In-vehicle apparatus

• US 8,694,323 B2
• Filed: 07/12/2007
• Issued: 04/08/2014
• Est. Priority Date: 09/04/2006
• Status: Active Grant

• Current Assignee: Xanavi Informatics Corporation (Hitachi, Ltd.)
• Original Assignee: Xanavi Informatics Corporation (Hitachi, Ltd.)
• Inventors: Hataoka, Nobuo, Kokubo, Hiroaki, Homma, Takeshi, Sagawa, Hirohiko, Takahashi, Hisashi
• Primary Examiner(s): JACKSON, JAKIEDA R
• Application Number:
  US11/826,161
• Publication Number:
  US 20080059199A1
• Time in Patent Office: 2,462 Days
• Field of Search: 704/275
• US Class Current: 704/275
• CPC Class Codes: G01C 21/36 Input/output arrangements for on-board computers
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The present invention provides a technique, by speech input, to specify a location, even when a name or the like of the location is not accurately known, while driving. An in-vehicle apparatus mounted in a vehicle has a speech recognition function, and stores information shown on a signboard and a noun substitute in storage. If speech inputted from a speech input device includes a noun substitute and further includes at least a part of the information shown on the signboard, a response is decided according to the information shown on the signboard, and the decided response is outputted from an output device.

Claims

1. An in-vehicle apparatus mounted in a vehicle, connected to a communication device, and provided with a speech recognition function, comprising,

a signboard information data store that stores a plurality of signboard information items each including a signboard position of a signboard located at a position so as to be visible from a road on which the vehicle is driving and a character string shown on the signboard,

a signboard information acquiring component that automatically obtains a signboard information item for a signboard including the signboard position of the signboard located at a position so as to be visible from the road where the vehicle is driving and the character string shown on the signboard and, upon obtaining the signboard information item, stores the obtained signboard information item in the signboard information data store,

an image capturing component that controls a camera in accordance with information indicating a line-of-sight of a user and extracts, from an image taken by the camera for a signboard captured in the image, a signboard position of the signboard indicating a location visible from the road on which the vehicle is driving where the image is taken and a character string shown on the signboard, and stores a signboard information item for the signboard that includes the extracted signboard position and the extracted character string in the signboard information data store,

a noun substitute data store that stores a noun substitute,

a speech processing component to which speech is inputted, the speech processing component, upon determining that the inputted speech includes the noun substitute, selects, comparing the inputted speech with each of the signboard information items stored in the signboard information data store, a signboard information item from the signboard information data store for which the signboard position is within a predetermined range from a current position of the vehicle and for which at least a part of the character string matches a part of the speech inputted, and determines a response for confirming the character string being included in the selected signboard information item, and

an output unit that provides an output indicating the response.

2. The in-vehicle apparatus according to claim 1, wherein, the communication device is a beacon transmitter.

3. The in-vehicle apparatus according to claim 1, wherein, the communication device is an RFID installed on the signboard, and the signboard information acquiring component uses a reader to obtain the signboard information item including the signboard position of the signboard located at a position so as to be visible from the road on which the vehicle is driving, and character string shown on the signboard.

4. The in-vehicle apparatus according to claim 1, wherein, the noun substitute data store associates and stores the noun substitute, and a relative azimuth for a traveling direction of the vehicle, when the noun substitute is included, and when the noun substitute is included in the speech inputted by the speech processing component, the speech processing component reads the relative azimuth associated with the noun substitute from the noun substitute data store, selects, from each of the signboard information items stored in the signboard information data store, a signboard information item for which the signboard position is within a predetermined range from the current position of the vehicle in the relative azimuth read, and for which at least a part of the character string matches a part of the speech inputted, and determines a response for confirming the character string being included in the selected signboard information item.