Method and apparatus for displaying speech recognition results

• US 6,993,482 B2
• Filed: 12/18/2002
• Issued: 01/31/2006
• Est. Priority Date: 12/18/2002
• Status: Expired due to Fees

• Current Assignee: Motorola Mobility, Inc. (Lenovo Group Ltd.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Ahlenius, Mark T.
• Primary Examiner(s): Knepper, David D.
• Application Number:
  US10/323,500
• Publication Number:
  US 20040122666A1
• Time in Patent Office: 1,140 Days
• Field of Search: 704231-246, 704/270, 704/275, 704/276
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

The method and apparatus for displaying speech recognition results includes a recognition filter (102) that receives a recognition result list (106) which includes a plurality of speech recognized terms (122), wherein each speech recognized term (122) has a term-specific recognition confidence value (124). The recognition filter (102) generates a modified recognition result list (108) that includes one or more speech recognized terms having term-specific recognition confidence values. The method and apparatus also includes a display generator (104) that receives the modified recognition result list (108) and generates a graphical recognition result list (110). The graphical recognition result list (110) includes speech recognized terms and a non-alphanumeric symbol as a graphical representation (274) of the term-specific recognition confidence value (128) and a speech recognized term (126).

Claims

1. A portable device comprising:

a recognition filter that receives a recognition result list that includes a plurality of speech recognized terms, each speech recognized term has a term-specific recognition confidence value, such that the recognition filter generates a modified recognition result list including the plurality of speech recognized terms having the term-specific recognition confidence value associated therewith; and

a display generator coupled to the recognition filter such that the display generator receives the modified recognition result list and generates a graphical recognition result list, wherein the graphical recognition result list includes the plurality of speech recognized terms and, for each of the plurality of speech recognized terms, a graphical representation of the corresponding term-specific recognition confidence value, wherein each graphical representation is a non-alphanumeric symbol.

2. The portable device of claim 1 further comprising:

a display device coupled to the display generator such that the display device receives the graphical recognition result list and displays the graphical recognition result list.

3. The portable device of claim 2 further comprising:

an audio input device capable of receiving an audio input, wherein the audio input device is operably coupled to a speech recognition engine such that the audio input may be provided to the speech recognition engine.

4. The portable device of claim 3 wherein the speech recognition generates the recognition result list.

5. The portable device of claim 3 wherein the speech recognition engine is at least one of the following:

an embedded speech recognition engine and an external speech recognition engine.

6. The portable device of claim 1 wherein the graphical representation includes at least one of the following:

a plurality of lines having varying colors, a plurality of lines having varying widths, a plurality of lines having varying spacing therebetween, and a geometrical element having at least one indicator line disposed therein.

7. The portable device of claim 6 wherein the display generator receives a preference signal that indicates the graphical representation for the graphical recognition result list.

8. The portable device of claim 1 wherein the recognition filter receives a maximum confidence threshold value and a minimum confidence threshold value such that the modified recognition result list is generated in view of at least one of:

the maximum confidence threshold value and the minimum confidence threshold value.

9. The portable device of claim 1 wherein the recognition filter receives a weighting indicator capable of being applied to each of the plurality of speech recognized terms to adjust the term-specific recognition confidence values.

10. The portable device of claim 1 wherein the display generator separately displays a) the plurality of speech recognized terms and b) the corresponding non-alphanumeric symbols.

11. A method for displaying speech recognition results comprising:

receiving a recognition result list including a plurality of speech recognized terms, wherein each of the speech recognized terms has a term-specific confidence value;

generating a graphical representation of the plurality of speech recognized terms and the term-specific confidence value for each of the speech recognized terms such that the graphical representation includes at least one non-alphanumeric symbol that indicates each of the at least one term-specific confidence values; and

displaying the graphical representation of the plurality of speech recognized terms and the corresponding term-specific confidence values.

12. The method of claim 11 further includes, prior to generating graphical representation of the plurality of speech recognized terms and the term-specific confidence value:

comparing the term-specific confidence values for each of the speech recognized terms to a minimum threshold value and discarding all of the speech recognized terms having the term-specific confidence value below the minimum threshold value;

comparing the term-specific confidence values for each of the speech recognized terms to a maximum threshold value and discarding all of the speech recognized terms having the term-specific confidence values below the maximum threshold value.

13. The method of claim 12 further comprising:

for each of the speech recognized terms of the graphical recognition list, receiving a weighting factor.

14. The method of claim 13 wherein the weighting factors are received from at least one of the following:

a memory and an executable application.

15. The apparatus of claim 14 wherein the display generator and the display device are disposed within a wireless device.

16. The method of claim 11, wherein the graphical representation includes at least one of the following:

a plurality of lines having varying colors, a plurality of lines having varying widths, a plurality of lines having varying spacing therebetween, and a geometrical element having at least one indicator line disposed therein.

17. An apparatus for displaying speech recognition results comprising:

a recognition filter that receives a recognition result list, wherein the recognition result list includes a plurality of speech recognized terms, each term having a term-specific recognition confidence value, such that the recognition filter generates a modified recognition result list including the plurality of speech recognized terms having the term-specific recognition confidence value associated therewith;

a display generator coupled to the recognition filter such that the recognition display generator receives the modified recognition result list and generates a graphical recognition result list, wherein the graphical recognition result list includes the plurality of speech recognized terms and a corresponding graphical representation of the term-specific recognition confidence values, wherein the graphical representation includes a non-alpha numeric symbol that indicates each of the at least one term-specific confidence values; and

a display device coupled to the display generator such that the display device receives the graphical recognition result list and displays the graphical recognition result list.

18. The apparatus of claim 17 further comprising:

an audio input device capable of receiving an audio input, wherein the audio input device is operably coupled to a speech recognition engine such that the audio input may be provided to the speech recognition engine.

19. The apparatus of claim 18 wherein the recognition result list is generated by at least one of the following:

an embedded speech recognition engine and an external speech recognition engine.

20. The apparatus of claim 17 wherein the graphical representation includes at least one of the following:

a plurality of lines having varying colors, a plurality of lines having varying widths, a plurality of lines having varying spacing therebetween, and a geometrical element having at least one indicators lines disposed therein.

21. The apparatus of claim 17 further comprising:

the display generator receives a preference signal that indicates the graphical representation for the graphical recognition result list;

the recognition filter receives a maximum confidence threshold value and a minimum confidence threshold value such that the modified recognition result list is generated in view of at least one of;

the maximum confidence threshold value and the minimum confidence threshold value; and

the recognition filter receives a weighting indicator capable of being applied to each of the plurality of speech recognized terms to adjust the term-specific recognition confidence values.

22. An apparatus for display speech recognition results comprising:

a memory storing executable instructions; and

a processor capable of receiving the executable instructions, such that the processor, in response to the executable instructions;

receives a recognition result list including a plurality of speech recognized terms, wherein each of the speech recognized terms has a term-specific confidence value;

generates a graphical representation of the plurality of speech recognized terms and the term-specific confidence values for each of the at least one speech recognized terms such that the graphical representation includes at least one non-alphanumeric symbol that indicates each of the term-specific confidence values; and

displays the graphical representation of the plurality of speech recognized terms and the term-specific confidence value.

23. The apparatus of claim 22 wherein the processor, in response to the executable instructions, prior to generating a graphical representation of the plurality of speech recognized terms and the term-specific confidence values:

compares the term-specific confidence values for each of the speech recognized terms to a minimum threshold value and discarding all of the speech recognized terms having the term-specific confidence value below the minimum threshold value;

compares the term-specific confidence values for each of the speech recognized terms to a maximum threshold value and discarding all of the speech recognized terms having the term-specific confidence values below the maximum threshold value.

24. The apparatus of claim 22 wherein the graphical representation includes at least one of the following:

a plurality of lines having varying colors, a plurality of lines having varying widths, a plurality of lines having varying spacing therebetween, and a geometrical element having at least one indicator line disposed therein.

25. An apparatus for displaying speech recognition results comprising:

a recognition filter that receives a recognition result list, wherein the recognition result list includes a plurality of speech recognized terms, each term having a term-specific recognition confidence value, such that the recognition filter generates a modified recognition result list including the plurality of speech recognized terms having the term-specific recognition confidence value associated therewith;

a display generator coupled to the recognition filter such that the recognition display generator receives the modified recognition result list and generates an audible recognition result list, wherein the audible recognition result list includes the plurality of speech recognized terms and an audible representation of the corresponding term-specific recognition confidence values; and

a display device coupled to the display generator such that the display device receives the audible recognition result list and outputs the audible recognition result list.

26. The apparatus of claim 25 wherein audible representation includes at least one of the following:

pitch adjustment, volume adjustment, pronunciation speed adjustment and adjustment of an at least one tone.