Methods and apparatus for correlating biometric attributes and biometric attribute production features

• US 6,411,933 B1
• Filed: 11/22/1999
• Issued: 06/25/2002
• Est. Priority Date: 11/22/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Maes, Stephane Herman, Zweig, Geoffrey G.
• Primary Examiner(s): Banks-Harold, Marsha D.
• Assistant Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/444,684
• Time in Patent Office: 946 Days
• Field of Search: 704/270, 704/273, 704/275, 704/231, 704/246, 704/251
• US Class Current: 704/273
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A method of validating production of a biometric attribute allegedly associated with a user comprises the following steps. A first signal is generated representing data associated with the biometric attribute allegedly received in association with the user. A second signal is also generated representing data associated with at least one feature detected in association with the production of the biometric attribute allegedly received from the user. Then, the first signal and the second signal are compared to determine a correlation level between the biometric attribute and the production feature, wherein the validation of the production of the biometric attribute depends on the correlation level. Accordingly, the invention serves to provide substantial assurance that the biometric attribute offered by the user has been physically generated by the user.

Claims

1. A method of validating production of a biometric attribute allegedly associated with a user, the method comprising the steps of:

generating a first signal representing data associated with the biometric attribute allegedly received in association with the user;

generating a second signal representing data associated with at least one feature detected in association with the production of the biometric attribute allegedly received from the user; and

comparing the first signal and the second signal to determine a correlation level between the biometric attribute and the production feature, wherein validation of the production of the biometric attribute depends on the correlation level.

2. The method of claim 1, further comprising the step of validating the production of the biometric attribute when the correlation level is not less than a threshold value.

3. The method of claim 1, wherein the biometric attribute is a spoken utterance alleged to have been produced by the user.

4. The method of claim 3, wherein the production feature is a physiological effect attributable to the production of the spoken utterance alleged to have been produced by the user.

5. The method of claim 4, wherein the first signal is generated by an audio-based recognition system.

6. The method of claim 5, wherein the audio-based recognition system is a speech recognition system.

7. The method of claim 5, wherein the audio-based recognition system is a speaker recognition system.

8. The method of claim 4, wherein the second signal is generated by a speech production detecting system.

9. The method of claim 8, wherein the speech production detecting system is in physical contact with the user.

10. The method of claim 9, wherein speech production detecting system is a laryngograph device.

11. The method of claim 8, wherein the speech production detecting system is not in physical contact with the user.

12. The method of claim 11, wherein speech production detecting system is an electromagnetic wave-based detecting device.

13. The method of claim 12, wherein the electromagnetic wave-based detecting device is a radar-based device.

14. The method of claim 5, wherein the audio-based recognition system produces a sequence of time-aligned phones associated with the spoken utterance.

15. The method of claim 5, wherein the audio-based recognition system assigns a first data value to a voiced phone and a second data value to an unvoiced phone such that the first signal represents a time-aligned sequence of first and second data values.

16. The method of claim 8, wherein the speech production detecting system detects a time varying signal representing the physiological effect attributable to the production of the spoken utterance alleged to have been produced by the user.

17. The method of claim 16, wherein the physiological effect is a glottal excitation.

18. The method of claim 16, wherein the time varying signal is processed to generate a sequence of first and second data values representing a characteristic of the signal.

19. The method of claim 18, wherein a first data value represents a first relative energy level associated with the time varying signal and a second data value represents a second relative energy level associated with the time varying signal.

20. The method of claim 8, wherein the comparing operation comprises correlating the first signal and the second signal to determine a relative fraction of matches between an unvoiced phone in the first signal and a relative low energy level portion of the second signal and between a voiced phone in the first signal and a relative high energy level portion of the second signal.

21. The method of claim 20, wherein the relative fraction of matches represents the level of correlation.

22. The method of claim 1, wherein the correlation level determining step is based on at least one of:

a relative fraction of matches between the signals;

mutual information between the signals;

a measure of association between the signals; and

a comparison of periodicities associated with the signals.

23. The method of claim 1, wherein the first signal is generated by an audio-based recognition system which includes at least one of a ballistic labeler, a speech recognition engine, and a classifier.

24. Apparatus for validating production of a biometric attribute allegedly associated with a user, the apparatus comprising:

at least one processor operative to;

(i) generate a first signal representing data associated with the biometric attribute allegedly received in association with the user;

(ii) generate a second signal representing data associated with at least one feature detected in association with the production of the biometric attribute allegedly received from the user; and

(iii) compare the first signal and the second signal to determine a correlation level between the biometric attribute and the production feature, wherein validation of the production of the biometric attribute depends on the correlation level; and

memory, coupled to the at least one processor, for storing at least a portion of results associated with one or more operations performed in accordance with the at least one processor.

25. A system for validating production of a biometric attribute allegedly associated with a user, the system comprising:

a biometric recognition device which generates a first signal representing data associated with the biometric attribute allegedly received in association with the user;

a biometric production detecting device which generates a second signal representing data associated with at least one feature detected in association with the production of the biometric attribute allegedly received from the user; and

a processor, operatively coupled to the biometric recognition device and the biometric production detecting device, which compares the first signal and the second signal to determine a correlation level between the biometric attribute and the production feature, wherein validation of the production of the biometric attribute depends on the correlation level.

26. The system of claim 25, wherein the biometric recognition device is a speech recognition device.

27. The system of claim 26, further comprising a speaker recognition device, coupled to the processor, for providing validation of the user.

28. The system of claim 27, wherein the speaker recognition device performs biometric recognition.

29. The system of claim 25, wherein the biometric recognition device is a speaker recognition device.

30. The system of claim 25, wherein the biometric attribute is a spoken utterance alleged to have been produced by the user and the system is integrated with one or more speech-based processing systems.

31. The system of claim 30, wherein the speech-based processing system is a biometric system.