Speech recognition apparatus, navigation apparatus including a speech recognition apparatus, and speech recognition method

• US 20070033043A1
• Filed: 07/06/2006
• Published: 02/08/2007
• Est. Priority Date: 07/08/2005
• Status: Active Grant

• Current Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Original Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Inventors: Hyakumoto, Toshiyuki
• Granted Patent: US 8,428,951 B2
• Time in Patent Office: Days
• US Class Current: 704/255
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A speech recognition apparatus includes a speech recognition dictionary and a speech recognition unit. The speech recognition dictionary includes comparison data used to recognize a voice input. The speech recognition unit is adapted to calculate the score for each comparison data by comparing voice input data generated based on the voice input with each comparison data, recognize the voice input based on the score, and produce the recognition result of the voice input. The speech recognition apparatus further includes data indicating score weights associated with particular comparison data, used to weight the scores calculated for the particular comparison data. After the score is calculated for each comparison data, the score weights are added to the scores of the particular comparison data, and the voice input is recognized based on total scores including the added score weights.

Claims

1. A speech recognition apparatus comprising:

a speech recognition dictionary including comparison data for use in recognition of a voice input;

a speech recognition unit adapted to calculate a matching degree by comparing voice input data generated based on the voice input with the comparison data, recognize the voice input based on the matching degree, and produce the recognition result of the voice input; and

one or more addition data which are associated with one or more particular comparison data for use in weighting the matching degree.

2. The apparatus according to claim 1, wherein the speech recognition unit selects one or more comparison data as candidates for the recognition result for the voice input based on the matching degree calculated for each comparison data;

adds the addition data associated with the one or more particular comparison data to the respective matching degrees calculated for the particular one or more comparison data; and

recognizes the voice input based on new matching degrees obtained as a result of the addition of the addition data.

3. The apparatus according to claim 1, wherein the speech recognition dictionary includes the addition data.

4. The apparatus according to claim 1, wherein the comparison data include the addition data.

5. The apparatus according to claim 1, wherein the addition data are associated with a configurational condition in which a voice input is accepted.

6. The apparatus according to claim 5, wherein a plurality of addition data are associated with each of the one or more particular comparison data, and the plurality of addition data are associated with respective configurational conditions in which the voice input can be accepted.

7. The apparatus according to claim 6, wherein a configurational condition in which the voice input can be accepted is a configurational condition in which an electronic device is operably connected to the speech recognition apparatus, and the operation of the electronic device is controlled by the voice input.

8. A navigation apparatus to which an electronic device is operably connected and which comprises the speech recognition apparatus according to claim 7, wherein the configurational condition in which the operation of the electronic device is controlled by the voice input is an operation mode selected for the electronic device.

9. The apparatus according to claim 8, wherein, in a state in which the electronic device is being used in a particular operation mode, comparison data other than the particular comparison data corresponding to the addition data associated with the operation mode in which the electronic device is currently being used are removed from the comparison data selected by the speech recognition unit as recognition candidates

10. The apparatus according to claim 5, wherein when the matching degree of first comparison data calculated for a voice input and the matching degree of second comparison data calculated for the same voice input both satisfy a predetermined matching condition, if the first comparison data is associated with the configurational condition in which the voice input is accepted, the addition data associated with the first comparison data is assigned a greater weight than the addition data associated with the second comparison data.

11. A navigation apparatus including a controller adapted to display an operation control screen on a display and also including the speech recognition apparatus according to claim 5, wherein the configurational condition in which the voice input is accepted is the operation control screen displayed by the controller.

12. The apparatus according to claim 11, wherein comparison data other than the particular comparison data corresponding to addition data associated with an operation control screen currently being displayed are removed from the comparison data selected by the speech recognition unit as recognition candidates.

13. The apparatus according to claim 1, wherein the weight of the addition data varies depending on the comparison data to which the addition data is associated.

14. The apparatus according to claim 13, wherein the shorter the voice input to be recognized using the comparison data, the greater the weight assigned to the addition data.

15. The apparatus according to claim 1, wherein only comparison data used to recognize a voice input of an operation command is assigned the addition data.

16. The apparatus according to claim 15, wherein comparison data other than the comparison data used to recognize the voice input of the operation command are removed from the comparison data selected by the speech recognition unit as recognition candidates.

17. A method for speech recognition comprising:

calculating the matching degree of each of a plurality of comparison data used to recognize voice inputs with respect to a voice input;

adding addition data to the calculated matching degree for one or more particular comparison data associated with addition data to weight the matching degree; and

recognizing the voice input based on the new matching degrees obtained as a result of the addition of the addition data.

18. The method according to claim 17, wherein the addition data are associated with a configurational condition in which a voice input can be accepted.

19. The method according to claim 18, wherein a plurality of addition data are associated with the one or more particular comparison data;

and the plurality of different addition data are associated with respective configurational conditions in which the voice input can be accepted.

20. The method according to claim 19, wherein a configurational condition in which the voice input is accepted is a configurational condition in which an electronic device is operably connected to the speech recognition apparatus and the operation of the electronic device is controlled by voice input.