JPH11325946A - On-vehicle navigation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To decrease erroneous recognition by reducing the number of times of voice input and voice recognizing processing time in the case of retrieving a target address through voice recognition. SOLUTION: This system is provided with a data base 13 hierarchically storing a prefecture name dictionary 13A, city name dictionary 13B and town name dictionary 13C concerning the address to be the destination of a vehicle, voice recognizing means 14 for recognizing the voice uttered by an unspecified speaker, and current position detecting means 16 for detecting the current position of the vehicle. Based on the current position detected by the current position detecting means 16, the prefecture or city including that position is specified and the town located in that prefecture or city and its name are inputted in voice. Thus, the target institution can be retrieved with a little number of times of voice input.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an in-vehicle navigation device for inputting the address of a destination of a vehicle by voice and searching for a route to the destination.

[0002]

2. Description of the Related Art FIG. 6 is a block diagram showing an example of a conventional navigation device of this type. In FIG. 6, reference numeral 1 denotes operation / input means having operation buttons, a touch panel, a microphone, etc., 2 a CPU for controlling the entire apparatus, and 3 a database storing facility names to be subjected to voice recognition. 3A, second hierarchy dictionary 3B, third hierarchy dictionary 3C
Consists of 4 is a voice recognition means for recognizing the voice of the unspecified speaker, 5 is a voice synthesis means for synthesizing voice for repeating the result of the voice recognition processing, 6 is a current position detection means for detecting the current position of the vehicle, 7 Is route search means for searching for a route from the current value using the facility name selected by voice recognition as the destination of the vehicle; 8, a map storage means for storing map data;
Is a ROM storing an operation program of the apparatus, 10 is a RAM for temporarily storing data when performing work, 1
Reference numeral 1 denotes a display / output unit having a liquid crystal display, a speaker, and the like. FIG. 7 shows an example of the data structure of the database 3. The first hierarchy dictionary 3A is a prefecture name dictionary,
The second hierarchy dictionary 3B is a municipal name dictionary, and the third hierarchy dictionary 3C is a town character name dictionary.

Next, the operation of the above conventional example will be described.
When the destination is set by voice recognition, the control switch of the operation / input means 1 is pressed to activate the voice recognition mode. In the following description, "Sagami-Ono, Sagamihara-shi, Kanagawa" is the target of speech recognition. First, when the voice "Kanagawa" is input, the CPU 2 causes the voice recognition means 4 to search the first layer 3A of the database 3 for sound piece data similar to the voice "Kanagawa", and performs voice recognition processing. Do. The recognition result is read back by the speech synthesis means 5. Next, when the voice input of “Sagamihara city” is performed in response to the guidance “Please input the name of municipalities by voice”, the voice recognition unit 4 outputs the voice “Sagamihara” from the second level 3B of the database 3. Is searched for speech piece data similar to the above, and speech recognition processing is performed.
The recognition result is read back by the speech synthesis means 5. Further, when the voice input of "Sagami-Ono" is performed in response to the guidance "Please input the town character name by voice," the voice recognition means 4
The voice unit data similar to the voice "Sagami Ono" is searched from the third hierarchy 3C of the database 3, and voice recognition processing is performed. The recognition result is read back by the speech synthesis means 5. If the recognition result matches the desired result, the route from the current position detected by the current position detecting means 6 is searched by the route searching means 7 using the result as the destination of the vehicle, and the search result is displayed on the display / output means 11. It is displayed over the map above. In the case of erroneous recognition, voice input can be performed again by pressing the control switch of the operation / input unit 1.

As described above, even in the above-mentioned conventional speech recognition method, since the database 3 has a hierarchical structure, the name of the prefecture, the name of the city, the name of the town, and the name of the town character are input in order in order to retrieve the target address. can do.

[0005]

However, the above-mentioned conventional on-vehicle navigation apparatus has a problem that three voice inputs are required to search for a target address, which is time-consuming and cumbersome. If the target address can be searched with about two voice inputs, the usability will be further improved. However, if the hierarchical structure of the database is made up of two layers, the search data for one time will be enormous. There is a problem that it takes time and misrecognition easily occurs.

SUMMARY OF THE INVENTION The present invention is to solve such a conventional problem, and to provide an excellent in-vehicle navigation apparatus capable of reducing the number of voice inputs and voice recognition processing time and reducing false recognition. With the goal.

[0007]

According to the present invention, in order to achieve the above object, a "prefecture name", a "municipal name" or a "town character name" of a three-layer structure database which has existed conventionally has been proposed. Fetching the position data corresponding to from the current position detecting means used in the in-vehicle navigation device,
The voice recognition is executed only in the prefecture or municipalities to which the current position of the vehicle belongs and in the prefectures or municipalities adjacent thereto or in an area within a certain distance. According to the present invention, the hierarchical structure of the database can be substantially reduced, and the number of times of voice input and the time of voice recognition processing can be reduced to reduce erroneous recognition.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The invention according to claim 1 of the present invention relates to an address which is a destination of a vehicle, divided by prefecture name.
A database that hierarchically stores data according to municipalities and town characters, a voice recognition unit that recognizes an input voice by comparing a plurality of vocabularies of voices uttered by unspecified speakers with data extracted from the database, and a vehicle. Current position detecting means for detecting the current position of the vehicle, and based on the current position detected by the current position detecting means, specifies the prefecture including the position, and identifies the municipalities and towns existing in the prefecture. This is an in-vehicle navigation device in which character-by-character data is to be subjected to voice recognition by the voice recognition means. Since there is no need to input the name of a prefecture by voice, the number of voice inputs and voice recognition processing time are reduced, and false recognition is performed. It has the effect that it can be reduced.

According to a second aspect of the present invention, there is provided a database storing hierarchically data of destination addresses of vehicles by prefecture name, municipalities and town characters, and an unspecified speaker. A voice recognition means for recognizing an input voice by comparing a plurality of vocabulary words of the voice uttered with the data extracted from the database, and a current position detection means for detecting a current position of the vehicle, wherein the current position detection means detects Based on the current position obtained, the municipalities including the position are specified, and the data for each town character existing in the municipalities is a vehicle-mounted navigation device to be subjected to voice recognition by the voice recognition means. Since it is not necessary to input the name of the municipalities by voice, the number of times of voice input and the time of voice recognition processing can be reduced, and erroneous recognition can be reduced.

[0010] The invention according to claim 3 of the present invention is a method for converting data of specified prefectures or municipalities and municipalities existing in the neighboring prefectures or municipalities and of each town or town by voice. 3. The in-vehicle navigation device according to claim 1, which is used as a voice recognition target in the recognition means, and has an effect that not only the prefecture or municipalities at the current position where the vehicle is located but also its neighboring prefectures or municipalities can be searched. Have.

According to a fourth aspect of the present invention, there is provided a mode in which a prefecture name, a municipal name, and a town character name are sequentially input by voice. An on-vehicle navigation device capable of selecting between a mode for inputting a town character name by voice and a mode for specifying a municipal town from the current position and inputting a town character name by voice, according to the user's preference. It has the effect that the method of recognition can be changed.

According to a fifth aspect of the present invention, there is provided a database storing hierarchically data of destination addresses of vehicles by prefecture name, municipalities and town characters, and an unspecified speaker. A voice recognition means for recognizing an input voice by comparing a plurality of vocabulary words of the voice uttered with the data extracted from the database, and a current position detection means for detecting a current position of the vehicle, wherein the current position detection means detects A vehicle-mounted navigation device that specifies an area within a certain distance from the current position based on the current position, and uses the data of each municipal or town character existing in the area as a voice recognition target in the voice recognition means. And the ability to search for an address within a prefecture or municipality within a certain distance from the current location, rather than by administratively determined prefecture or municipal A.

According to a sixth aspect of the present invention, there is provided a mode in which a prefecture name, a municipal name, and a town character name are sequentially input by voice. A mode in which a town character name is input by voice, a mode in which a municipal name is specified from the current position described in claim 2 and voice input of a town character name is performed, and an area within a certain distance from the current position described in claim 5 is specified. This is an in-vehicle navigation device that can select a mode of inputting a municipal name or a town character name by voice, and has an effect that a voice recognition method can be changed according to a user's preference.

(Embodiment 1) FIG. 1 is a block diagram showing a schematic configuration of a vehicle-mounted navigation device according to Embodiment 1 of the present invention. In FIG. 1, reference numeral 11 denotes an operation / input unit having operation buttons, a touch panel, a microphone, and the like;
Reference numeral 2 denotes a CPU for controlling the entire apparatus, and reference numeral 13 denotes a database storing addresses to be subjected to voice recognition. Similar to the conventional example shown in FIG. 7, a first hierarchical dictionary 13A, a second hierarchical dictionary 13B, It is composed of a hierarchical dictionary 13C. 14 is a voice recognition means for recognizing the voice of the unspecified speaker, 15 is a voice synthesis means for synthesizing a voice for repeating the result of the voice recognition processing,
16 is a current position detecting means for detecting the current position of the vehicle, 1
7 is a route search means for searching for a route from the current location using the address selected by voice recognition as the destination of the vehicle, 18 is a map storage means storing map data, 19 is a ROM storing operation programs of the apparatus, and 20 is a ROM. A RAM 21 for temporarily storing data when performing work is a display / output unit having a liquid crystal display, a speaker, and the like.

Next, the operation of the first embodiment will be described. When the destination is set by voice recognition, the control switch of the operation / input means 11 is pressed to activate the voice recognition mode. In the following description, it is assumed that Sagami-Ono, Sagamihara-shi, Kanagawa is a search target address. First, the CPU 12 obtains position data indicating the current position from the current position detecting means 16 and
As shown in (1), it is specified which prefecture of the prefecture name dictionary data loaded into the RAM 20 from the first hierarchical dictionary 13A of the database 13 belongs to the prefecture. Next, when the voice input of “Sagamihara city” is performed in response to the guidance “Please input the name of the city, town and village”, the CPU 12 reads the voice from the second hierarchy 13B of the database 13 into the voice recognition unit 14 and stores it in the RAM 20. In the stored municipal name dictionary data of the local prefecture and the neighboring prefectures, the voice unit data similar to the municipal name input by voice is searched, and voice recognition processing is performed. The recognition result is read back by the speech synthesis means 15. Next, when the voice input of “Sagami Ono” is performed in response to the guidance “Please input the town character name by voice,” the voice recognizing means 14 takes in the data from the third hierarchy 13C of the database 13 and stores it in the RAM 20. The voice recognition processing is performed by retrieving speech piece data similar to the town character name input by voice from the town character name dictionary data of the own city and the neighboring municipalities. The result of the recognition is the speech synthesis means 15
Is repeated by The relationship between the state or municipalities to which the vehicle's current location belongs and its neighboring prefectures or municipalities is
As shown in FIG. 3, it is obtained by referring to the adjacent prefecture table or the adjacent city table. If the recognition result matches the desired result, the route from the current position detected by the current position detecting means 16 is searched by the route searching means 17 using this as the destination of the vehicle. It is displayed over the map on the display. In the case of erroneous recognition, the voice input can be performed again by pressing the control switch of the operation / input unit 11.

As described above, according to the first embodiment,
By simply inputting the name of the municipalities and street characters at the current location where the vehicle is located, the target address can be searched by voice recognition, reducing the number of voice inputs and the time required for voice recognition processing, and reducing erroneous recognition. Can be reduced.

In the first embodiment, the search target of the address by voice recognition is expanded to the prefecture and the municipalities to which the current position detected by the current position detecting means 16 belongs, and the neighboring prefectures and the adjacent municipalities. However, it is also possible to limit to the prefecture or municipalities at the current position where the vehicle is located. Further, as shown in FIG. 4, if the municipalities are specified directly from the current position where the vehicle is located, the address can be immediately searched by voice input of the town character name. Further, there is a mode in which a prefecture name, a municipal name, and a town character name are sequentially input by voice as in the conventional example, a mode in which the prefecture is specified from the above-described current position, and a city, town, and town character name is input by voice. A mode in which a municipalities are specified from a position and a town character name is input by voice can be selected.

(Embodiment 2) Next, Embodiment 2 of the present invention will be described with reference to FIG. Embodiment 2
Includes a distance calculating unit 22 configured to calculate a linear distance between a target facility position and a current position in the configuration of the first embodiment;
A distance threshold setting unit 23 for setting a distance range to be subjected to voice recognition is added, and the other configuration is the same as that of the first embodiment. Omitted.

Next, the operation of the second embodiment will be described. When the control switch of the operation / input unit 11 is pressed to activate the voice recognition mode, the CPU 12 stores the data indicating the current position calculated by the current position detection unit 16 and the distance data set by the distance threshold setting unit 23. From the data in the first hierarchy dictionary 13A of the database 13, the distance calculating means 22 specifies an area existing within the set distance, for example, Kanagawa Prefecture. Next, "Sagamihara city" according to the guidance "Please input the municipal name by voice"
Of the voice recognition means 14
Then, in the municipal name dictionary data of the local prefecture and the neighboring prefectures fetched from the second hierarchy 13B of the database 13 and stored in the RAM 20, speech unit data similar to the municipal name input by voice is searched, and the voice recognition processing is performed. Do. The recognition result is read back by the speech synthesis means 15. Next, when the voice input of “Sagami-Ono” is performed in response to the guidance “Please input the town character name by voice,” the voice recognition unit 14 takes in the data from the third hierarchy 13C of the database 13 and stores it in the RAM 20. The voice recognition processing is performed by retrieving speech piece data similar to the town character name input by voice from the town character name dictionary data of the own city and the neighboring municipalities. The result of the recognition is the speech synthesis means 15
Is repeated by The relationship between the state or municipalities to which the vehicle's current location belongs and its neighboring prefectures or municipalities is
As shown in FIG. 3, it is obtained by referring to the adjacent prefecture table or the adjacent city table. If the recognition result matches the desired result, the route is searched by the route searching means 17 using the result as the destination of the vehicle, and the search result is displayed on the map of the display / output means 21 in a superimposed manner. In the case of erroneous recognition, the voice input can be performed again by pressing the control switch of the operation / input unit 11.

As described above, according to the second embodiment,
Determine in advance how far the address should be searched from the current position, and simply input the name of the city, town, and village for the address up to that range, and search for the target address by voice recognition. Thus, the number of voice inputs and the voice recognition processing time can be reduced, and erroneous recognition can be reduced.

In the second embodiment, the search target by the voice recognition of the address is the prefecture within a certain distance range from the current position detected by the current position detecting means 16, but this is the distance threshold setting means. Depending on the distance set by 23, there may be more than one radially from the vehicle position,
There may be multiple cases in the same direction from the own vehicle position. Further, the area within the certain distance range may be a municipal or a town character. Further, a mode in which the name of a prefecture, a municipal name, and a name of a town character are input in order in the same manner as in the conventional example, and a name of the prefecture is specified from the current position shown in the first embodiment, and the name of the city, town, and town is input by voice A mode in which a municipalities are specified from the current position and the town character name is input by voice, and a mode in which an area within a certain distance range from the current position is specified and the address is input by voice as described in the second embodiment. It can be configured to be selectable.

[0022]

According to the present invention, as is apparent from the above embodiment, the position data corresponding to the "prefecture name", "municipal name" or "town character name" in the three-layer structure database is mounted on the vehicle. From the current position detecting means used in the navigation system for the vehicle, and performs voice recognition only in the prefecture or municipalities to which the current position of the vehicle belongs and the prefectures or municipalities adjacent thereto, or in an area within a certain distance. As a result, the number of times of voice input and the time for voice recognition processing can be reduced, and erroneous recognition can be reduced.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a schematic configuration of a vehicle-mounted navigation device according to a first embodiment of the present invention.

FIG. 2 is a schematic diagram showing a data structure of a RAM according to the first embodiment;

FIG. 3 is a schematic diagram for obtaining a neighboring prefecture or a neighboring municipal name from a current position according to the first embodiment;

FIG. 4 is a schematic diagram showing another search method according to the first embodiment.

FIG. 5 is a block diagram showing a schematic configuration of a vehicle-mounted navigation device according to a second embodiment of the present invention;

FIG. 6 is a block diagram showing a schematic configuration of an in-vehicle navigation device in a conventional example.

FIG. 7 is a schematic diagram showing a data structure of a database in a conventional example.

[Explanation of symbols]

 Reference Signs List 11 operation / input means 12 CPU 13 database 14 voice recognition means 15 voice synthesis means 16 current position detection means 17 route search means 18 map storage means 19 ROM 20 RAM 21 display / output means 22 distance calculation means 23 distance threshold setting means

Claims (6)

[Claims] 1. A database storing hierarchically data of destinations of vehicles according to prefecture names, municipalities and town characters, and a plurality of vocabularies of voices uttered by unspecified speakers. Voice recognition means for recognizing the input voice in comparison with the data extracted from the data, and current position detection means for detecting the current position of the vehicle, based on the current position detected by the current position detection means, An in-vehicle navigation device that specifies a prefecture including a municipal government and uses data of each municipalities and each town character existing in the prefecture as a voice recognition target in the voice recognition means. 2. A database storing hierarchically data of destinations of vehicles according to prefecture names, municipalities and town characters, and a plurality of vocabularies of voices uttered by unspecified speakers. Voice recognition means for recognizing the input voice in comparison with the data extracted from the data, and current position detection means for detecting the current position of the vehicle, based on the current position detected by the current position detection means, An on-vehicle navigation device that specifies a municipalities including a municipalities and uses data for each town character existing in the municipalities as a voice recognition target in the voice recognition means. 3. The speech recognition means in which the specified prefectures or municipalities and the data of each municipalities and town characters or town characters existing in the neighboring prefectures or municipalities are subjected to speech recognition by the speech recognition means. 3. The in-vehicle navigation device according to 1 or 2. 4. A mode in which a prefecture name, a municipal name, and a town character name are sequentially input by voice, a mode in which a prefecture is specified from the current position according to claim 1, and a city, town, and town character name is input by voice. An in-vehicle navigation device capable of selecting a mode in which a municipal town is specified from the current position according to claim 2 and a town character name is input by voice. 5. A database which hierarchically stores data by address of a destination of a vehicle by prefecture, municipalities and town characters, and a plurality of vocabularies of voices uttered by unspecified speakers. Voice recognition means for recognizing the input voice in comparison with the data extracted from the data, and current position detection means for detecting the current position of the vehicle, based on the current position detected by the current position detection means, An in-vehicle navigation device that specifies an area within a certain distance from a vehicle, and uses data of each municipal or town character existing in the area as a voice recognition target in voice recognition means. 6. A mode in which a prefecture name, a municipal name, and a town character name are sequentially input by voice, and a mode in which the prefecture is specified from the current position according to claim 1 and the city, town, and town character name are input by voice. A mode in which a municipal name is specified from the current position described in claim 2 and a town character name is input by voice, and a region within a certain distance from the current position described in claim 5 is specified and a municipal name or a town character name is voiced. An in-vehicle navigation device capable of selecting an input mode.