METHOD FOR JUDGMENT OF DRINKING USING DIFERENTIAL REQUENCY ENERGY, RECORDING MEDIUM AND DEVICE FOR PERFORMING THE METHOD

• US 20170181695A1
• Filed: 04/02/2014
• Published: 06/29/2017
• Est. Priority Date: 03/28/2014
• Status: Active Grant

• Current Assignee: Foundation of Soongsil University-Industry Cooperation
• Original Assignee: Foundation of Soongsil University-Industry Cooperation
• Inventors: BAE, Myung Jin, LEE, Sang Gil, BAE, Seong Geon
• Granted Patent: US 9,907,509 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/4845 Toxicology, e.g. by detection of alcohol, drug or toxic products A61B5/4848 takes precedence
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: B60K 28/06 responsive to incapacity of driver
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 25/21 the extracted parameters being power information
• CPC Class Codes: G10L 25/30 using neural networks
• CPC Class Codes: G10L 25/66 for extracting parameters related to health condition detecting or measuring for diagnostic purposes A61B5/00

Abstract

An alcohol consumption determination method includes: detecting an effective frame of an input voice signal; detecting a difference signal of an original signal of the effective frame; performing fast Fourier conversion on the original signal and the difference signal; and determining, in the frequency domain, whether alcohol has been consumed based on a slope difference between the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal. Accordingly, it is also possible to determine whether a driver or an operator from a remote location has consumed alcohol and a degree of the consumption, thus preventing an accident caused by an individual operating a vehicle under the influence.

Claims

1-13. -13. (canceled)

14. A method for determining whether a person is drunk comprising:

forming an effective frame of an input voice signal from said person;

generating an original signal of the formed effective frame and a difference signal of the original signal;

performing a fast Fourier transform algorithm on the original signal and the difference signal; and

determining whether said person is drunk based on an energy difference in the frequency domain between the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal.

15. The method of claim 14, wherein the forming an effective frame of an input voice signal from said person comprises:

forming a voice frame of an input voice signal from said person; and

determining whether the formed voice frame corresponds to a voiced sound.

16. The method of claim 15, wherein the determining whether the formed voice frame corresponds to a voiced sound comprises:

extracting periodic characteristics of harmonics or features from the formed voice frame, and

determining whether the formed voice frame is from a voiced sound, an unvoiced sound, or background noise based on the extracted periodic characteristics of harmonics or features.

17. The method of claim 16, wherein periodic characteristics of harmonics or features comprise root mean square energy (RMSE) or zero-crossing count (ZC) of a low-band voice signal energy area.

18. The method of claim 16, wherein the determining whether the formed voice frame is from a voiced sound, an unvoiced sound, or background noise based on the extracted periodic characteristics of harmonics or features comprises use of neural network.

19. The method of claim 14, wherein the generating an original signal of the formed effective frame and a difference signal of the original signal comprises:

generating an original signal S(n) of the formed effective frame;

generating a shift signal S(n−

1) by shifting the original signal S(n); and

generating a difference signal S(n)−

S(n−

1) between the original signal S(n) and the shift signal S(n−

1).

20. The method of claim 19, wherein the difference signal S(n)−

S(n−

1) comprises a characteristic of highlighting high-frequency components.

21. The method of claim 14, wherein the performing a fast Fourier transform algorithm on the original signal and the difference signal comprises:

performing a fast Fourier transform algorithm on the original signal; and

performing a fast Fourier transform algorithm on the difference signal.

22. The method of claim 14, wherein the determining whether said person is drunk based on an energy difference in the frequency domain between the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal comprises:

generating frequency slopes of the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal;

measuring a difference between the slopes to measure an energy difference between the original signal and the difference signal; and

determining that said person is drunk when the energy difference is greater than a threshold and outputting a result of the determination.

23. The method of claim 22, wherein each of the frequency slopes of the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal is a formant slope.

24. A computer-readable recording medium having a computer program recorded thereon for performing the method of claim 14 of determining whether a person is drunk.

25. A device for determining whether a person is drunk comprising:

an effective frame detection unit configured to detect an effective frame of an input voice signal from said person;

a difference signal detection unit configured to detect a difference signal of an original signal of the effective frame;

a Fourier transform unit configured to perform a fast Fourier transform algorithm on the original signal and the difference signal; and

an alcohol consumption determination unit configured to determine whether said person is drunk based on an energy difference in the frequency domain between the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal.

26. The device of claim 25, wherein the effective frame detection unit comprises:

a frame forming unit configured to form a voice frame of the input voice signal; and

a voiced sound determination unit configured to determine whether the voice frame corresponds to a voiced sound.

27. The device of claim 25, wherein the difference signal detection unit comprises:

a shift signal unit configured to generate a shift signal S(n−

1) by shifting the original signal S(n) of the effective frame; and

a difference signal output unit configured to output a difference signal S(n)−

S(n−

1) between the original signal and the shift signal.

28. The device of claim 25, wherein the Fourier transform unit comprises:

a first Fourier transform unit configured to perform a fast Fourier transform algorithm on the original signal; and

a second Fourier transform unit configured to perform a fast Fourier transform algorithm on the difference signal.

29. The device of claim 25, wherein the Fourier transform unit comprises:

a Fourier transform unit configured to perform a fast Fourier transform algorithm on the original signal and on the difference signal at the same time, in any order, or in sequence.

30. The device of claim 25, wherein the alcohol consumption determination unit comprises:

a slope extraction unit configured to generate frequency slopes of the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal;

an energy comparison unit configured to measure a difference between the slopes to measure an energy difference between the original signal and the difference signal; and

a result output unit configured to determine that said person is drunk when the energy difference is greater than a threshold and output a result of the determination.

31. The device of claim 30, wherein each of the frequency slopes of the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal is a formant slope.

32. The device of claim 30, wherein the alcohol consumption determination device utilizes a formant energy comparison method.

33. A portable device comprising the device of claim 25 for determining whether a person is drunk.