Method, device and system for estimating the condition of a user

• US 6,289,313 B1
• Filed: 06/22/1999
• Issued: 09/11/2001
• Est. Priority Date: 06/30/1998
• Status: Expired due to Term

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Mobile Phones UK Limited (Nokia Corporation)
• Inventors: Heinonen, Pekka, Okkonen, Harri, Ranta, Jukka
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/338,205
• Time in Patent Office: 812 Days
• Field of Search: 704/223, 704/200, 704/219, 704/270, 704/271, 704/275, 704/207, 600/300, 600/301
• US Class Current: 704/270
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

An improved method for estimating the status of human physiological and/or psychological conditions by observing the values of the vocal tract parameters output from a digital speech encoder. The user (40) speaks to his device (41), which transforms the input speech from analog to digital form, performs speech encoding (42) on the derived digital signal, and provides values of speech coding parameters (43) locally for further analysis. The stored mathematical relation, e.g. the user-specific vocal tract transformation matrix (47) is retrieved from the memory and utilized in the calculation of corresponding condition parameters (45). Based on these calculated parameters, an estimation (48) of the present status of user'"'"'s condition can be derived (48).

Claims

1. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein:

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters; and

estimating the status of said condition based on said calculated values of said condition parameters.

2. A method according to claim 1, wherein said calculation is carried out locally in a device comprising a speech encoder.

3. A method according to claim 1 or 2, wherein the method further comprises transmitting the locally generated set of values of speech coding parameters to a remote monitoring system via a telecommunication link for said calculation of values of said condition parameters.

4. A method according to claim 3, wherein said transmission is carried out as a response to a user command to estimate the status of said condition.

5. A method according to claim 1, wherein said set of values of speech coding parameters is collected from normal uplink bitstream by a network element (BSC).

6. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters;

estimating the status of said condition based on said calculated values of said condition parameters;

wherein said condition is the condition of user'"'"'s pulmonary function, and the method further comprises the steps of

measuring values of chosen pulmonary function parameters in a number of different asthma conditions;

taking speech samples virtually simultaneously with said measurements and processing said samples into input audio signals;

generating a set of values for certain speech coding parameters from said input audio signals; and

deriving a user-specific mathematical relation between said values of pulmonary function parameters and values of speech coding parameters.

7. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters;

wherein the mathematical relation is a user-specific transformation matrix C_nxk derived from the equation;

8. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal, wherein said speech coding parameters comprise at least one of the following parameters of an RPE-LTP speech encoder;

LPC coefficients, LTP parameters, FFT spectrum calculated from the LPC residual signal, parameters from the LPC residual signal, parameters from the LPC residual signal calculated using true LPC coefficients instead of the quantized coefficients;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters; and

estimating the status of said condition based on said calculated values of said condition parameters.

9. A device (MS) for estimating the status of at least one of a physiological and psychological condition of a user, wherein the device comprises:

input means (21;

320, 301) for receiving input speech and transforming it into input audio signal;

a speech encoder (22;

302) for generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

a memory (23;

330) for storing data on a user-specific mathematical relation between parameters of said condition and speech parameters;

a processor (24;

319) for applying said user-specific mathematical relation to calculate values of said condition parameters from said set of values of speech coding parameters; and

output means (25;

320) for providing the resulting calculated values of certain condition parameters for estimation of the status of the user'"'"'s condition.

10. A device according to claim 9, wherein the device also comprises means (303-318) for functioning as a mobile station in a telecommunication network.

11. A device according to claim 10, wherein the device is arranged to, as a response to a user command, direct said speech coding parameters locally to said processor (319) to be used for estimation of said condition.

12. A device according to claim 9 or 10, wherein the speech encoder (302) comprises two functional units (82, 85), a first unit (82) for generating speech coding parameters for normal transmission over the radio path, and a second unit (85) for generating speech coding parameters for monitoring purposes.

13. A device (MS) for estimating the status of at least one of a physiological and psychological condition of a user, wherein the device comprises:

input means (21;

320, 301) for receiving input speech and transforming it into input audio signal;

a speech encoder (22;

302) for generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

a memory (23;

330) for storing data on a user-specific mathematical relation between parameters of said condition and speech parameters, wherein said condition is the condition of user'"'"'s pulmonary function;

a processor (24;

319) for applying said user-specific mathematical relation to calculate values of said condition parameters from said set of values of speech coding parameters; and

output means (25;

320) for providing the resulting calculated values of certain condition parameters for estimation of the status of the user'"'"'s condition.

14. A system for estimating the status of at least one of a physiological and psychological condition of a user, wherein said system comprising:

a plurality of monitoring devices (MS) comprising

input means (21;

320, 301) for receiving input speech and transforming it into input audio signal, and

a speech encoder (22;

302) for generating a set of values for speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

a central monitoring unit (SYS) comprising

a database (DB) for storing data on a user-specific mathematical relation between parameters representing said condition and speech parameters, separately defined for each user,

a processing unit (CP) for, as a response to a received set of values for certain speech coding parameters, retrieving the user-specific mathematical relation from the database (DB) and applying said relation to calculate the values of chosen condition parameters from said set of values for chosen speech parameters;

an estimation unit (SYS) for, as a response to the calculated values of chosen condition parameters, producing an estimate on the status of condition of the user.

15. A system according to claim 14, wherein the processing unit (CP) is arranged to calculate the user-specific mathematical relation from given values of said condition parameters and speech coding parameters.

16. A system according to claim 14, wherein the link between the elements comprises a cellular digital network, and the monitoring device comprises a mobile station (MS) of said network.

17. A system according to claim 14, wherein said central monitoring unit (SYS) is connected to the mobile switching center of the network (MSC).

18. A system according to claim 14, wherein said central monitoring unit (SYS) is situated in a remote location and can also be accessed by authorized third parties.

19. A system according to claim 14, wherein said central monitoring unit (SYS) is arranged to constantly survey said calculated values of pulmonary function parameters, and in case of observed emergency situation, initiate a necessary rescue operation.

20. A system for estimating the status of at least one of a physiological and psychological condition of a user, wherein said system comprising:

a plurality of monitoring devices (MS) comprising;

input means (21;

320, 301) for receiving input speech and transforming it into input audio signal,

a speech encoder (22;

302) for generating a set of values for speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

a central monitoring unit (SYS) comprising;

a database (DB) for storing data on a user-specific mathematical relation between parameters representing said condition and speech parameters, separately defined for each user, wherein said condition is the condition of user'"'"'s pulmonary function;

a processing unit (CP) for, as a response to a received set of values for certain speech coding parameters, retrieving the user-specific mathematical relation from the database (DB) and applying said relation to calculate the values of chosen condition parameters from said set of values for chosen speech parameters;

an estimation unit (SYS) for, as a response to the calculated values of chosen condition parameters, producing an estimate on the status of condition of the user.

21. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters;

estimating the status of said condition based on said calculated values of said condition parameters;

wherein said condition is the condition of user'"'"'s physiological and psychological function, and the method further comprises the steps of

measuring values of chosen physiological and psychological function parameters in a number of different pulmonary conditions;

taking speech samples virtually simultaneously with said measurements and processing said samples into input audio signals;

generating a set of values for certain speech coding parameters from said input audio signals; and

deriving a user-specific mathematical relation between said values of physiological and psychological function parameters and values of speech coding parameters.

22. A method for estimating the status of at least one of a physiological and psychological condition of a user, wherein

taking speech samples from the user and processing said samples into an input audio signal;

generating a set of values of speech coding parameters from said input audio signal, said speech coding parameters representing characteristics of said input audio signal, wherein said speech coding parameters comprise at least one of the following parameters of speech encoder;

LPC coefficients, LTP parameters, FFT spectrum calculated from the LPC residual signal, parameters from the LPC residual signal, parameters from the LPC residual signal calculated using true LPC coefficients instead of the quantized coefficients;

applying a user specific mathematical relation to calculate values for parameters of said condition from said set of values of speech coding parameters; and

estimating the status of said condition based on said calculated values of said condition parameters.