SYSTEM, METHOD AND ARTICLE OF MANUFACTURE FOR A VOICE ANALYSIS SYSTEM THAT DETECTS NERVOUSNESS FOR PREVENTING FRAUD

• US 20020010587A1
• Filed: 08/31/1999
• Published: 01/24/2002
• Est. Priority Date: 08/31/1999
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture LLP (Accenture PLC)
• Inventors: PERTRUSHIN, VALERY A.
• Granted Patent: US 6,427,137 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A system, method and article of manufacture are provided for detecting nervousness in a voice in a business environment to help prevent fraud. First, voice signals are received from a person during a business event. The voice signals are analyzed during the business event to determine a level of nervousness of the person, which is then output before the business event is completed. A degree of certainty as to the level of nervousness of the person may be output to assist one searching for fraud in making a determination as to whether the person was speaking fraudulently. Optionally, the level of nervousness of the person may be output in real time. As another option, an alarm may be set off when the level of nervousness goes above a predetermined level.

Claims

1. A method for detecting nervousness in a voice in a business environment, comprising the steps of:

(a) receiving voice signals from a person during a business event;

(b) analyzing the voice signals for determining a level of nervousness of the person during the business event; and

(c) outputting an indication of the level of nervousness of the person prior to completion of the business event.

2. A method as recited in claim 1, further comprising outputting a degree of certainty as to the level of nervousness of the person.

3. A method as recited in claim 1, wherein outputting the indication of the level of nervousness of the person occurs in real time.

4. A method as recited in claim 1, further comprising setting off an alarm when the level of nervousness goes above a predetermined level.

5. A method as recited in claim 1, further comprising recording the voice signals of the person.

6. A method as recited in claim 1, further comprising extracting at least one feature of the voice signals selected from the group of features consisting of a maximum value of a fundamental frequency, a standard deviation of the fundamental frequency, a range of the fundamental frequency, a mean of the fundamental frequency, a mean of a bandwidth of a first formant, a mean of a bandwidth of a second formant, a standard deviation of energy, a speaking rate, a slope of the fundamental frequency, a maximum value of the first formant, a maximum value of the energy, a range of the energy, a range of the second formant, and a range of the first formant, wherein the level of nervousness of the person is determined based on the extracted feature of the voice signals.

7. A computer program embodied on a computer readable medium for detecting nervousness in a voice in a business environment, comprising:

(a) a code segment that receives voice signals from a person during a business event;

(b) a code segment that analyzes the voice signals for determining a level of nervousness of the person during the business event; and

(c) a code segment that outputs an indication of the level of nervousness of the person prior to completion of the business event.

8. A computer program as recited in claim 7, further comprising a code segment that outputs a degree of certainty as to the level of nervousness of the person.

9. A computer program as recited in claim 7, wherein outputting the indication of the level of nervousness of the person occurs in real time.

10. A computer program as recited in claim 7, further comprising a code segment that sets off an alarm when the level of nervousness goes above a predetermined level.

11. A computer program as recited in claim 7, further comprising a code segment that records the voice signals of the person.

12. A computer program as recited in claim 7, further comprising a code segment that extracts at least one feature of the voice signals selected from the group of features consisting of a maximum value of a fundamental frequency, a standard deviation of the fundamental frequency, a range of the fundamental frequency, a mean of the fundamental frequency, a mean of a bandwidth of a first formant, a mean of a bandwidth of a second formant, a standard deviation of energy, a speaking rate, a slope of the fundamental frequency, a maximum value of the first formant, a maximum value of the energy, a range of the energy, a range of the second formant, and a range of the first formant, wherein the level of nervousness of the person is determined based on the extracted feature of the voice signals.

13. A system for detecting nervousness in a voice in a business environment, comprising:

(a) logic that receives voice signals from a person during a business event;

(b) logic that analyzes the voice signals for determining a level of nervousness of the person during the business event; and

(c) logic that outputs an indication of the level of nervousness of the person prior to completion of the business event.

14. A system as recited in claim 13, further comprising logic that outputs a degree of certainty as to the level of nervousness of the person.

15. A system as recited in claim 13, wherein outputting the indication of the level of nervousness of the person occurs in real time.

16. A system as recited in claim 13, further comprising logic that sets off an alarm when the level of nervousness goes above a predetermined level.

17. A system as recited in claim 13, further comprising logic that records the voice signals of the person.

18. A system as recited in claim 13, further comprising logic that extracts at least one feature of the voice signals selected from the group of features consisting of a maximum value of a fundamental frequency, a standard deviation of the fundamental frequency, a range of the fundamental frequency, a mean of the fundamental frequency, a mean of a bandwidth of a first formant, a mean of a bandwidth of a second formant, a standard deviation of energy, a speaking rate, a slope of the fundamental frequency, a maximum value of the first formant, a maximum value of the energy, a range of the energy, a range of the second formant, and a range of the first formant, wherein the level of nervousness of the person is determined based on the extracted feature of the voice signals.