KR970022962A - Voice recognition device, voice recognition method, map display device, map display method, navigation device, navigation method and car - Google Patents

Abstract

Voice processing for recognizing a predetermined voice such as a place name from the voice signal input to the microphone 11 is performed by the voice processing unit 14 on the basis of the operation of the operation means 18. If a map display or the like based on the recognized name is performed, an incorrect reading manner and a name that tends to be wrong may be recognized or recognized. Therefore, the advanced operation of the navigation device can be performed simply without disturbing the driving of the vehicle.

Description

Voice recognition device, voice recognition method, map display device, map display method, navigation device, navigation method and car

Since this is an open matter, no full text was included.

1 is a perspective view showing a state in which the device of one embodiment of the present invention is assembled to a vehicle.

2 is a perspective view showing the vicinity of a driver's seat when the device of one embodiment is assembled to a vehicle;

3 is a block diagram showing an embodiment of the present invention.

6 is a flowchart showing processing by voice recognition according to an embodiment.

7 is a flowchart showing display processing in the navigation apparatus of one embodiment.

8 is a flowchart showing processing from an audio input of one example to a map display.

Claims (39)

Recognition means for recognizing speech, and for transmitting the output data of the recognition means in a predetermined form, in order to obtain the same output information, in some cases comprises a data transmission means having at least two input information number Voice recognition device. 2. A speech recognition apparatus according to claim 1, wherein said data transmission means has a memory means, and in some cases at least two input passages of said memory means in order to obtain the same output information of said memory means. The apparatus of claim 2, wherein the output information is location information and / or name of a point or an area. The speech recognition apparatus of claim 2, wherein the output information is information for performing a predetermined operation on another apparatus. The speech recognition apparatus of claim 3, wherein the input passages are words having the same expression and different pronunciations. 4. The apparatus of claim 3, wherein the input paths are names that actually exist and names that do not exist but are similar to the names that exist. The apparatus of claim 4, wherein the input passages represent sentences, words, or the predetermined operation. 4. The apparatus of claim 3, wherein the input paths are place names represented in a predetermined language and the place names represented in another language. A recognition step for recognizing a voice, and for transmitting the output data of the recognition step in a predetermined form, characterized in that it comprises a data transmission step of at least two input information in some cases to obtain the same output information. Voice recognition method. 10. The speech recognition method of claim 9, wherein the output information is location information and / or name of a point or a region. 10. The speech recognition method of claim 9, wherein the output information is information for performing a predetermined operation on another device. The voice recognition method of claim 10, wherein the plurality of input information are words having the same expression and different pronunciations in the data transmission step. The voice recognition method of claim 10, wherein, in the data transmission step, the plurality of input information are names that actually exist and names that do not exist but are similar to the names that exist. 12. The voice recognition method of claim 11, wherein the plurality of pieces of input information in the data transmission step are names of sentences, words, or expressions of the predetermined operation. The voice recognition method according to claim 10, wherein in the data transmission step, the plurality of input information is a place name expressed in a predetermined language and the place name expressed in another language. A recognition step for recognizing a voice, and for transmitting the output data of the recognition step in a predetermined form; in order to obtain the same output information, in some cases, data transmission means having at least two input information, and the data transmission means. And a display signal generating means for generating a map display signal from the output signal of the display signal and display means for displaying the map display signal. 17. A map display apparatus according to claim 16, wherein the data transmission means has a memory means, and the number of input passages of the memory means is at least two in some cases to obtain the same output information of the memory means. 18. The map display apparatus according to claim 17, wherein the output information is location information and / or name of a point or an area. The map display apparatus according to claim 18, wherein the input passages are words having the same expression and different pronunciations. The map display apparatus according to claim 18, wherein the input paths are names that actually exist and names that do not exist but are similar to the names that exist. 19. The map display apparatus according to claim 18, wherein the input paths are place names represented in a predetermined language and the place names represented in another language. 19. The map display apparatus according to claim 18, wherein the location information indicates a location of an office in a predetermined area. The map display apparatus according to claim 18, wherein the location information indicates a center location of a predetermined area. The map display apparatus according to claim 18, wherein the location information indicates an edge position of a predetermined area. A recognition step for recognizing a voice, and for transmitting the output data in the recognition step in a predetermined form; in order to obtain the same output information, in some cases, a data transmission step having at least two input information; and the data transmission. And a display signal generation step for generating a map display signal from the output signal in the step; and a display step for displaying the map display signal. A position detecting means for detecting a current position, a recognition means for recognizing a voice, and an output data of the recognition means in a predetermined form, wherein in some cases the number of input information is at least to obtain the same output information. Two data transmission means, a display signal generation means for generating a display signal from the output signal of the position detection means and / or an output signal of the data transmission means, and display means for displaying the display signal. Navigation device, characterized in that. A position detecting means for detecting a current position, a recognition means for recognizing a voice, and an output data of the recognition means in a predetermined form, wherein in some cases the number of input information is at least to obtain the same output information. Display signals from two data transmission means, map data storage means for storing map data, and output signals of the position detection means and / or output signals of the data transmission means while reading map data from the map data storage means. And display means for displaying the display signal, and display means for displaying the display signal. 27. A navigation apparatus according to claim 26, wherein said data transmission means has a memory means, and at least two of the number of input passages of said memory means in some cases in order to obtain the same output information for said memory means. 28. A navigation apparatus according to claim 27, wherein said data transmission means has a memory means, and at least two of the number of input passages of said memory means in some cases in order to obtain the same output information for said memory means. 30. The navigation apparatus according to claim 29, wherein the output information is location information and / or name of a point or area. 31. The navigation apparatus of claim 30, wherein the input passages are words having the same expression and different pronunciations. 31. The navigation apparatus of claim 30, wherein the input paths are names that actually exist and names that do not exist but are similar to the names that exist. 31. The navigation apparatus according to claim 30, wherein the input paths are place names represented in a predetermined language, and place names represented in another language. 31. A navigation apparatus according to claim 30, wherein said position information indicates the position of an office in a predetermined area. The navigation apparatus as claimed in claim 30, wherein the position information indicates a center position of a predetermined area. The navigation apparatus according to claim 30, wherein the position information indicates an edge position of a predetermined area. 30. The navigation apparatus according to claim 29, wherein the output information is information for performing the same predetermined operation on the navigation apparatus. A reading step for reading the map data from the map data storing means, a position detecting step for detecting the current position, a recognition step for recognizing the voice, and for transmitting the output data in the recognition step in a predetermined form In some cases, in order to obtain the same output information, a data transmission step having at least two numbers of input information and a display signal for generating a display signal from an output signal in the data transmission step and / or an output signal in the reading step And a display step for displaying the display signal. A position detecting means for detecting the current position of the vehicle, a microphone means located inside the vehicle, a speech recognition means for recognizing voices collected by the microphone means, and output data of the recognition means in a predetermined form. Data transmission means having at least two number of input information for obtaining the same output information, map data storage means for storing map data, and reading the map data from the map data storage means to detect the position. Display signal generation means for generating a display signal from the output signal of the means and / or the output signal of the data transmission means, and display means located inside the vehicle to display the display signal. A vehicle having a navigation device. ※ Note: The disclosure is based on the initial application.