Quantifying psychological stress levels using voice patterns

• US 7,571,101 B2
• Filed: 05/25/2006
• Issued: 08/04/2009
• Est. Priority Date: 05/25/2006
• Status: Active Grant

• Current Assignee: Charles Humble
• Original Assignee: Charles Humble
• Inventors: Humble, Charles
• Primary Examiner(s): Opsasnick; Michael N
• Application Number:
  US11/441,419
• Publication Number:
  US 20070276669A1
• Time in Patent Office: 1,167 Days
• Field of Search: 704/270, 704/273
• US Class Current: 704/273
• 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 and method of assigning a numeric score to a voice pattern of a human subject wherein the score is indicative of the psychological stress level of the human subject. A verbal utterance of a human subject is converted into electrical signals to provide a subject wave pattern. The pattern is quantified and compared with known voice pattern characteristics which exhibit a sequential progression in the degree of blocking in the pattern, wherein each of the known voice patterns is assigned a numerical value range. A numerical value obtained from calculations is assigned to the subject wave pattern based on the comparison. The numerical value represents the degree of blocking present in the subject wave pattern which correlates to the amount of psychological stress exhibited by the human subject.

Claims

1. A system for assigning a numeric score to a sample of a voice pattern of a human subject wherein the score is indicative of the psychological stress level of the human subject comprising:

means to convert a verbal utterance of a human subject into electrical signals which are plotted on a Cartesian coordinate system whereby a subject wave pattern having x and y axes are provided;

means for filtering said subject wave pattern to remove extraneous values at the leading and trailing edges of said subject wave pattern whereby a working frame is provided for analysis;

means to provide a consecutive series of known voice pattern characteristics, wherein said consecutive series exhibits a sequential progression in the degree of blocking in said subject wave pattern;

means for assigning a numerical value range to each of the consecutive series of known voice pattern characteristics based on the degree of blocking in said subject wave pattern;

means for analyzing said subject wave pattern within said working frame to provide quantified data which define a set of characteristics for said subject wave pattern;

means for providing quantified data which define a set of characteristics for said consecutive series of known voice pattern characteristics;

means for comparing said quantified data of said subject wave pattern within said working frame to said quantified data for each of said known voice pattern characteristics to ascertain a match between said subject wave pattern and one or more of said known voice pattern characteristics; and

means for generating a score for said subject wave pattern based on said one or more matching known voice pattern characteristics.

2. The system of claim 1, further including means for applying a value averaging algorithm to the component of said subject wave pattern to filter said subject wave pattern.

3. The system of claim 1, further comprising means for measuring said subject wave pattern to determine if said subject wave pattern conforms to required characteristics for optimal analysis.

4. The system of claim 1, wherein said quantified data for said subject wave pattern and said known voice pattern characteristics includes the wave frequency.

5. The system of claim 1, wherein said quantified data for said subject wave pattern and said known voice pattern characteristics include the wave amplitude.

6. The system of claim 1, wherein said quantified data for said subject wave pattern and said known voice pattern characteristics include the number of cycles in said working frame of said subject wave pattern.

7. The system of claim 1, wherein said means for analyzing said subject wave pattern further includes means for forming a maximum point array based on the peak of each cycle in said subject wave pattern.

8. The system of claim 1, wherein said means for analyzing said subject wave pattern further includes means for forming a minimum point array based on the base of each cycle in said subject wave pattern.

9. The system of claim 1, wherein said means for analyzing said subject wave pattern further includes means for forming a midpoint array based on the midpoint between each maximum point and each minimum point in said subject wave pattern.