Method and system for diagnosing pathological phenomenon using a voice signal

• US 7,398,213 B1
• Filed: 05/16/2006
• Issued: 07/08/2008
• Est. Priority Date: 05/17/2005
• Status: Active Grant

• Current Assignee: Beyond Verbal Communication, Ltd. (Vocalis Health, Inc.)
• Original Assignee: Exaudios Technologies Ltd.
• Inventors: Lossos-Shifrin, Lan, Levanon, Yoram
• Primary Examiner(s): Hudspeth; David R.
• Assistant Examiner(s): Jackson; Jakieda R
• Application Number:
  US11/383,634
• Time in Patent Office: 784 Days
• Field of Search: 704/271, 704/261
• US Class Current: 704/271
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

The present invention relates to a method and system for diagnosing pathological phenomenon using a voice signal. In one embodiment, the existence of at least one pathological phenomena is determined based at least in part upon a calculated average intensity function associated with speech from the patient. In another embodiment, the existence of at least one pathological phenomena is determined based at least in part upon the a calculated maximum intensity function associated with speech from the patient.

Claims

1. A method for diagnosing a patient, comprising:

receiving data indicative of speech from the patient;

calculating, based upon the received data, an average intensity function across a plurality of frequencies; and

determining, based at least in part upon a change in intensity between at least two frequencies found in the calculated average intensity function, an existence of at least one pathological phenomena associated with the patient;

wherein the average intensity function is calculated across the plurality of frequencies by averaging, at each of the plurality of frequencies, a plurality of sample intensity values of the speech.

2. The method of claim 1, wherein for each of the plurality of frequencies each of the respective plurality of sample intensity values is separated by a time period.

3. The method of claim 2, wherein each time period is essentially the same.

4. The method of claim 2, wherein the speech has a finite duration and each time period separating the respective plurality of sample intensity values is essentially evenly distributed within the duration of the speech.

5. The method of claim 1, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the average intensity function including at least one crater feature.

6. The method of claim 5, wherein at least one of a height and a width of the crater feature provides an indicator of an intensity of the pathological phenomena.

7. The method of claim 1, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the average intensity function including at least one table feature.

8. The method of claim 1, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the average intensity function including a relatively rapid decline in intensity at the high end of the frequency range of the average intensity function.

9. The method of claim 1, wherein the steps are carried out in the order recited.

10. A method for diagnosing a patient, comprising:

receiving data indicative of speech from the patient;

calculating, based upon the received data, a maximum intensity function across a plurality of frequencies; and

determining, based at least in part upon a change in intensity between at least two frequencies found in the calculated maximum intensity function, an existence of at least one pathological phenomena associated with the patient;

wherein the maximum intensity function is calculated across the plurality of frequencies by determining, at each of the plurality of frequencies, a maximum of a plurality of sample intensity values of the speech.

11. The method of claim 10, wherein for each of the plurality of frequencies each of the respective plurality of sample intensity values is separated by a time period.

12. The method of claim 11, wherein each time period is essentially the same.

13. The method of claim 11, wherein the speech has a finite duration and each time period separating the respective plurality of sample intensity values is essentially evenly distributed within the duration of the speech.

14. The method of claim 10, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the maximum intensity function including at least one crater feature.

15. The method of claim 14, wherein at least one of a height and a width of the crater feature provides an indicator of an intensity of the pathological phenomena.

16. The method of claim 10, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the maximum intensity function including at least one table feature.

17. The method of claim 10, wherein the existence of at least one pathological phenomena associated with the patient is determined based at least in part upon the maximum intensity function including a relatively rapid decline in intensity at the high end of the frequency range of the maximum intensity function.

18. The method of claim 10, wherein the steps are carried out in the order recited.

19. A system for diagnosing a patient, comprising:

an input mechanism, wherein the input mechanism receives data indicative of speech from the patient;

a calculating mechanism, wherein the calculating mechanism calculates, based upon the received data, an average intensity function across a plurality of frequencies; and

a determining mechanism, wherein the determining mechanism determines, based at least in part upon a change in intensity between at least two frequencies found in the calculated average intensity function, an existence of at least one pathological phenomena associated with the patient;

wherein the average intensity function is calculated across the plurality of frequencies by averaging, at each of the plurality of frequencies, a plurality of sample intensity values of the speech.

20. The system of claim 19, wherein each of the input mechanism, the calculating mechanism and the determining mechanism comprises at least one of computer software and computer hardware.

21. A system for diagnosing a patient, comprising:

an input mechanism, wherein the input mechanism receives data indicative of speech from the patient;

a calculating mechanism, wherein the calculating mechanism calculates, based upon the received data, a maximum intensity function across a plurality of frequencies; and

a determining mechanism, wherein the determining mechanism determines, based at least in part upon a change in intensity between at least two frequencies found in the calculated maximum intensity function, an existence of at least one pathological phenomena associated with the patient;

wherein the maximum intensity function is calculated across the plurality of frequencies by determining, at each of the plurality of frequencies, a maximum of a plurality of sample intensity values of the speech.

22. The system of claim 21, wherein each of the input mechanism, the calculating mechanism and the determining mechanism comprises at least one of computer software and computer hardware.

23. A method for diagnosing a patient, comprising:

receiving data indicative of speech from the patient;

calculating, based upon the received data, an average intensity function across a plurality of frequencies;

calculating, based upon the received data, a maximum intensity function across the plurality of frequencies;

determining, based at least in part upon a change in intensity between at least two frequencies found in the calculated average intensity function and based at least in part upon a change in intensity between at least two frequencies found in the calculated maximum intensity function, an existence of at least one pathological phenomena associated with the patient;

wherein the average intensity function is calculated across the plurality of frequencies by averaging, at each of the plurality of frequencies, a plurality of sample intensity values of the speech; and

wherein the maximum intensity function is calculated across the plurality of frequencies by determining, at each of the plurality of frequencies, a maximum of a plurality of sample intensity values of the speech.