GUI for the semantic normalization of natural language

• US 7,899,674 B1
• Filed: 01/30/2007
• Issued: 03/01/2011
• Est. Priority Date: 08/11/2006
• Status: Active Grant

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Rubin, Stuart Harvey
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): Colucci; Michael C
• Application Number:
  US11/668,831
• Time in Patent Office: 1,491 Days
• Field of Search: 704/235, 704/9, 704/251, 704/275, 704/273, 704/272, 704/270, 704/260, 704/257, 704/200, 704/10, 704/1, 715/257, 715/723, 715/243, 463/30, 345/418
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A graphical user interface for a semantic normalizer of natural language comprising: a link to a preference menu, in which a user may set the semantic normalizer to operate in a predictive or learning mode; an input textbox disposed to display user-typed text in a first font color and user-spoken text in a second font color; a semantic echo textbox disposed to display semantically normalized text in a third font color, wherein the first, second, and third font colors are different from each other; graphical buttons that are only enabled when the semantic normalizer is in learning mode, wherein the graphical buttons may be selected by the user after the user has been prompted by the semantic normalizer to verify the accuracy of the semantically normalized text, the graphical buttons comprising a “Yes” button, a “No” button, and an “Enter Correction” button.

Claims

1. A computer apparatus configured with a graphical user interface for a semantic normalizer, comprising:

a predictor processor configured to;

I) prompt a user to speak or type;

II) flash a background color of an input textbox on a graphical user interface (GUI) of the semantic normalizer from white to a first pastel color several times a second until spoken text or typed text is detected by the semantic normalizer;

III) perform the following steps if typed text is detected;

a. setting the semantic normalizer to a typed input mode;

b. setting a color of the typed input circle to a first color;

c. setting the color of a speech input circle to the background color of the GUI;

d. sounding a short audible signal; and

e. displaying typed text in the input textbox, wherein the font color of the displayed typed text is the first color;

IV) perform the following steps if spoken text is detected;

a. setting the semantic normalizer to a speech input mode;

b. setting the color of a speech input circle to a second color;

c. setting the color of a typed input circle to a background color of the GUI;

d. sounding a short audible signal; and

e. displaying spoken text in the input textbox, wherein the font color of the displayed spoken text is the second color;

V) perform the following steps after typed or spoken text has been submitted to the semantic normalizer, software for performing the following steps;

a. setting the color of the speech input circle and the typed input circle to the background color of the GUI;

b. obtaining resulting text from a Predictor Algorithm utilizing parallel hardware of the semantic normalizer;

c. displaying the resulting text in a semantic echo textbox;

d. if the resulting text has been transformed by the semantic normalizer,

i. setting the color of a semantic echo circle to a third color;

ii. sounding a short audible signal; and

iii. setting the font color of the resulting text to the third color;

e. if the semantic normalizer is in speech input mode and the resulting text is syntactically the same as the spoken text,

i. setting the color of the semantic echo circle to the first color; and

ii. setting the font color of the resulting text to the first color;

f. if the semantic normalizer is in typed input mode and the resulting text is syntactically the same as the typed text,

i. setting the color of the semantic echo circle to the second color; and

ii. setting the font color of the resulting text to the second color; and

a learning processor configured to perform the following steps if the semantic normalizer is in learning mode;

a. prompting the user to verify the resulting text;

b. enabling “

Yes,”

“

No,” and

“

Enter Correction”

buttons;

c. setting the color of a circle that is adjacent to a printed question, “

Is This Correct?”

on the GUI to a fourth color; and

d. allowing the user to enter corrections to the resulting text.

2. The apparatus of claim 1, wherein the graphical user interface is further configured to enunciate the resulting text by the semantic normalizer.

3. The apparatus of claim 1, wherein the graphical user interface is further configured to flash the background color of the semantic echo textbox from white to a second pastel color several times a second while the resulting text is being enunciated by the semantic normalizer.

4. The apparatus of claim 3, wherein the first, second, third, and fourth colors are distinct from one another.

5. The apparatus of claim 4, wherein the first, second, third, and fourth colors are green, blue, red and white respectively.