Voice recognition device with larger weights assigned to displayed words of recognition vocabulary

• US 7,076,425 B2
• Filed: 03/05/2002
• Issued: 07/11/2006
• Est. Priority Date: 03/19/2001
• Status: Expired due to Fees

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan Motor Co., Ltd.
• Inventors: Ono, Takeshi, Nakayama, Okihiko
• Primary Examiner(s): Storm, Donald L.
• Application Number:
  US10/087,980
• Publication Number:
  US 20020133338A1
• Time in Patent Office: 1,589 Days
• Field of Search: 704/252, 704/275, 704/276, 704/251, 704/200
• US Class Current: 704/252
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A voice recognition device is provided to improve a recognition rate for objective recognition terms on display. The device includes a voice pickup unit for picking up user'"'"'s voices, a storing unit for storing a plurality of objective recognition terms, a display unit for displaying a designated number of objective recognition terms stored in the storing unit and a voice recognition unit. The voice recognition unit has a weighting section for weighting the objective recognition terms on display more heavily than those not on display, and a calculating section for calculating respective degrees of agreement between the objective recognition terms after the objective recognition terms are weighted and the user'"'"'s voices are picked up by the voice pickup unit. Based on this calculating result of the degrees of agreement, the voice recognition device recognize the user'"'"'s voices.

Claims

1. A voice recognition device comprising:

a voice pickup unit configured to pick up voices of a user;

a memory unit configured to store a plurality of objective recognition terms;

a display unit configured to display a predetermined number of objective recognition terms that are included in the plurality of objective recognition terms stored in the memory unit;

a weighting unit configured to weight the objective recognition terms on the display unit with respective weighted values, each of the respective weighted values being larger than weighted values of the other objective recognition terms that are not displayed on the display unit; and

a calculating unit configured to calculate respective degrees of agreement between the objective recognition terms after being weighted by the weighting unit and the user'"'"'s voices being picked up by the voice pickup unit,

wherein;

the user'"'"'s voices are recognized based on the degrees of agreement calculated by the calculating unit,

the memory unit stores the plurality of objective recognition terms in a prescribed order,

the display unit displays the objective recognition terms in a display area adapted to display the objective recognition terms of a predetermined number in the prescribed order, and

the weighting unit operates to weight the objective recognition terms outside the display area such that each of the weighted values of the objective recognition terms outside the display area is gradually reduced from the weighted values of the objective recognition terms in the display area as a position of a respective objective recognition term outside the display area is apart from the display area.

2. The voice recognition device of claim 1, further comprising a changing unit configured to change contents in the display area, wherein

the weighting unit operates to weight the objective recognition terms in the display area with weighted values, each of the weighted values of the objective recognition terms in the display area is larger than weighted values of the other objective recognition terms outside the display area only when the contents in the display area is changed by the changing unit.

3. The voice recognition device of claim 1, further comprising a changing unit configured to change contents in the display area,

wherein the weighting unit operates to weight the objective recognition terms in the display area with weighted values, each of the weighted values of the objective recognition terms in the display area is larger than weighted values of the other objective recognition terms outside the display area only when a small change in the contents in the display area is carried out after completing a big change in the contents in the display area by the changing unit.

4. The voice recognition device of claim 1, further comprising a changing unit configured to change contents in the display area,

wherein the weighting unit operates to weight the objective recognition terms in the display area in an order of the objective recognition terms that have appeared in the display area as a result of changing the contents in the display area by the changing unit, whereby the latest objective recognition term in the display is weighted with the largest weighted value.

5. The voice recognition device of claim 1, further comprising a changing unit configured to change contents in the display area,

wherein the weighting unit operates to weight the objective recognition terms in the display area with weighted values, each of the weighted values of the objective recognition terms in the display area is larger than weighted values of the other objective recognition terms outside the display area, and further operates to weight each of the objective recognition terms that are arranged outside the display area in a direction to change the contents in the display area, with a weighted value that is reduced from the weighted values of the objective recognition terms in the display area gradually as separating from the display area.

6. A voice recognition device comprising:

a voice pickup unit configured to pick up voices of a user;

a memory unit configured to store a plurality of objective recognition terms;

a display unit configured to display in a display area a predetermined number of objective recognition terms that are included in the plurality of objective recognition terms stored in the memory unit;

a weighting unit configured to weight the objective recognition terms on the display unit with respective weighted values, each of the respective weighted values being larger than weighted values of the other objective recognition terms not displayed on the display unit;

a calculating unit configured to calculate respective degrees of agreement between the objective recognition terms after being weighted by the weighting unit and the user'"'"'s voices being picked up by the voice pickup unit, wherein the users s voices are recognized based on the degrees of agreement calculated by the calculating unit;

an extracting unit configured to extract another predetermined number of objective recognition terms from the objective recognition terms, in an order of respective degrees of agreement, wherein the objective recognition terms extracted by the extracting unit are displayed on the display unit to allow the final objective recognition term desired by the user to be selected; and

a replacing unit configured to replace the objective recognition term having the lowest degree of agreement in the extracted objective recognition terms with the objective recognition term arranged outside the display area having the highest degree of agreement when any one of the objective recognition terms outside the display area is not included in a group of the extracted objective recognition terms extracted by the extracting unit.