Speech recognition disambiguation on mobile devices

• US 8,224,656 B2
• Filed: 03/14/2008
• Issued: 07/17/2012
• Est. Priority Date: 03/14/2008
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Scholz, Oliver, Chambers, Robert L., Odell, Julian James
• Primary Examiner(s): Harper, Vincent P
• Application Number:
  US12/049,243
• Publication Number:
  US 20090234647A1
• Time in Patent Office: 1,586 Days
• Field of Search: 704/276, 704/251, 704/270, 704/270.1
• US Class Current: 704/276
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A method, program storage device and mobile device provide speech disambiguation. Audio for speech recognition processing is transmitted by the mobile device. Results representing alternates identified to match the transmitted audio are received. The alternates are displayed in a disambiguation dialog screen for making corrections to the alternates. Corrections are made to the alternates using the disambiguation dialog screen until a correct result is displayed. The correct result is selected. Content associated with the selected correct result is received in parallel with the receiving of the results representing alternates identified to match the transmitted audio.

Claims

1. A method for providing speech disambiguation on a mobile device, comprising:

transmitting audio for speech recognition processing;

receiving results representing alternates identified to match the transmitted audio;

caching the received results, the cache utilizing a least recently used (LRU) algorithm to handle cache overflow;

searching for content associated with the received results;

displaying the alternates in a disambiguation dialog screen for making corrections to the alternates;

making corrections to the alternates using the disambiguation dialog screen until a correct result is displayed, wherein the correction to the alternates using the disambiguation dialog screen and the receiving of the results representing the alternates are performed in parallel to the search for the content associated with the received results;

selecting the correct result;

upon selecting the correct result, mapping the correct result to one of the received results in the cache, the cache deleting unselected results prior to utilizing the LRU; and

immediately displaying a matching associated search result.

2. The method of claim 1, wherein the displaying the alternates in a disambiguation dialog screen comprises displaying a text box showing a current alternate and an alternates box for displaying a list of additional alternates.

3. The method of claim 2, wherein the displaying a text box showing a current alternate comprises displaying an alternate ranked as being a most likely match to the transmitted audio.

4. The method of claim 1, wherein the making corrections to the alternates using the disambiguation dialog screen further comprises editing a current alternate in a displayed text box.

5. The method of claim 4, wherein the editing comprises entering text.

6. The method of claim 4, wherein the editing comprises selecting displayed text and replacing the selected text using speech.

7. The method of claim 1, wherein the making corrections to the alternates using the disambiguation dialog screen further comprises selecting an alternate from an alternates box.

8. The method of claim 1 further comprising displaying content associated with the selected correct result and received in parallel with the receiving of the results representing alternates identified to match the transmitted audio.

9. A computer-readable device that stores a set of instructions which when executed performs a method for providing speech disambiguation on a mobile device, the method executed by the set of instructions comprising:

transmitting audio for speech recognition processing;

receiving results representing alternates identified to match the transmitted audio;

caching the received results, the cache utilizing a least recently used (LRU) algorithm to handle cache overflow;

searching for content associated with the received results;

displaying the alternates in a disambiguation dialog screen for making corrections to the alternates;

making corrections to the alternates using the disambiguation dialog screen until a correct result is displayed, wherein the correction to the alternates using the disambiguation dialog screen and the receiving of the results representing the alternates are performed in parallel to the search for the content associated with the received results;

selecting the correct result;

upon selecting the correct result, mapping the correct result to one of the received results in the cache, the cache deleting unselected results prior to utilizing the LRU; and

immediately displaying a matching associated search result.

10. The computer-readable device of claim 9, wherein the displaying the alternates in a disambiguation dialog screen comprises displaying a text box showing a current alternate and an alternates box for displaying a list of additional alternates.

11. The computer-readable device of claim 10, wherein the displaying a text box showing a current alternate comprises displaying an alternate ranked as being a most likely match to the transmitted audio.

12. The computer-readable device of claim 9, wherein the making corrections to the alternates using the disambiguation dialog screen further comprises editing a current alternate in a displayed text box.

13. The computer-readable device of claim 12, wherein the editing comprises entering text.

14. The computer-readable device of claim 12, wherein the editing comprises selecting displayed text and replacing the selected text using speech.

15. The computer-readable device of claim 9, wherein the making corrections to the alternates using the disambiguation dialog screen further comprises selecting an alternate from an alternates box.

16. The computer-readable device of claim 9 further comprising displaying content associated with the selected correct result and received in parallel with the receiving of the results representing alternates identified to match the transmitted audio.

17. A mobile device, comprising:

a memory device for storing executable program code; and

a processor, functionally coupled to the memory device, the processor being responsive to computer-executable instructions contained in the program code and operative to;

transmit audio for speech recognition processing;

receive results representing alternates identified to match the transmitted audio;

cache the received results, the cache utilizing a least recently used (LRU) algorithm to handle cache overflow;

search for content associated with the received results;

display the alternates in a disambiguation dialog screen for making corrections to the alternates;

make corrections to the alternates using the disambiguation dialog screen until a correct result is displayed, wherein the correction to the alternates using the disambiguation dialog screen and the receiving of the results representing the alternates are performed in parallel to the search for the content associated with the received results;

select the correct result;

upon selecting the correct result, map the correct result to one of the received results in the cache, the cache deleting unselected results prior to utilizing the LRU; and

immediately display a matching associated search result.

18. The mobile device of claim 17, wherein the processor, in displaying the alternates in a disambiguation dialog screen, is operative to display a text box showing a current alternate and an alternates box for displaying a list of additional alternates.

19. The mobile device of claim 18, wherein the processor, in displaying a text box showing a current alternate, is operative to display an alternate ranked as being a most likely match to the transmitted audio.

20. The mobile device of claim 17, wherein the processor, in making corrections to the alternates using the disambiguation dialog screen, is further operative to edit a current alternate in a displayed text box.