Method for Providing Context-Based Correction of Voice Recognition Results

• US 20150269935A1
• Filed: 03/18/2014
• Published: 09/24/2015
• Est. Priority Date: 03/18/2014
• Status: Active Grant

• Current Assignee: Bayerische Motoren Werke AG
• Original Assignee: Bayerische Motoren Werke AG
• Inventors: SUESSENGUTH, Philipp
• Granted Patent: US 9,448,991 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Context-based corrections of voice recognition results are provided by displaying text-based result from a speech-to-text conversion operation on a display screen of an electronic client device. One or more element categories associated with corresponding portions of the text-based result are identified. Graphical icons corresponding to the element categories are also displayed on the display in areas where the corresponding portions of the text-based result are also displayed. A user selection of one of the graphical icons is then detected, and an edit operation is enabled for the portion of the text-based result associated with the selected graphical icon. An updated version of the text-based results is then displayed on the display.

Claims

1. A method for providing context-based corrections of voice recognition results using an electronic client device, the method comprising the acts of:

displaying, by the electronic client device on a display, a text-based result from a speech-to-text conversion operation, wherein the result comprises a plurality of words;

identifying, by the electronic client device, an element category associated with a portion of the text-based result;

displaying, by the electronic client device on the display, a graphical icon corresponding to the element category in an area of the display corresponding to where the portion of the text-based result is also displayed;

detecting a user selection, by the electronic client device, of the graphical icon;

enabling, by the electronic client device and in response to the user selection, an edit operation to be performed on the portion of the text-based result associated with the graphical icon; and

displaying, by the electronic client device on the display, an updated version of the text-based based on said edit operation.

2. The method of claim 1, further comprising the acts of:

storing a plurality of element categories in a memory of the client device; and

storing, in the memory, a plurality of recognized words and phrases corresponding to the plurality of element categories.

3. The method of claim 2, wherein said identifying the element category further comprises the acts:

parsing the plurality of words to determine if at least one of the plurality of recognized words and phrases is contained in the text-based result;

performing a lookup operation of the plurality of element categories using an identified one of the plurality of recognized words and phrases from said parsing; and

identifying said element category from among the plurality of element categories in response to the lookup operation producing a match between one of the plurality of element categories and the identified one of the plurality of recognized words and phrases.

4. The method of claim 1, wherein displaying, by the client device on the display, the graphical icon corresponding to the element category comprises displaying the graphical icon and the portion of the text-based result in an at least partially overlapping manner on the display of the client device.

5. The method of claim 1, wherein detecting the user selection comprises detecting a finger gesture on the display in an area corresponding to where the graphical icon is displayed.

6. The method of claim 1, wherein enabling the edit operation comprises activating an area of the display for text entry, wherein the area containing to where the portion of the text-based result is displayed.

7. The method of claim 6, wherein during the edit operation, the plurality of words of the text-based results that are outside the portion of the text-based result are uneditable.

8. The method of claim 1, further comprising transmitting, by the client device over a network, an electronic message comprising the updated version of the text-based result.

9. An electronic client device configured to enable context-based corrections of voice recognition results, the electronic device comprising:

a display;

a memory containing processor-executable instructions for enabling context-based corrections of voice recognition results; and

a processor electrically coupled to the display and to the memory, the processor configured to execute the processor-executable instructions to;

display, on the display, a text-based result from a speech-to-text conversion operation, wherein the result comprises a plurality of words, identify an element category associated with a portion of the text-based result,

display, on the display, a graphical icon corresponding to the element category in an area of the display corresponding to where the portion of the text-based result is also displayed,

detect a user selection of the graphical icon,

enable, in response to the user selection, an edit operation to be performed on the portion of the text-based result associated with the graphical icon, and

display, on the display, an updated version of the text-based based on said edit operation.

10. The electronic client device of claim 9, wherein the processor is further configured to execute the processor-executable instructions to:

store, in the memory, a plurality of element categories, and

store, in the memory, a plurality of recognized words and phrases corresponding to the plurality of element categories.

11. The electronic client device of claim 10, wherein the processor is configured to execute the processor-executable instructions to identify the element category by further executing processor-executable instructions to:

parse the plurality of words to determine if at least one of the plurality of recognized words and phrases is contained in the text-based result,

perform a lookup operation of the plurality of element categories using an identified one of the plurality of recognized words and phrases from said parsing, and

identify said element category from among the plurality of element categories in response to the lookup operation producing a match between one of the plurality of element categories and the identified one of the plurality of recognized words and phrases.

12. The electronic client device of claim 9, wherein the processor is configured to execute the processor-executable instructions to display the graphical icon by displaying the graphical icon and the portion of the text-based result in an at least partially overlapping manner on the display.

13. The electronic client device of claim 9, wherein the display is a touchscreen display and the processor is further configured to execute the processor-executable instructions to detect the user selection by detecting a finger gesture on the touchscreen display in an area corresponding to where the graphical icon is displayed.

14. The electronic client device of claim 9, wherein the display is a touchscreen display and the processor is further configured to execute the processor-executable instructions to enable the edit operation by activating an area of the touchscreen display for text entry, wherein the area containing to where the portion of the text-based result is displayed.

15. The electronic client device of claim 14, wherein during the edit operation, the plurality of words of the text-based results that are outside the portion of the text-based result are uneditable.

16. The electronic client device of claim 9, wherein the processor is further configured to execute the processor-executable instructions to transmit, over a network, an electronic message comprising the updated version of the text-based result.

17. A computer program product, comprising:

a processor readable medium having processor executable code embodied therein to enable context-based corrections of voice recognition results using an electronic client device, the processor readable medium having;

processor executable program code to display, on a display of the electronic client device, a text-based result from a speech-to-text conversion operation, wherein the result comprises a plurality of words,

processor executable program code to identify an element category associated with a portion of the text-based result,

processor executable program code to display, on the display, a graphical icon corresponding to the element category in an area of the display corresponding to where the portion of the text-based result is also displayed,

processor executable program code to detect a user selection of the graphical icon,

processor executable program code to enable, in response to the user selection, an edit operation to be performed on the portion of the text-based result associated with the graphical icon, and

processor executable program code to display, on the display, an updated version of the text-based based on said edit operation.

18. The computer program product of claim 17, wherein the processor readable medium further includes:

processor executable program code to store, in a memory of the electronic client device, a plurality of element categories; and

processor executable program code to store, in the memory, a plurality of recognized words and phrases corresponding to the plurality of element categories.

19. The computer program product of claim 18, wherein the processor executable program code to identify the element category further comprises:

processor executable program code to parse the plurality of words to determine if at least one of the plurality of recognized words and phrases is contained in the text-based result,

processor executable program code to perform a lookup operation of the plurality of element categories using an identified one of the plurality of recognized words and phrases from said parsing, and

processor executable program code to identify said element category from among the plurality of element categories in response to the lookup operation producing a match between one of the plurality of element categories and the identified one of the plurality of recognized words and phrases.

20. The computer program product of claim 17, wherein the processor executable program code to display the graphical icon further comprises processor executable program code to display the graphical icon and the portion of the text-based result in an at least partially overlapping manner on the display.

21. The computer program product of claim 17, wherein the display is a touchscreen display and wherein the processor executable program code to detect the user selection further comprises processor executable program code to detect a finger gesture on the touchscreen display in an area corresponding to where the graphical icon is displayed.

22. The computer program product of claim 17, wherein the display is a touchscreen display and wherein the processor executable program code to enable the edit operation further comprises processor executable program code to activate an area of the touchscreen display for text entry, wherein the area containing to where the portion of the text-based result is displayed.

23. The computer program product of claim 22, wherein during the edit operation, the plurality of words of the text-based results that are outside the portion of the text-based result are uneditable.

24. The computer program product of claim 17, wherein the processor readable medium further includes processor executable program code to transmit, over a network, an electronic message comprising the updated version of the text-based result.