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

• US 8,498,869 B2
• Filed: 04/30/2012
• Issued: 07/30/2013
• 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:
  US13/459,274
• Publication Number:
  US 20120271637A1
• Time in Patent Office: 456 Days
• Field of Search: 704/231, 704/270, 704/275, 704/201, 704/274, 600/529, 600/532, 600/300, 380/275, 380/276
• 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, by a server, non-verbal components of a plurality of speech signals which underwent de-identifying prior to being received by the server, so as to preserve privacy of the speaker at the server, and geographical locations respectively associated with the speech signals;

deducing, by the server, physiological or psychological conditions corresponding to the non-verbal components, using predefined relations between characteristics of the non-verbal components and physiological or psychological conditions of human speakers; and

providing a geographical distribution of the deduced physiological or psychological conditions by associating the deduced physiological or psychological conditions with the respective geographical locations of the obtained speech signals from which the conditions were deduced.

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

3. 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.

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

5. The method according to claim 1, wherein the obtaining is performed for speech signals 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.

6. The method according to claim 1, wherein obtaining the non-verbal components comprises obtaining a plurality of speech signals, and extracting the non-verbal components from the speech signals, by the server.

7. The method according to claim 1, wherein obtaining the speech signals comprises obtaining speech signals that underwent time-domain windowing.

8. The method according to claim 1, wherein obtaining the speech signals comprises obtaining speech signals that underwent frequency-domain filtering.

9. The method according to claim 1, wherein obtaining the speech signals comprises obtaining speech signals that underwent a time-domain scrambling algorithm.

10. The method according to claim 1, wherein obtaining the geographical locations comprises obtaining from at least one communication network.

11. The method according to claim 10, wherein obtaining the geographical locations comprises obtaining from at least one telephone communication network.

12. A system comprising:

a server arranged to;

obtain non-verbal components of a plurality of speech signals, which underwent de-identifying prior to being received by the server, so as to preserve privacy of the speaker at the server, and geographical locations respectively associated with the speech signals;

deduce physiological or psychological conditions corresponding to the non-verbal components, using predefined relations between characteristics of the non-verbal components and physiological or psychological conditions of human speakers; and

provide a geographical distribution of the deduced physiological or psychological conditions by associating the deduced physiological or psychological conditions with the geographical locations of the obtained speech signals from which the conditions were deduced.

13. The system according to claim 12, wherein the server is arranged to obtain the geographical locations and the speech signals from at least one communication network.

14. The system according to claim 12, wherein the physiological or the psychological conditions of the human speakers are associated with the human speakers'"'"' respiratory system.

15. The system according to claim 12, 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 system according to claim 12, 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.

17. 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 non-verbal components of a plurality of speech signals, which underwent de-identifying prior to being received by a server running the computer readable program code, so as to preserve privacy of the speaker at the server, and geographical locations respectively associated with the speech signals;

computer readable program code configured to deduce physiological or psychological conditions corresponding to the obtained non-verbal components, using predefined relations between characteristics of the non-verbal components and physiological or psychological conditions of human speakers; and

computer readable program code configured to provide a geographical distribution of the deduced physiological or psychological conditions by associating the deduced physiological or psychological conditions with the geographical locations of the obtained speech signals from which the conditions were deduced.