Text editing with gesture control and natural speech

• US 9,640,181 B2
• Filed: 12/19/2014
• Issued: 05/02/2017
• Est. Priority Date: 12/27/2013
• Status: Active Grant

• Current Assignee: Kopin Corporation
• Original Assignee: Kopin Corporation
• Inventors: Parkinson, Christopher, Leib, Shai
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): Nguyen, Timothy
• Application Number:
  US14/577,600
• Publication Number:
  US 20150187355A1
• Time in Patent Office: 865 Days
• Field of Search: 704235
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A speech processing engine of an HSC device transcribes user utterance input and displays resulting text on a microdisplay. The speech processing engine further provides to the user text editing functions and auto suggestions. The user interface utilizes head gesture control and natural language for text editing. Standard language dictionaries, user'"'"'s dictionary and user'"'"'s address book contacts data are utilized.

Claims

1. A headset computer device comprising:

a microdisplay driven by a processor;

a microphone configured to provide user utterances as input to the processor;

head tracking circuitry configured to provide orientational sensing information describing an orientation of the headset computer;

a joint head-tracking and voice command text selection module configured to receive the user utterances and orientational sensing information and produce user input based on the user utterances and orientational sensing information;

a speech processing engine, executed by the processor, the speech processing engine configured to (i) transcribe the user utterances and display resulting transcription text on the microdisplay, (ii) be responsive to the user input directed to editing the displayed transcription text, and (iii) provide editing assistance using fuzzy matching.

2. The headset computer device of claim 1, wherein the editing assistance includes suggested alternatives to one or more portions of the transcription text.

3. The headset computer device of claim 2, wherein the suggested alternatives are based at least on context of the portions of the transcription text within the transcription text.

4. Previously presented) The headset computer device of claim 1, wherein the editing assistance includes auto-correcting transcription text based on a dictionary.

5. The headset computer device of claim 4, wherein the dictionary includes one or more of a standard language dictionary and a personal dictionary.

6. The headset computer device of claim 1, wherein the editing assistance includes name correction using a local contact database.

7. The headset computer device of claim 1, wherein the user input directed to editing the displayed transcription text includes at least one spoken global language command.

8. The headset computer device of claim 1, wherein the user input includes at least one of (i) a user control gesture, and (ii) a user control utterance, for selecting a portion of the transcription text.

9. The headset computer device of claim 8, wherein the user input further includes at least one of (i) a user edit gesture, and (ii) a user edit utterance, for selecting an edit command to apply to the portion of the transcription text.

10. A method of editing on a headset computer device, comprising:

by a processor,

generating orientational sensing information describing an orientation of the headset computer;

producing user input based on user utterances received via a microphone and the orientational sensing information;

transcribing the user utterances to produce transcription text;

displaying the transcription text;

responding to the user input directed to editing the displayed transcription text; and

providing editing assistance using fuzzy matching.

11. The method of claim 10, wherein providing editing assistance includes suggesting alternatives to one or more portions of the transcription text.

12. The method of claim 11, wherein the alternatives are based at least on context of the portions of the transcription text within the transcription text.

13. The method of claim 10, wherein providing editing assistance includes auto-correcting transcription text based on a dictionary.

14. The method of claim 10, wherein providing editing assistance includes correcting names using a local contact database.

15. The method of claim 10, wherein the user input directed to editing the displayed transcription text includes at least one spoken global language command.

16. The method of claim 10, wherein the user input includes at least one of (i) a user control gesture, and (ii) a user control utterance, for selecting a portion of the transcription text.

17. The method of claim 16, wherein the user input further includes at least one of (i) a user edit gesture, and (ii) a user edit utterance, for selecting an edit command to apply to the portion of the transcription text.

18. A non-transitory computer-readable medium for editing text, the non-transitory computer-readable medium comprising computer software instructions stored thereon, the computer software instructions, when executed by at least one processor, causes a computer system to:

generate orientational sensing information describing an orientation of the headset computer;

produce user input based on user utterances received via a microphone and the orientational sensing information;

transcribe the user utterances to produce transcription text;

display the transcription text;

respond to the user input directed to editing the displayed transcription text; and

provide editing assistance using fuzzy matching.