Detection of conditions from sound

• US 9,223,863 B2
• Filed: 12/05/2012
• Issued: 12/29/2015
• Est. Priority Date: 12/20/2007
• Status: Active Grant

• Current Assignee: Dean Enterprises, LLC
• Original Assignee: Dean Enterprises, LLC
• Inventors: Dean, Vickie A.
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Sirjani, Fariba
• Application Number:
  US13/705,416
• Publication Number:
  US 20130096844A1
• Time in Patent Office: 1,119 Days
• Field of Search: 704/243
• US Class Current: 1/1
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

Disclosed are various systems, methods, and programs embodied in a computer-readable medium for sound analysis. The sound analysis involves transforming a sound print into a frequency domain in a memory to generate a frequency spectrum. A plurality of signatures are identified in the frequency spectrum. Also, a plurality of frequency ranges associated with the signatures are identified in the sound print. The frequencies associated with a physiological profile are cross-referenced with the frequency ranges to determine if the physiological profile is applicable to the sound print.

Claims

1. A method for sound analysis, comprising the steps of:

transforming, in a computing device, a sound print into a frequency domain in a memory to generate a frequency spectrum;

identifying, in the computing device, a plurality of signatures in the frequency spectrum, wherein the signatures each comprise a maximum amplitude shift that is less than a predefined threshold over a predefined frequency band;

identifying, in the computing device, a plurality of frequency ranges associated with the signatures in the sound print; and

cross referencing, in the computing device, a plurality of frequencies associated with a profile with the frequency ranges to determine if the profile is applicable to the sound print.

2. The method of claim 1, wherein the step of transforming, in the computing device, the sound print into the frequency domain in the memory to generate the frequency spectrum further comprises the step of:

processing the sound print through a Frequency Transform.

3. The method of claim 1, wherein the step of identifying, in the computing device, the plurality of signatures further comprises the step of:

identifying, in the computing device, the signatures in the sound print by analyzing the sound print over a plurality of octaves.

4. The method of claim 1, wherein the signatures are substantial zero slopes.

5. The method of claim 1, further comprising:

generating, in the computing device, a prioritized list of the frequency ranges wherein the prioritized list of frequency ranges is prioritized by a magnitude of each of the frequency ranges.

6. The method of claim 1, wherein the step of cross referencing, in the computing device, the plurality of frequencies further comprises the step of:

cross referencing, in the computing device, a list of frequencies associated with the profile, where the profile is one of a plurality of profiles.

7. The method of claim 6, wherein the step of cross referencing the list of frequencies further comprises the step of:

determining if the profile is applicable to the sound print by a degree to which the frequencies associated with the profile fall within the frequency ranges.

8. A non-transitory computer-readable medium having a computer program executable on a computing device for sound analysis, comprising:

code that provides for transforming a sound print into a frequency domain to generate a frequency spectrum;

code that identifies a plurality of signatures in the frequency spectrum, wherein the signatures each comprise a maximum amplitude shift that is less than a predefined threshold over a predefined frequency band;

code that identifies a plurality of frequency ranges associated with the signatures in the sound print; and

code that cross references a plurality of frequencies associated with a profile with the frequency ranges to determine if the profile is applicable to the sound print.

9. The non-transitory computer-readable medium of claim 8, wherein the code that provides for transforming the sound print into the frequency domain to generate the frequency spectrum further comprises a Fast Fourier Transform (FFT).

10. The non-transitory computer-readable medium of claim 8, wherein the code that identifies the plurality of signatures in the frequency spectrum further comprises:

code that identifies the signatures in the sound print by analyzing the sound print over a plurality of octaves.

11. The non-transitory computer-readable medium of claim 8, wherein the plurality of signatures are substantial zero slopes.

12. The non-transitory computer-readable medium of claim 8, further comprising:

code that generates a prioritized list of the frequency ranges wherein the prioritized list of frequency ranges is prioritized by a magnitude of each frequency range.

13. The non-transitory computer-readable medium of claim 8, wherein the code that cross references the plurality of frequencies associated with the profile with the frequency ranges further comprises:

code that cross references a list of frequencies associated with the profile, where the profile is one of a plurality of profiles.

14. A system, comprising:

a processor circuit having a processor and a memory;

a sound analysis system stored in the memory and executable by the processor, the sound analysis system comprising;

logic that provides for transforming a sound print into a frequency domain to generate a frequency spectrum;

logic that identifies a plurality of signatures in the frequency spectrum, wherein the signatures each comprise a maximum amplitude shift that is less than a predefined threshold over a predefined frequency band;

logic that associates a plurality of frequency ranges with the signatures in the sound print; and

logic that cross references a plurality of frequencies associated with a profile with the frequency ranges to determine if the profile is applicable to the sound print.

15. The system of claim 14, wherein the sound analysis system further comprises a set of sound prints.

16. The system of claim 14, wherein the sound print is transformed into the frequency domain to generate the frequency spectrum over a plurality of octaves, wherein the signatures in the sound print are identified by analyzing the sound print over the plurality of octaves.

17. The system of claim 14, wherein the plurality of signatures are substantial zero slopes.

18. A method for signature identification, the method comprising the steps of:

identifying, in a computing device, a plurality of frequency measurement points within a frequency spectrum, the frequency spectrum being generated from a sound print;

measuring, in the computing device, an amplitude shift between consecutive ones of the frequency measurement points; and

identifying, in the computing device, an existence of a signature in a frequency band in the frequency spectrum, the signature comprising a maximum amplitude shift that is less than a predetermined maximum amplitude shift over the frequency band.

19. The method of claim 18, wherein the frequency band has a width of at least 0.33Hz.

20. The method of claim 18, wherein the predetermined maximum amplitude shift is 0.15dB.