DERIVING GEOGRAPHIC DISTRIBUTION OF PHYSIOLOGICAL OR PSYCHOLOGICAL CONDITIONS OF HUMAN SPEAKERS WHILE PRESERVING PERSONAL PRIVACY

• US 20120271637A1
• Filed: 04/30/2012
• Published: 10/25/2012
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Shechtman, Slava, Steinberg, Raphael
• Granted Patent: US 8,498,869 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• 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:

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;

de-identifying the plurality of speech signals so as to preserve the anonymity of the human speaker;

extracting the non-verbal components from the obtained speech signals wherein the non-verbal components comprise speech components that are not derivable from the human language,

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 the geographical locations thereof.

2. The method according to claim 1, further comprising, before the obtaining, rendering the verbal components unidentifiable by applying a de-identifying function to the speech signals.

3. The method according to claim 1, wherein, in the extracting, verbal content associated with the speech signals is rendered unidentifiable.

6. The method according to claim 1, wherein the physiological or the psychological conditions of the human speakers are related to human respiratory systems.

7. The method according to claim 1, wherein the predefined relations between the characteristics of the non-verbal components of the speech signals and the physiological or the psychological conditions of the human speakers are associated with effects of a particular human speaker health condition on the non-verbal components of the respective speech signal.

8. The method according to claim 1, further comprising outputting the geographical distribution of the human speakers and their corresponding physiological or psychological conditions.

9. The method according to claim 1, wherein the providing is performed in at least two time-defined instances, thereby presenting a historical geographical distribution, by presenting a change of the physiological or psychological conditions of the human speakers, over the two time-defined instances, in view of the geographical locations thereof.

4. (canceled)

5. (canceled)

10. A server comprising:

a communication module arranged to obtain, 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;

a location module arranged to identify a plurality of geographical locations, each geographic location associated with a respective one of the plurality of the communication devices;

a de-identification module for de-identifying the plurality of speech signals so as to preserve the anonymity of the human speaker;

an extraction module arranged to extract the non-verbal components from the obtained speech signals, wherein the non-verbal components comprise speech components that are not derivable from the human language;

an analysis module arranged to deduce 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

an association module arranged to provide 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 the geographical locations thereof.

11. The server according to claim 10, wherein the extraction module is further arranged such that verbal content associated with the speech signals is rendered unidentifiable.

14. The server according to claim 10, wherein the physiological or the psychological conditions of the human speakers are related to human respiratory systems.

15. The server according to claim 10, wherein the predefined relations between the characteristics of the non-verbal components of the speech signals and the physiological or the psychological conditions of the human speakers are associated with effects of a particular human speaker health condition on the non-verbal components of the respective speech signal.

16. The server according to claim 10, further comprising an output module arranged to output the geographical distribution of the human speakers and their corresponding physiological or psychological conditions.

17. The server according to claim 10, wherein the association module is arranged to provide the deduced physiological or psychological conditions of the human speakers with the geographical locations thereof, in at least two time-defined instances, thereby presenting a historical geographical distribution, by presenting a change of the physiological or psychological conditions of the human speakers, over the two time-defined instances, in view of the geographical locations thereof.

12. (canceled)

13. (canceled)

18. A system comprising:

a server; and

a plurality of communication devices in communication with the server,

wherein the server is arranged to;

obtain, via the plurality of communication devices, a plurality of speech signals respectively associated with human speakers, the speech signals including verbal components and non-verbal components;

identify a plurality of geographical locations, each geographic location associated with a respective one of the plurality of the communication devices;

de-identify the plurality of speech signals so as to preserve the anonymity of the human speaker;

extract the non-verbal components from the obtained speech signals wherein the non-verbal components comprise speech components that are not derivable from the human language;

deduce 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

provide 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 the geographical locations thereof.

19. The system according to claim 18, wherein the communication devices are cellular communication devices operating within at least one cellular communication network, and wherein the geographical locations and the speech signals are obtained from the at least one cellular communication network.

21. The system according to claim 18, wherein the server is further arranged to extract non-verbal components from the speech signals such that verbal content associated with the speech signals becomes unidentifiable.

22. The system according to claim 18, wherein the physiological or the psychological conditions of the human speakers are associated with the human speakers'"'"' respiratory system.

23. The system according to claim 18, wherein the predefined relations between the characteristics of the non-verbal components of the speech signals and the physiological or the psychological conditions of the human speakers are associated with effects of a particular human speaker health condition on the non-verbal components of the respective speech signal.

24. The system according to claim 18, wherein the server is further arranged to associate the deduced physiological or psychological conditions of the human speakers with the geographical locations thereof, in at least two time-defined instances, thereby presenting a historical geographical distribution, by presenting a change of the physiological or psychological conditions of the human speakers, over the two time-defined instances, in view of the geographical locations thereof.

20. (canceled)

25. A non-transitory computer program product, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to obtain, 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;

computer readable program code configured to identify a plurality of geographical locations, each geographic location associated with a respective one of the plurality of the communication devices;

a computer readable program code configured to de-identify the plurality of speech signals so as to preserve the anonymity of the human speaker;

computer readable program code configured to extract the non-verbal components from the obtained speech signals, wherein the non-verbal components comprise speech components that are not derivable from the human language;

computer readable program code configured to deduce 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

computer readable program code configured to provide 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 the geographical locations thereof.