Speech recognition method and system

• US 20060167684A1
• Filed: 04/22/2005
• Published: 07/27/2006
• Est. Priority Date: 01/24/2005
• Status: Abandoned Application

• Current Assignee: Delta Electronics Incorporated
• Original Assignee: Delta Electronics Incorporated
• Inventors: Wang, Jui-Chang, Tsai, Ching-Ho
• Application Number:
  US11/112,212
• Publication Number:
  US 20060167684A1
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

In the present invention, a speech recognition method is provided. The speech recognition method includes steps of (a) receiving a speech from a user and recognizing the speech for generating a plurality of recognition results, (b) displaying the recognition results for the user to lock correct values in the recognition results, (c) determining whether the correct values are sufficient for searching a database, (d) saving the correct values as known values to narrow the recognition range and repeating step (a) to step (c) when the correct values are insufficient for searching the database, and (e) searching the database for a desired datum based on the correct values when the correct values are sufficient.

Claims

1. A speech recognition method, comprising steps of:

(a) receiving a speech from a user and recognizing said speech for generating a plurality of recognition results;

(b) displaying said recognition results for said user to lock correct values in said recognition results;

(c) determining whether said correct values are sufficient for searching a database;

(d) saving said correct values as known values to narrow the recognition range and repeating step (a) to step (c) when said correct values are insufficient for searching said database; and

(e) searching said database for a desired datum based on said correct values when said correct values are sufficient.

2. The speech recognition method as claimed in claim 1, wherein said recognition results are shown on a displaying device.

3. The speech recognition method as claimed in claim 2, wherein said displaying device is a touch screen.

4. The speech recognition method as claimed in claim 1, wherein said correct values in said recognition results are locked by said user with a locking device.

5. The speech recognition method as claimed in claim 4, wherein said locking device is one selected from a group consisting of a button, said touch screen and a remote controller.

6. The speech recognition method as claimed in claim 1, wherein said known values are stored in a storage device.

7. The speech recognition method as claimed in claim 6, wherein said storage device is a register.

8. The speech recognition method as claimed in claim 1, wherein said database is one selected from a group consisting of a memory, a flash disk, a hard disk and a remote server.

9. The speech recognition method as claimed in claim 1, further comprising a step of re-recognizing said speech from said user when a part of said correct values is known.

10. A speech recognition method, comprising steps of:

(a) displaying a plurality of fields on a displaying device, wherein each of said field corresponds to an attribute;

(b) inputting a speech by a user based on said attribute;

(c) recognizing said speech to generate a plurality of recognition results;

(d) displaying said recognition results in corresponding fields for said user to lock correct values in said recognition results with a locking device;

(e) determining whether said correct values are sufficient for searching a database;

(f) saving said correct values as know values to narrow the recognition range and repeating step (b) to step (e) when said correct values are insufficient for searching said database; and

(g) searching said database for a desired datum based on said correct values when said correct values are sufficient.

11. The speech recognition method as claimed in claim 10, further comprising a step of re-recognizing said speech from said user when a part of said correct values is known.

12. The speech recognition method as claimed in claim 10, further comprising a step of automatically searching for said desired datum without completely filling said fields.

13. A speech recognition system, comprising:

a speech input device for receiving a speech from a user;

a speech recognition device connected to said speech input device for recognizing said speech to generate a plurality of recognition results;

a displaying device connected to said speech recognition device for displaying said recognition results;

a locking device connected to said displaying device for said user to lock correct values in said recognition results;

a storage device for saving said correct values as known values; and

a database for storing a desired datum to be searched according to said correct values.

14. The speech recognition system as claimed in claim 13, wherein said displaying device is a touch screen.

15. The speech recognition system as claimed in claim 14, wherein said locking device is one selected from a group consisting of a button, said touch screen and a remote controller.

16. The speech recognition system as claimed in claim 13, wherein said storage device is a register.

17. The speech recognition system as claimed in claim 13, wherein said correct values are saved as said known values via said storage device when said correct values are insufficient.

18. The speech recognition system as claimed in claim 13, wherein said database is one selected from a group consisting of a memory, a flash disk, a hard disk and a remote server.

19. The speech recognition system as claimed in claim 13, wherein said desired datum is searched from said database based on said correct values when said correct values are sufficient for searching said database.

20. A speech recognition method, comprising steps of:

(a) receiving a speech from a user and recognizing said speech for generating a plurality of recognition results;

(b) displaying one of said recognition results for said user to confirm/correct said recognition result;

(c) repeating step (b) until all of said recognition results are confirmed/corrected by said user; and

(d) searching for a desired datum based on said confirmed/corrected recognition results.

21. The speech recognition method as claimed in claim 20, wherein said recognition results are shown one by one on a specific region of a displaying device.

22. The speech recognition method as claimed in claim 21, wherein said recognition results are shown as an ‘

attribute-value’

format.

23. The speech recognition method as claimed in claim 22, wherein said attributes and said values are confirmed/corrected one by one by said user via a control device.

24. The speech recognition method as claimed in claim 23, wherein said control device is one selected from a group consisting of a keypad, a remote controller and a personal digital assistant.

25. The speech recognition method as claimed in claim 24, wherein said keypad comprises a recording/playing button, an accepting button, a rejecting button, an attribute-correcting button and a value-correcting button.

26. The speech recognition method as claimed in claim 23, further comprising a step of searching for said desired datum based on said confirmed/corrected attributes and said confirmed/corrected values after one of said attributes and said values is confirmed/corrected.

27. The speech recognition method as claimed in claim 21, further comprising a step of determining whether said attributes and said values which are not confirmed/corrected need to be confirmed/corrected continuously.

28. A speech recognition system, comprising:

an input device for receiving a speech from a user;

a speech recognition understanding device connected to said input device for generating a plurality of recognition results in response to said speech;

a confirmation/correction module connected to said speech recognition understanding device for confirming/correcting said recognition results;

a displaying device connected to said confirmation/correction module for displaying said recognition results one by one on a specific region thereof;

a control device connected to said confirmation/correction module for said user to confirm/correct said recognition results; and

a search module connected to said confirmation/correction module for searching for a desired datum based on said confirmed/corrected recognition results.

29. The speech recognition system as claimed in claim 28, further comprising a storage/receiving device for storing said datum.

30. The speech recognition system as claimed in claim 29, wherein said datum is one of a digital datum and a video program.

31. The speech recognition system as claimed in claim 28, wherein said input device is a microphone.

32. The speech recognition system as claimed in claim 28, wherein said speech recognition understanding device comprises a speech recognition device and a language understanding device.

33. The speech recognition system as claimed in claim 32, wherein said speech recognition device performs a speech recognition based on a lexicon.

34. The speech recognition system as claimed in claim 32, wherein said language understanding device performs a language understanding based on a grammar rule.

35. The speech recognition system as claimed in claim 28, wherein said recognition results are shown as an ‘

attribute-value’

format.

36. The speech recognition system as claimed in claim 28, wherein said confirmation/correction module is an interactive meaning confirmation/correction software.

37. The speech recognition system as claimed in claim 28, wherein said control device is one selected from a group consisting of a keypad, a remote controller and a personal digital assistant.

38. The speech recognition system as claimed in claim 37, wherein said keypad comprises a recording/playing button, an accepting button, a rejecting button, an attribute-correcting button and a value-correcting button.

39. The speech recognition system as claimed in claim 28, wherein said search unit is a search software.

40. A speech recognition method, comprising steps of:

(a) receiving a speech from a user and recognizing said speech for generating a plurality of recognition results;

(b) displaying said recognition results for said user to confirm/correct said recognition results; and

(c) searching for a desired datum based on said confirmed/corrected recognition results.

41. The speech recognition method as claimed in claim 40, wherein said recognition results are shown simultaneously.

42. The speech recognition method as claimed in claim 40, wherein said recognition results are shown one by one.

43. The speech recognition method as claimed in claim 40, wherein said step (b) is performed by receiving a next speech from said user.

44. The speech recognition method as claimed in claim 40, wherein said step (b) is performed by means of a control device.