Deriving geographic distribution of physiological or psychological conditions of human speakers while preserving personal privacy

• US 9,159,323 B2
• Filed: 07/29/2013
• Issued: 10/13/2015
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Shechtman, Slava, Steinberg, Raphael
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/953,527
• Publication Number:
  US 20130317825A1
• Time in Patent Office: 806 Days
• Field of Search: 704/201, 704/231, 704/270, 704/275, 600/529, 600/301, 379/38
• US Class Current: 1/1
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34

Abstract

A method including: obtaining, via a plurality of communication devices, a plurality of speech signals respectively associated with human speakers, the speech signals including verbal components and non-verbal components; identifying a plurality of geographical locations, each geographic location associated with a respective one of the plurality of the communication devices; extracting the non-verbal components from the obtained speech signals; deducing physiological or psychological conditions of the human speakers by analyzing, over a specified period, the extracted non-verbal components, using predefined relations between characteristics of the non-verbal components and physiological or psychological conditions of the human speakers; and providing a geographical distribution of the deduced physiological or psychological conditions of the human speakers by associating the deduced physiological or psychological conditions of the human speakers with geographical locations thereof.

Claims

1. A method comprising:

for each speech signal of a plurality of speech signals;

obtaining, by a computer, non-verbal components of the speech signal and a geographical location associated with the speech signal, the speech signal having been de-identified;

deducing, by the computer, a physiological and/or psychological condition corresponding to the non-verbal components; and

associating the deduced physiological and/or psychological condition with the respective geographical location of the obtained speech signal,

thereby providing a geographical distribution of the physiological and/or psychological conditions.

2. The method according to claim 1, wherein deducing further comprises using, at least in part, characteristics of the non-verbal components of the speech signal and/or information relating to physiological and/or psychological conditions of human speakers.

3. The method according to claim 2, wherein deducing comprises evaluating information that specifies relationships between the characteristics of the non-verbal components of the speech signal and the physiological and/or the psychological condition of a human speaker associated with the speech signal.

4. The method according to claim 1, further comprising outputting the geographical distribution of the physiological and/or psychological conditions and of human speakers associated with the physiological and/or psychological conditions at least by outputting an alarm if at least one criterion is met.

5. The method according to claim 2, further comprising outputting the geographical distribution of the physiological and/or psychological conditions and of human speakers associated with the physiological and/or psychological conditions.

6. The method according to claim 1, wherein obtaining is performed for each speech signal of the plurality of speech signals in at least two time-defined instances, thereby presenting a historical geographical distribution, by presenting, for each speech signal of the plurality of speech signals, a change of the deduced physiological and/or psychological condition, over the at least two time-defined instances, in view of the geographical location thereof.

7. The method according to claim 1, wherein obtaining further comprises obtaining the speech signal and extracting the non-verbal components from the speech signal, by the computer.

8. The method according to claim 1, wherein the speech signal having been de-identified comprises the speech signal having underwent time-domain scrambling and/or frequency-domain filtering.

9. The method according to claim 1, wherein obtaining further comprises obtaining the geographical location from at least one telephone communication network.

10. A system comprising:

a computer configured to, for each speech signal of a plurality of speech signals;

obtain non-verbal components of the speech signal and a geographical location associated with the speech signal, the speech signal having been de-identified;

deduce a physiological and/or psychological condition corresponding to the non-verbal components; and

associate the deduced physiological and/or psychological condition with the respective geographical location of the obtained speech signal,

thereby providing a geographical distribution of the physiological and/or psychological conditions.

11. The system according to claim 10, wherein the computer is further configured to obtain the geographical location and the speech signal from at least one communication network.

12. The system according to claim 10, wherein the computer is further configured to deduce the physiological and/or the psychological condition based, at least in part, on information about human respiratory systems.

13. The system according to claim 10, wherein the computer is further configured to associate characteristics of the non-verbal components of the speech signal and the physiological and/or the psychological condition with effects of a particular health condition of a human speaker on the non-verbal components of a speech signal associated with the human speaker.

14. The system according to claim 10, wherein the computer is further configured to, for each speech signal of the plurality of speech signals, associate the deduced physiological and/or psychological condition with the geographical location in at least two time-defined instances, and thereby to present a historical geographical distribution, by presenting, for each speech signal of the plurality of speech signals, a change of the physiological and/or psychological condition, over the at least two time-defined instances, in view of the geographical location thereof.

15. A non-transitory computer-readable storage medium having instructions that, when executed by a processor, perform a method comprising:

for each speech signal of a plurality of speech signals;

obtaining non-verbal components of the speech signal and a geographical location associated with the speech signal, the speech signal having been de-identified;

deducing a physiological and/or psychological condition corresponding to the non-verbal components; and

associating the deduced physiological and/or psychological condition with the respective geographical location of the obtained speech,

thereby providing a geographical distribution of the physiological and/or psychological conditions.

16. The non-transitory computer-readable storage medium according to claim 15, wherein the method further comprises deducing, at least in part, characteristics of the non-verbal components of the speech signal and/or information relating to physiological and/or psychological conditions of human speakers.

17. The non-transitory computer-readable storage medium according to claim 16, wherein the method further comprises associating the characteristics of the non-verbal components of the speech signal and the physiological and/or the psychological condition with effects of a particular health condition of a human speaker on the non-verbal components of a speech signal associated with the human speaker.

18. The non-transitory computer-readable storage medium according to claim 15, wherein the method further comprises outputting the geographical distribution of the physiological and/or psychological conditions and of human speakers associated with the physiological and/or psychological conditions.

19. The non-transitory computer-readable storage medium according to claim 15, wherein the method further comprises obtaining, for each speech signal of the plurality of speech signals, the speech signal in at least two time-defined instances, the thereby presenting a historical geographical distribution, by presenting, for each speech signal of the plurality of speech signals, a change of the deduced physiological and/or psychological condition, over the at least two time-defined instances, in view of the geographical location thereof.

20. The non-transitory computer-readable storage medium according to claim 15, wherein the method further comprises obtaining the geographical location from at least one telephone communication network.