Using sounds for determining a worn state of a wearable computing device

• US 9,720,083 B2
• Filed: 02/15/2017
• Issued: 08/01/2017
• Est. Priority Date: 06/05/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gossett, Carroll Philip, Johnson, Michael Patrick
• Primary Examiner(s): Chin, Vivian
• Assistant Examiner(s): ODUNUKWE, UBACHUKWU A
• Application Number:
  US15/433,233
• Publication Number:
  US 20170160394A1
• Time in Patent Office: 167 Days
• Field of Search: 381 58
• CPC Class Codes: G01S 15/04 Systems determining presence of a target
• CPC Class Codes: G02B 2027/0178 Eyeglass type eyeglass details G02C
• CPC Class Codes: G02B 27/017 Head mounted
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: H04R 1/028 associated with devices performing functions other than acoustics, e.g. electric candles
• CPC Class Codes: H04R 29/001 for loudspeakers H04R29/007 takes precedence
• CPC Class Codes: H04R 3/00 Circuits for transducers , loudspeakers or microphones

Abstract

Methods, apparatus, and computer-readable media are described herein related to using self-generated sounds for determining a worn state of a wearable computing device. A wearable computing device can transmit an audio signal. One or more sensors coupled to the wearable computing device may then receive a modified version of the audio signal. A comparison may be made between the modified version of the audio signal and at least one reference signal, where the at least one reference signal is based on the audio signal that is transmitted. Based on an output of the comparison, a determination can be made of whether the wearable computing device is being worn.

Claims

1. A method, comprising:

transmitting, by one or more audio sources, an audio signal;

receiving, at one or more sensors coupled to a wearable computing device, an airborne version of the audio signal, modified by an environment of the wearable computing device;

processing the airborne version of the audio signal to obtain an impulse response parameter and a power spectrum parameter;

comparing the obtained impulse response and power spectrum parameters with at least one classifier of a support vector machine (SVM) model, wherein the at least one classifier is associated with one or more worn states of the wearable computing device, and wherein the SVM model correlates an impulse response parameter and a power spectrum parameter of one or more reference signals; and

based on the comparison of the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model, determining, from the one or more worn states, a worn state of the wearable computing device.

2. The method of claim 1, wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining whether the obtained parameters are within a threshold of the at least one classifier.

3. The method of claim 1, wherein the at least one classifier includes a plurality of classifiers that together define a plurality of regions within the SVM model, each region of the plurality of regions corresponding to a respective worn state of the one or more worn states,

wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining, from the plurality of regions, a particular region in which the obtained impulse response and power spectrum parameters are,

wherein determining, from the one or more worn states, the worn state of the wearable computing device based on the comparison of the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining the worn state of the wearable computing device to be the worn state that corresponds to the determined particular region.

4. The method of claim 1, wherein the at least one classifier includes at least one linear classifier.

5. The method of claim 1, wherein the at least one classifier includes at least one non-linear classifier.

6. The method of claim 1, wherein the SVM model comprises an n-dimensional SVM model, wherein n is greater than two.

7. The method of claim 1, further comprising:

receiving, from another one or more sensors of the wearable computing device, data indicative of the worn state of the wearable computing device; and

wherein determining the worn state of the wearable computing device is further based on the received data from the other one or more sensors.

8. The method of claim 1, further comprising:

receiving an output signal indicative of the determination of the worn state of the wearable computing device;

based on the output signal, determining a first power state of the wearable computing device, wherein the first power state is associated with the wearable computing device operating at a first power level;

determining a change in the output signal; and

after a predetermined amount of time, transitioning from the first power state to a second power state of the wearable computing device, wherein the second power state is associated with the wearable computing device operating at a second power level that is different from the first power level.

9. A non-transitory computer readable medium having stored thereon instructions that, upon execution by a wearable computing device, cause the wearable computing device to perform functions comprising:

transmitting, by one or more audio sources, an audio signal;

receiving, at one or more sensors coupled to the wearable computing device, an airborne version of the audio signal, modified by an environment of the wearable computing device;

processing the airborne version of the audio signal to obtain an impulse response parameter and a power spectrum parameter;

comparing the obtained impulse response and power spectrum parameters with at least one classifier of a support vector machine (SVM) model, wherein the at least one classifier is associated with one or more worn states of the wearable computing device, and wherein the SVM model correlates an impulse response parameter and a power spectrum parameter of one or more reference signals; and

based on the comparison of the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model, determining, from the one or more worn states, a worn state of the wearable computing device.

10. The non-transitory computer readable medium of claim 9, wherein the wearable computing device is a head-mountable computing device (HMD) configured to be worn by a wearer of the HMD on a head of the wearer, and wherein the one or more audio sources are coupled to the HMD.

11. The non-transitory computer readable medium of claim 10, wherein transmitting the audio signal comprises transmitting the audio signal through a bone structure of the head of the wearer,

wherein the one or more sensors includes at least a first and second sensor proximate to the head of the wearer.

12. The non-transitory computer readable medium of claim 9, wherein the one or more reference signals are based on the transmitted audio signal.

13. The non-transitory computer readable medium of claim 9, the functions further comprising:

determining a kurtosis measurement based on the obtained impulse response and power spectrum parameters of the airborne version of the audio signal,

wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises comparing the kurtosis measurement with the at least one classifier of the SVM model.

14. The non-transitory computer readable medium of claim 9, wherein the at least one classifier includes a plurality of classifiers that together define a plurality of regions within the SVM model, each region of the plurality of regions corresponding to a respective worn state of the one or more worn states,

wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining, from the plurality of regions, a particular region in which the obtained impulse response and power spectrum parameters are,

wherein determining, from the one or more worn states, the worn state of the wearable computing device based on the comparison of the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining the worn state of the wearable computing device to be the worn state that corresponds to the determined particular region.

15. The non-transitory computer readable medium of claim 9, wherein the at least one classifier includes at least one linear classifier.

16. A system, comprising:

a head-mountable computing device (HMD);

one or more audio sources;

one or more sensors coupled to the HMD;

at least one processor coupled to the HMD; and

data storage comprising instructions executable by the at least one processor to cause the system to perform functions comprising;

transmitting, by the one or more audio sources, an audio signal;

receiving, at the one or more sensors, an airborne version of the audio signal, modified by an environment of the HMD;

processing the airborne version of the audio signal to obtain an impulse response parameter and a power spectrum parameter;

comparing the obtained impulse response and power spectrum parameters with at least one classifier of a support vector machine (SVM) model, wherein the at least one classifier is associated with one or more worn states of the HMD, and wherein the SVM model correlates an impulse response parameter and a power spectrum parameter of one or more reference signals; and

based on the comparison of the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model, determining, from the one or more worn states, a worn state of the HMD.

17. The system of claim 16, wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises determining whether the obtained parameters are within a threshold of the at least one classifier.

18. The system of claim 16, wherein processing the airborne version of the audio signal to obtain the impulse response and power spectrum parameters of the airborne version of the audio signal comprises performing a Fast Fourier Transform on the airborne version of the audio signal to obtain the impulse response and power spectrum parameters of the airborne version of the audio signal.

19. The system of claim 16, the functions further comprising:

receiving, from another one or more sensors coupled to the HMD, data indicative of whether or not the HMD is being worn, wherein the other one or more sensors include one or more of a proximity sensor and a capacitive sensor, and

wherein determining the worn state of the HMD is further based on the received data from the other one or more sensors.

20. The system of claim 16, the functions further comprising:

determining a kurtosis measurement based on the obtained impulse response and power spectrum parameters of the airborne version of the audio signal,

wherein comparing the obtained impulse response and power spectrum parameters with the at least one classifier of the SVM model comprises comparing the kurtosis measurement with the at least one classifier of the SVM model.