Location tracking from natural speech

• US 9,640,199 B2
• Filed: 12/17/2014
• Issued: 05/02/2017
• Est. Priority Date: 12/27/2013
• Status: Active Grant

• Current Assignee: Kopin Corporation
• Original Assignee: Kopin Corporation
• Inventors: Parkinson, Christopher, Jacobsen, Jeffrey J., Leib, Shai
• Primary Examiner(s): Holder, Regina N
• Application Number:
  US14/573,835
• Publication Number:
  US 20150187371A1
• Time in Patent Office: 867 Days
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: H04R 1/08 Mouthpieces; Microphones; Attachments therefor
• CPC Class Codes: H04R 1/1091 Details not provided for in groups H04R1/1008 - H04R1/1083

Abstract

A headset computer device provides user voice indication of location of the device. The user may implicitly or explicitly present by voice input his and hence the HSC device location. A voice driven location module is coupled to the voice recognition engine, a map database and GPS of the HSC device. Based on user voiced indications of 3D space location, the voice driven location module determines device location and resets 3D space location accordingly.

Claims

1. A headset computer device comprising:

a microdisplay driven by a processor;

a microphone coupled to provide user-voiced input to the processor; and

a voice location module, executed by the processor, configured to

(i) extract one or more location-related phrases from an ongoing user utterance that was produced during ordinary conversation, conveyed through the user-voiced input;

(ii) analyze the one or more location-related phrases to identify at least one location-related reference word; and

(iii) establish a location of the device based on the at least one location-related reference word.

2. The headset computer device of claim 1, wherein the processor resets the established location based on the user-voiced input.

3. The headset computer device of claim 1, wherein the voice location module is further configured to establish the location of the device within a three dimensional coordinate system.

4. The headset computer device of claim 1, wherein the user-voiced input is in response to a solicitation from the headset computer device.

5. The headset computer device of claim 1, wherein the headset computer device is further configured to extract the user-voiced input from unsolicited utterances.

6. The headset computer device of claim 1, wherein the user-voiced input includes information describing proximity to an object.

7. The headset computer device of claim 6, wherein the headset computer device is further configured to cross-reference the information describing proximity to an object with a reference plan of known objects.

8. The headset computer device of claim 6, wherein the headset computer device is further configured to identify a match between the information describing proximity to an object and a known object described in the reference plan.

9. The headset computer device of claim 1, wherein the headset computer is further configured to use inertial navigation to determine a subsequent location of the device, after the voice location module establishes the location of the device.

10. A method of enhancing a location system, comprising:

by a digital processing device,

(i) extracting one or more location-related phrases from an ongoing user utterance that was produced during ordinary conversation;

(ii) analyzing the one or more location related phrases to identify at least one location-related reference word;

(iii) recognizing the location-related reference word as a description of an object disposed within a region;

(iv) identifying the object within a map of the region;

(v) extracting locational coordinates associated with the object from the map of the region; and

(vi) establishing a location of the device based on the locational coordinates.

11. The method of claim 10, further including resetting the established location based on the user voiced input.

12. The method of claim 10, further including establishing the location of the device within a three dimensional coordinate system.

13. The method of claim 10, wherein the description of the object includes proximity to an object.

14. The method of claim 10, wherein the user-voiced input is in response to a solicitation from the headset computer device.

15. The method of claim 10, wherein the headset computer device extracts the user-voiced input from unsolicited utterances.

16. The method of claim 10, wherein the user-voiced input includes information describing proximity to an object.

17. The method of claim 16, further including cross-referencing the information describing proximity to an object with a reference plan of known objects.

18. The method of claim 16, further including identifying a match between the information describing proximity to an object and a known object described in the reference plan.

19. The method of claim 10, further including using inertial navigation to determine a subsequent location of the device, after the voice location module establishes the location of the device.

20. A non-transitory computer-readable medium for recognizing speech, the non-transitory computer-readable medium comprising computer software instructions stored thereon, the computer software instructions, when executed by at least one processor, cause a computer system to:

(i) extract one or more location-related phrases form an ongoing user utterance that was produced during ordinary conversation;

(ii) analyze the one or more location related phrases to identify at least one location-related reference word;

(i) recognize the location-related reference word as a description of an object disposed within a region;

(ii) identify the object within a map of the region;

(iii) extract locational coordinates associated with the object from the map of the region; and

(iv) establish a location of a user who produced the user utterance based on the locational coordinates.