CLIAMS:WE CLAIM:
1. A processor-implemented method for detecting liveness of a user during biometric authentication, comprising:
identifying, via a detector, a speech signal of the user in a pre-determined time interval;
determining a speech respiration co-occurrence (SRC) score associated with the speech signal; and
detecting, via the detector, liveness of the user if the SRC score is above a predefined threshold.
2. The method of claim 1, further comprising:
collecting an ECG signal and a respiration signal along with the speech signal of the user.
3. The method of claim 2, further comprising:
determining a slope sequence s(t) which is the derivative of the respiration signal.
4. The method of claim 3, further comprising,
determining histogram of the slope sequence H(s) for the time internal.
5. The method of claim 4, further comprising:
SRC score = - sign(Smax + Smin)*max(H(s))/variance (H(s)), wherein sign () is the signum function of the input parameter, Smax and Smin are the maximum and minimum slope of the respiration signal.
6. The method of claim 1, further comprising:
detecting the ECG signal as a spoof signal, if the SRC score is less than the predefined threshold; and
rejecting the biometric authentication of the user.
7. The method of claim 1, further comprising:
identifying if the speech signal is generated during an exhale phase of respiration by the user.
8. The method of claim 1, further comprising:
initiating one or more biometric authentications if the liveness is detected.
9. A system for detecting liveness of a user during biometric authentication, comprising:
at least one processor in electronic communication with at least one traffic management device; and
a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to:
identify a speech signal of the user in a pre-determined time interval;
determine a speech respiration co-occurrence (SRC) score associated with the speech signal; and
detect liveness of the user, if the SRC score is above a predefined threshold.

10. The system of claim 9, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
collect an ECG signal and a respiration signal along with the speech signal of the user.
11. The system of claim 10, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
determine an slope sequence s(t) which is the derivative of the respiration signal.

12. The system of claim 11, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
determine histogram of the slope sequence H(s) for the time internal.
13. The system of claim 12, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
SRC score = - sign(Smax + Smin)*max(H(s))/variance (H(s)), wherein sign () is the signum function of the input parameter, Smax and Smin are the maximum and minimum slope of the respiration signal.
14. The system of claim 9, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
detect the ECG signal as a spoof signal, if the SRC score is less than the predefined threshold; and
reject the biometric authentication of the user.
15. The system of claim 9, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
identify if the speech signal is generated during an exhale phase of respiration by the user.
16. The system of claim 9, wherein the computer-readable medium storing instructions that, when executed by the at least one processor, further cause the at least one processor to:
initiate one or more biometric authentications if the liveness is detected.
17. A non-transitory computer readable medium including instructions stored thereon that when processed by a processor cause a first computing device to perform acts of:
identifying, via a detector, a speech signal of the user in a pre-determined time interval;
determining a speech respiration co-occurrence (SRC) score associated with the speech signal; and
detecting, via the detector, liveness of the user if the SRC score is above a predefined threshold.

Dated this 29th day of June, 2015

Swetha S.N
Of K&S Partners
Agent for the Applicant

,TagSPECI:TECHNICAL FIELD
This disclosure relates generally to biometric authentication. More specifically, it relates to a system and method for detecting liveness during biometric authentication.