES', Red for 'NO' etc. In case the voice samples are not matched by the comparison unit 16, the person may also be asked again to record the voice samples and match. The output unit 18can also provide a subjective or objective confidence measure on the correctness of the output at the second instance. The same person may be verified more than once after the first instance.

The matching of voice samples recorded at the first instance and the second instance can be performed automatically or manually or by both means. The comparison unit 16uses an algorithm for matching the voice samples recorded at the instances. The algorithm is based on one or more of the following: speech processing, speech analysis, speech recognition, speaker recognition and identification, crowdsourcing, machine learning or pattern recognition. It should be appreciated ¾that .any other matching technique can also be used for matching the voice samples.

In another embodiment of the invention, the system 10 is also used for verifying the identity of a student giving test/examination from a remote ¹ location. In this case, the student is asked to take the test at home on at phone/computer at the first instance. The student is asked to record the first sample of voice at home. The first sample of voice is saved in the memory unit 14. At the later stage i.e. at the second instance, when the student is present in the school, teacher can ask the student to record the-^' second sample of voice of the student. The comparison unit 16 matched the first sample of voice and the second sample of voice of the student to. verify that the student who was assigned for the test took it.

Fig. 2 shows a flow chart 100 indicating the steps involved for verifying identity of the person using the system 10, in accordance with various embodiment of the invention. At step 102, a first sample of voice of the person is recorded at a first instance using the recording unit 12. At step 104, the person is appeared for the evaluation test for a selection process for the first time. It should be appreciated that the step 102 and 104 can be performed in any order. It should also be appreciated that the step 102 and 104 can also be performed simultaneously. At step 106, the first sample of voice recorded at step 102 are saved in a memory unit 14. The step 106 can be performed automatically or manually or by mix of both automatically and manually by an evaluator. At step 108, the second sample of voice of the person is recorded at a second instance. The second instance is an instance at which the person reappears for the selection process. At step 1 0, the first sample of voice recorded at the first instance is compared with the second sample of voice recorded at the second instance by the comparison unit 16. And finally at step 1 12, the results of the comparison unit 16 are indicated at the output unit 18.

In an embodiment of the invention, the algorithm may also use other information, biometric or otherwise, about the person or the two instances to establish a match between more than two appearances of a person. In an illustrative embodiment of the ^invention, the person takes an interactive voice response (IVR) based evaluation test of spoken English at the first instance. The IVR based test is conducted by dialing in a phone number using a landline or mobile phone. The voice sample is recorded from the person's speech during th evaluation test. At the second instance, the person comes for further evaluation process for a job or educational institution admission, either by being shortlisted through the scores of the first test or otherwise. The person, at the second instance, again calls a number and provides a voice sample. Both the voice samples from the first instance and the second instance are matched automatically and the match or deviance output is provided by one or more of the following: phone, computer database, otherwise.

In another illustrative embodiment of the invention, the person takes computer based test, which may or may not be a speech based test, in the first instance. The person provides a voice sample by speaking in a microphone or over a phone call by dialing a number just before, just after or during the test. At the second instance, the person comes for further evaluation process for a job or educational institution admission, either by being shortlisted through the scores of the first test or otherwise. The person, at the second instance, again calls a number and provides a voice sample. Both the voice samples are matched automatically and the match or deviance output is provided by one or more of the following: phone, computer database, otherwise.

The present invention has been described herein with reference to a particular embodiment for a particular application. Although selected embodiments have been illustrated and described in detail, it may be understood that various substitutions and alterations are possible. Those having ordinary skill in the art and access to the present teachings may recognize additional various substitutions and alterations are also possible without departing from the spirit and scope of the present invention, and as defined by the following claims.

Claims

WHAT IS CLAIMED IS:

A system for verifying identity of a person, the system comprising:

a recording unit for recording a first sample of voice of the person at a first instance, wherein the first instance is an instance at which the person appears for an evaluation test for the first time in a process; a memory unit for storing the first sample of voice recorded at the first instance;

a comparison unit configured to compare a second sample of voice of the person recorded at a second instance with the first sample of voice, wherein the second instance is an instance at which the person reappears in the process; and

an output unit for indicating a result of the comparison performed by the comparison unit.

The system of claim 1 , wherein the process is at least one of a recruitment process of a candidate appearing for a job, a university admission process, and taking an examination by a student from a remote location.

The system of claim 1 , wherein the evaluation test is one of a computer based test, a tablet based test, a paper-pencil based subjective or multiple choice based test, a simulation based test, an interview, a simulation, a voice based test activated from a computer, an IVR based test and a mix of these.

The system of claim 1 , wherein the first sample of voice at the first instance and second sample of voice at the second instance are captured by at least one of reading a given text and speaking, listening to a speech and repeating, speaking anything that the person wishes, speaking on a given topic or voice samples captured during the evaluation process conversation.

5. The system of claim 1 , wherein the first recording unit is at least one of a microphone, mobile phone, and a landline telephone.

6. The system of claim 1 , wherein the first sample of voice at the first instance and second sample of voice at the second instance are captured by at least one of reading a given text and speaking, listening to a speech and repeating, speaking anything that the person wishes, speaking on a given topic or voice samples captured during the evaluation process conversation.

7. The system of claim 1 , wherein the result is at least one of a Yes, 'No, Cannot say or More sample needed!

8. The system of claim 1 , wherein the result is indicative of the confidence measure of the person at the second, instance. 9. A method for verifying identity of a |erson, the method comprising: recording a first sample of voice of the person at a first instance using a recording unit, wherein the first instance is an instance at which the person appears for an evaluation test of a selection process for the first time;

saving the first sample of voice recorded at the first instance in a memory unit;

recording a second sample of voice of the person at a second instance, wherein the second instance is an instance at which the person reappears for the selection process; comparing the first sample of voice recorded at the first instance and the second sample of voice recorded at the second instance using a comparison unit; and

indicating a result of the comparison performed by the comparison unit on an output unit.

10. A system for verifying identity of a student taking an examination from a remote location, the system comprising:

a recording unit for recording a first sample of voice of the student at a first instance, wherein the first instance is an instance at which the student appears for the examination at the remote location;

a memory unit for storing the first sample of voice recorded at the first instance;

a comparison unit configured to compare a second sample of voice of the student recorded at a second instance with the first sample of voice, wherein the second instance is an instance at which the student is present in a school, college or training institution; and