VOICE COMMAND RECOGNITION METHOD AND RELATED ELECTRONIC DEVICE AND COMPUTER-READABLE MEDIUM

• US 20130218573A1
• Filed: 02/21/2012
• Published: 08/22/2013
• Est. Priority Date: 02/21/2012
• Status: Active Grant

• Current Assignee: MediaTek, Inc.
• Original Assignee: MediaTek, Inc.
• Inventors: Cheng, Yiou-Wen, Sun, Liang-Che, Hsu, Chao-Ling, Tsao, Hsi-Kang, Lin, Jyh-Horng
• Granted Patent: US 9,691,381 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

An electronic device for browsing a document is disclosed. The document being browsed includes a plurality of command-associated text strings. First, a text string selector of the electronic device selects a plurality of candidate text strings from the command-associated text strings. Afterward, an acoustic string provider of the electronic device prepares a candidate acoustic string for each of the candidate text strings. Thereafter, a microphone of the electronic device receives a voice command. Next, a speech recognizer of the electronic device searches the candidate acoustic strings for a target acoustic string that matches the voice command, wherein the target acoustic string corresponds to a target text string of the candidate text strings. Finally, a document browser of the electronic device executes a command associated with the target text string.

Claims

1. A voice command recognition method, comprising:

selecting a plurality of candidate text strings from a plurality of command-associated text strings of a document being browsed;

preparing a candidate acoustic string for each of the candidate text strings;

receiving a voice command;

searching the candidate acoustic strings for a target acoustic string that matches the voice command, the target acoustic string corresponding to a target text string of the candidate text strings; and

executing a command associated with the target text string.

2. The method of claim 1, wherein the step of preparation comprises:

transforming each of the candidate text strings into a candidate acoustic string that represents the pronunciation of the corresponding candidate text string.

3. The method of claim 1, wherein each of the candidate acoustic strings represents the pronunciation of the sequence of a corresponding candidate text string among the plurality of candidate text strings.

4. The method of claim 1, wherein each of the candidate acoustic strings represents the pronunciation of a symbol additionally displayed for a corresponding candidate text string.

5. The method of claim 1, wherein the step of selection comprises:

selecting the candidate text strings from a displayed region of the document.

6. The method of claim 1, wherein the step of selection comprises:

selecting the candidate text strings from a region specified by a user browsing the document.

7. The method of claim 1, wherein the step of selection comprises:

selecting the candidate text strings from a gazed region of the document.

8. The method of claim 1, wherein the step of selection comprises:

selecting the candidate text strings from a gesture-specified region of the document.

9. The method of claim 1, wherein the step of selection comprises:

selecting the candidate text strings from a subordinate level of a parent object specified by a user browsing the document.

10. The method of claim 1, wherein each of the selected candidate text strings has a portion that is similar to a partial voice command received.

11. An electronic device, comprising:

a text string selector, configured to select a plurality of candidate text strings from a plurality of command-associated text strings of a document being browsed;

an acoustic string provider, configured to prepare a candidate acoustic string for each of the candidate text strings;

a microphone, configured to receive a voice command; and

a speech recognizer, configured to search the candidate acoustic strings for a target acoustic string that matches the voice command, the target acoustic string corresponding to a target text string of the candidate text strings;

wherein the electronic device is configured to execute a command associated with the target text string.

12. The electronic device of claim 11, wherein the acoustic string provider is configured to transform each of the candidate text strings into a candidate acoustic string that represents the pronunciation of the corresponding candidate text string.

13. The electronic device of claim 11, wherein each of the candidate acoustic strings represents the pronunciation of the sequence of a corresponding candidate text string among the plurality of candidate text strings.

14. The electronic device of claim 11, wherein each of the candidate acoustic strings represents the pronunciation of a symbol additionally displayed for a corresponding candidate text string.

15. The electronic device of claim 11, wherein the text string selector is configured to select the candidate text strings from a displayed region of the document.

16. The electronic device of claim 11, wherein the text string selector is configured to select the candidate text strings from a gazed region of the document, and the electronic device further comprises an eye tracker configured to assist in defining the gazed region by tracking a user'"'"'s eyes.

17. The electronic device of claim 11, wherein the text string selector is configured to select the candidate text strings from a gesture-specified region of the document, and the electronic device further comprises a gesture detector configured to assist in defining the gesture-specified region by detecting a user'"'"'s gestures.

18. A computer-readable medium storing at least one computer program which, when executed by an electronic device, causes the electronic device to perform operations comprising:

selecting a plurality of candidate text strings from a plurality of command-associated text strings of a document being browsed;

preparing a candidate acoustic string for each of the candidate text strings;

receiving a voice command;

searching the candidate acoustic strings for a target acoustic string that matches the voice command, the target acoustic string corresponding to a target text string of the candidate text strings; and

executing a command associated with the target text string.

19. The computer-readable medium of claim 18, wherein the operation of preparation comprises:

transforming each of the candidate text strings into a candidate acoustic string that represents the pronunciation of the corresponding candidate text string.

20. The computer-readable medium of claim 18, wherein the operation of preparation comprises:

transforming each of the candidate text strings into a candidate acoustic string that represents the pronunciation of a symbol additionally displayed for a corresponding candidate text string.