JP2004317803A - Navigation system and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a navigation system capable of attaining utterance with more natural and accurate readings as much as possible. <P>SOLUTION: Position information based upon a set point (e.g. a destination) and a reference position 307 of speech recognition data 301 are made to match each other, and speech patterns 303 of an administrative area name and a facility name corresponding to the matching reference position 307 are voiced out. The speech patterns 303 are originally used to recognize a speech, but used for speech output. Thus, data prepared for speech recognition are used, so a navigation system having a speech recognizing function can realize the speech output without nearly preparing data for speech output. Further, administrative area names, facility names, and position information of speech recognition data are made to accurately correspond to one another, so, for example, even if an administrative area name of the same Chinese characters are read differently with areas, accurately speech output becomes possible. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a navigation device and the like having a voice recognition function.
[0002]
[Prior art]
Conventionally, various navigation devices have been developed, and one of the functions of the navigation device is a route guidance function. This is to calculate a recommended route to a destination set by a user, and to guide the recommended route by displaying a map or outputting sound. As a method for the user to set the destination, there is a method in which the user inputs voice to the microphone, and the voice response device recognizes the voice input to the microphone and sets the destination. Further, there is a method of specifying and setting an arbitrary point on a map displayed on a display unit using a touch panel, a remote controller, or the like, and a method of selecting or setting an address or a facility name by text input. However, no matter which method is used, there is a possibility that the destination is set by mistake, so that the address and facility name of the destination set after the setting are output by voice to the user. It is desirable to have a mechanism to prompt confirmation.
[0003]
In order to confirm by voice output in this way, some voice data is required. If voice data prepared by reading and recording (sampling) all addresses and facility names by a person is prepared in advance, and voice is output using the voice data, the user hardly feels uncomfortable. But in practice, this is difficult. Because, apart from the name of the facility, the number of addresses is enormous, and the volume of recorded voice data is generally large compared to other data. It is impossible to prepare them.
[0004]
Therefore, a technology for accurately outputting an address or a facility name by voice while reducing the data amount of voice data as much as possible has been considered.
For example, the speech synthesis device described in Patent Literature 1 searches a kanji reading database based on an input text code and outputs a synthesized speech based on the search result. According to this technology, it is possible to read aloud kanji place names and to output kanji as they are (that is, mere reading aloud), so that the user can easily confirm.
[0005]
[Patent Document 1]
JP 10-141978 A
[Problems to be solved by the invention]
However, in order to output a synthesized speech, it is necessary to first accurately specify a text code based on a text to be output as a synthesized speech, and if not, a problem may occur. For example, there is a case where the same kanji and different readings exist in different regions. In such a case, if the identification is made only by the matching of the kanji, the synthesized voice may be output in an incorrect reading manner. In addition, this speech synthesizer needs to prepare a dedicated kanji reading database in advance, which may cause an increase in cost. Furthermore, since the reading is simply registered in the kanji reading database, it is not a voice in which accent, intonation, and the like are taken into consideration, so that the user may have a sense of discomfort.
[0007]
The present invention has been made in view of such a problem, and an object of the present invention is to provide a navigation device or the like that can speak with accurate reading as much as possible.
[0008]
Means for Solving the Problems and Effects of the Invention
Usually, a navigation device having a voice recognition function can use voice recognition data in which a voice pattern for recognizing an administrative division name or a facility name and its position data are set in order to set a destination or the like. It is configured. Then, by using the voice recognition data, the name of the administrative division or the name of the facility spoken by the user is recognized, and the reference position (for example, the position of the government office or the center position) of the recognized administrative division or the location of the facility is specified. . The present invention pays attention to this point, and performs voice output by using the voice recognition data also in voice output.
[0009]
The navigation device according to claim 1, wherein a voice pattern for recognizing an administrative section name and a voice recognition data storage medium storing voice recognition data in which position data indicating a reference position of the administrative section are paired. Voice recognition data obtaining means for obtaining voice recognition data, voice output means for outputting voice based on the voice pattern, and voice recognition data obtaining means obtaining a voice pattern corresponding to position information input by a user. Control means for searching the voice recognition data and outputting the searched voice pattern as voice to the voice output means. The voice pattern referred to here means a voice waveform pattern for recognizing voice, text, and the like, which are generally known. This text may be just text or may include accents and intonation symbols. The reference position of the administrative division is a position for specifying the administrative division, for example, the position of the government office or the center position.
[0010]
As described above, the navigation device according to the first aspect uses the voice recognition data prepared for voice recognition, so that it is not necessary to newly prepare voice output data storing the administrative division name as dedicated data. . Therefore, any navigation device having a voice recognition function can be easily realized. In addition, since the voice pattern of the administrative division name in the voice recognition data and the position data of the administrative division are accurately correlated, for example, even if the administrative division name of the same kanji is read differently depending on the region, it can be accurately determined. Can output voice.
[0011]
In the navigation device according to the second aspect, the voice recognition data obtaining unit obtains voice recognition data in which a voice pattern for recognizing a facility name and position data indicating the location of the facility are paired. It is included in the voice recognition data. Then, the control unit searches for a voice pattern corresponding to the position information input by the user from the voice recognition data obtained by the voice recognition data obtaining unit, and causes the voice output unit to output the searched voice pattern as voice. .
[0012]
With this configuration, it is possible to output a sound with accurate reading even for the facility name.
By the way, when it is considered to output the administrative division name by voice, only the administrative division name (for example, only “Showa-cho”) may be output by voice. For example, the user can easily understand if the sound is output in the form of “Showa-cho, Kariya-shi, Aichi”. With the navigation device according to the third aspect, this can be realized. The administrative apparatus according to claim 3, further comprising: obtaining the position data and the hierarchical data from the administrative division data storage medium storing the positional data of the administrative division and the hierarchical data indicating the hierarchical relation of the administrative division. An acquisition unit is provided. Then, the control means specifies an address composed of a plurality of administrative division names corresponding to the input position information based on the position data and the hierarchical data acquired by the administrative division data acquisition means, and specifies each of the identified administrative divisions. The voice patterns corresponding to the sections are combined from the voice recognition data, and the combined voice patterns are output as voice to the voice output means. Note that the hierarchical data indicating the hierarchical relation of the administrative divisions is data indicating, for example, the hierarchical relation of a certain administrative division to which town, which ward, which city, and which prefecture.
[0013]
In such a case, voice is output in the form of an address, so that the user can easily specify the position of the administrative division or facility.
By the way, even if it does not cover all the names, if there is audio data that has been recorded (sampled) in advance even for some administrative division names (including address format) and facility names, use them. I hope it is. That is, as described in the fourth aspect, there is further provided an audio data acquisition means for acquiring audio data from an audio data storage medium for storing audio data recorded in advance corresponding to an audio pattern. If the voice data corresponding to the voice pattern to be output as voice to the voice output means exists in the voice data obtained by the voice data obtaining means, the control means outputs the voice data instead of the voice pattern. It is output to the output means.
[0014]
With this configuration, for a case where voice data exists, a very fluent voice output is made, and the user can easily understand.
Further, a program for functioning as the control means of the navigation device according to any one of claims 1 to 4 as described in claim 5 may be executed by a computer built in the navigation device. Good. If this is the case, for example, the program is recorded on a computer-readable recording medium such as a flexible disk, a magneto-optical disk, a CD-ROM, a hard disk, a ROM, and a RAM, and loaded into the computer as necessary. When activated, it can function as a robot pointing device. Further, since the program can be distributed through a network, it is easy to upgrade the functions.
[0015]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments to which the present invention is applied will be described with reference to the drawings. It should be noted that the embodiments of the present invention are not limited to the following examples in any way, and can take various forms as long as they belong to the technical scope of the present invention.
[0016]
FIG. 1 is a block diagram illustrating a schematic configuration of a navigation device 20 according to the embodiment. The navigation device 20 is mounted on a vehicle, and a position detector 21 for detecting a current position of the vehicle, an operation switch group 22 for inputting various instructions from a user, and various instructions can be input similarly to the operation switch group 22 Therefore, a remote control terminal (hereinafter, referred to as a remote controller) 23a separate from the navigation device 20, a remote control sensor 23b for inputting a signal from the remote controller 23a, and information from a device different from the navigation device 20 An external information input / output unit 24 capable of inputting and outputting information to another device; a map data input unit 25 for inputting map data and the like from an external storage medium in which map data and various kinds of information are recorded; , A display unit 26 for displaying a map and various information, a voice output unit 27 for outputting various guide voices, and the like. Various processes are executed in accordance with inputs from the position detector 21, the operation switch group 22, the remote control sensor 23b, the external information input / output unit 24, and the map data input unit 25, and the external information input / output unit 24, the display unit 26, the voice And a control circuit 29 for controlling the output unit 27.
[0017]
The position detector 21 receives a transmission radio wave from a GPS (Global Positioning System) artificial satellite via a GPS antenna, and detects a position, a direction, a speed, and the like of the vehicle, and a GPS receiver 21a, which is added to the vehicle. A gyroscope 21b for detecting the magnitude of the rotational movement, a distance sensor 21c for detecting the distance traveled from the longitudinal acceleration of the vehicle, and the like, and a geomagnetic sensor 21d for detecting the traveling direction from the geomagnetism are provided. I have. Each of the sensors 21a to 21d has an error having a different property, and is configured to be used while complementing each other.
[0018]
As the operation switch group 22, a touch panel provided on the display screen, a mechanical key switch provided around the display unit 26, and the like, which are integrally formed with the display unit 26, are used. The touch panel and the display unit 26 are laminated and integrated, and there are various types of touch panels such as a pressure-sensitive type, an electromagnetic induction type, a capacitance type, and a combination thereof. May be used.
[0019]
The external information input / output unit 24 is connected to an antenna (not shown), and receives traffic information from a VICS center (not shown) via the antenna. The received traffic information is sent to the control circuit 29 and used for setting a guidance route.
The map data input device 25 is a device for inputting various data stored in the storage medium 30. The storage medium 30 stores map data 200, voice data 201, voice recognition data 301, and administrative division hierarchy data 401. As an actual recording medium, a CD-ROM or DVD is generally used because of its data amount, but other media such as a magnetic storage device such as a hard disk or a memory card may be used. The map data 200 stored in the storage medium 30 includes road shape data, road width data, road regulation data, terrain data, mark data, intersection data, facility data, and the like. The audio data 201 is audio data generated by recording. The voice data generated by the recording is, for example, a human voice voice recorded by a PCM method with a sampling frequency of 44.1 KHz and a quantization bit number of 16 bits. The uttered voice includes an administrative division name, a facility name, and the like. Specifically, it is composed of a main administrative division name (for example, Aichi Prefecture), a combination of main administrative division names (for example, Nagoya City, Aichi Prefecture), and a main facility name (for example, Nagoya Dome).
[0020]
The speech recognition data 301 will be described using the data example of FIG. The voice recognition data 301 shown in FIG. 2 includes a voice pattern 303, a display text 305, a reference position 307, and a section 309 as data items. The voice pattern 303 is composed of kana for voice reading, accents and intonations (not shown), and is used when performing voice recognition. The display text 305 is data to be displayed on the display unit 26 when confirming the recognized voice. The reference position 307 indicates a reference position (for example, the position of a government office or the center position) of the recognized administrative division name or facility name. The section 309 is data indicating whether the name is an administrative division name or a facility name.
[0021]
In addition, the administrative division hierarchy data 401 will be described using the data example of FIG. The administrative division hierarchy data 401 shown in FIG. 3 has a tree structure composed of a plurality of cells, and each cell is composed of an administrative division name and position data. Among them, the position data is data indicating a reference position such as the location where the government office of the administrative division is located or the center position. It is preferable that each cell also has information (for example, vertex position information indicating a boundary line) that can specify the area of the administrative division.
[0022]
In FIG. 3, the cell 403 corresponds to Aichi prefecture, and the cells related thereto include a cell 405 in Kariya city, a cell 407 in Nagoya city, a cell 409 in Chiryu city, and the like. Among them, the cells related to the Kariya city 405 include the cell 411 in Aizuma-cho, the cell 413 in Igaya-cho, and the cell 415 in Shiromachi. Since the hierarchy of the administrative division names can be understood in this way, the hierarchical relation of an arbitrary administrative division can be specified by using the administrative division hierarchical data 401.
[0023]
Returning to FIG. 1, the display unit 26 is a color display device, such as a liquid crystal display, an organic EL display, or a CRT, but any of them may be used. The display screen of the display unit 26 includes a mark indicating the current position specified from the current position of the vehicle detected by the position detector 21 and the map data input from the map data input unit 25, a guidance route to the destination, and a name. And additional data such as marks, marks of various facilities, etc. can be displayed in a superimposed manner. In addition, facility guides and the like can be displayed.
[0024]
The voice output unit 27 can output voices of facility guides and various types of guidance input from the map data input unit 25 and voices of traffic information received via the external information input / output unit 24.
The microphone 28 outputs an electric signal based on the input voice when the user inputs (utters) a voice. The user can operate the navigation device 20 by inputting various sounds into the microphone 28.
[0025]
The control circuit 29 is mainly composed of a well-known microcomputer including a CPU, a ROM, a RAM, an I / O, and a bus line for connecting these components, and is based on a program stored in the ROM and the RAM. A display that calculates the current position of the vehicle as a set of coordinates and traveling direction based on each detection signal from the position detector 21 and displays a map or the like near the current position read via the map data input device 25 on the display unit 26. Based on the processing and the point data stored in the map data input device 25, a facility as a destination is selected according to an operation of the operation switch group 22 or the remote controller 23a, and an optimal route from the current position to the destination is automatically determined. , A guide route setting process of setting a guide route by performing a route calculation required.
[0026]
The schematic configuration of the navigation device 20 has been described so far. Here, correspondence with the terms described in the claims will be described. The control circuit 29 corresponds to the control means described in the claims, and the audio output unit 27 corresponds to the audio output means. Further, the map data input device 25 corresponds to voice recognition data obtaining means, administrative division data obtaining means, and voice data obtaining means. Further, the storage medium 30 corresponds to a voice recognition data storage medium, an administrative division data storage medium, and a voice data storage medium.
[0027]
Next, audio output for confirming a point performed by the control circuit 29 will be described using a destination setting process as an example. Descriptions of other processes, such as a guidance process, which is usually performed by a conventional general vehicle navigation device, are omitted.
FIG. 4 is a flowchart for explaining the destination setting process. The destination setting process is started when the user operates the operation switch group 22 or the remote controller 23a to set a destination.
[0028]
When started, first, operation information is acquired (S105). This is because the user intends to set a destination, for example, information of a voice signal output from the microphone 28 when the user voice-inputs the name of the facility into the microphone 28, or a map displayed on the display unit 26. Means the operation information output from the operation switch group 22 or the remote controller 23a when the user operates the operation switch group 22 or the remote controller 23a based on the. The destination may be a facility or a simple point on a map where no facility exists.
[0029]
Next, the destination address set by the user is calculated based on the operation information acquired in S105 and the map data input by the map data input device 25 (S110). For example, when the user voice-inputs the facility name “Kariya Stadium” to the microphone 28, the address of the Kariya Stadium is calculated as “1-49 Jomachi, Kariya City, Aichi Prefecture” in this step. When the user specifies the address and sets the destination, the address is already specified at that time, and thus this step is skipped.
[0030]
Next, it is determined whether or not voice data corresponding to the address calculated in S110 (or the address specified in S105) exists in the voice data 201 (S115). This is determined by searching the audio data 201 by the administrative division name. The search unit may be an individual administrative division name or a combination of administrative division names. For example, if the address calculated in S110 is “1-49 Jomachi, Kariya-shi, Aichi” and if the data “Kariya-shi, Aichi” is found in the voice data 201, it is determined that the voice data corresponding to the address exists. I do. The search in this step needs to be performed carefully. This is because, since the voice data 201 is searched by the administrative division name, there may be audio data with different reading styles and accents even if the administrative division name itself is the same. Therefore, in order to eliminate such a problem, it is preferable to previously remove voice data in which a plurality of types of reading are present under the same administrative division name. Of course, the present invention is not limited to the case where each audio data of the audio data 201 is the audio data 201 which can be specified by the position information.
[0031]
As a result of the determination, if the voice data corresponding to the address calculated in S110 exists in the voice data 201, the process proceeds to S120, and if not, the process proceeds to S125.
In step S120, according to the address calculated in step S110, speech data 303 is generated by combining the speech pattern 303 of the speech recognition data 301. At this time, first, a pair of the administrative division name and the reference point is obtained with reference to the administrative division hierarchical data 401. The voice pattern 303 is specified from the voice recognition data 301 by using the obtained pair, and the voice pattern 303 is combined.
[0032]
A specific example will be described. For example, if the address calculated in S110 is “1-49 Jomachi, Kariya City, Aichi Prefecture”, first, from the administrative division hierarchy data 401, the cell 403 of Aichi Prefecture, the cell 405 of Kariya City, and the cell 415 of Jomachi are Identify and extract. Then, the voice pattern 303 is specified from the voice recognition data 301 by using the pair of the administrative division name of each cell and the reference point. That is, the administrative division name of each cell is matched with the display text 305 of the speech recognition data 301, the position information of each cell is matched with the reference position 301 of the speech recognition data 301, and the logical product of both is obtained. Is extracted from the voice pattern 303 of the data record that matches. Then, the plurality of extracted voice patterns 303 are combined according to the address. Specifically, read-aloud data is generated in combination like "Aichiken Kariyashi Shiromachi Ichino Yongyukyu".
[0033]
On the other hand, in S125, according to the address calculated in S110, the read voice data is generated by combining the searched voice data 201 and the voice pattern 303 of the voice recognition data 301. At this time, if the reading data corresponding to the address can be generated only by the voice data 201, the voice pattern 303 is not used. The method of using the voice pattern 303 is the same as the method described in S120.
[0034]
A specific example will be described. For example, if the address calculated in S110 is “1-49 Jomachi, Kariya City, Aichi Prefecture”, the voice data 201 is used first. Here, assuming that there is data reading out “Kariya City, Aichi Prefecture” as the audio data 201, this data is used. Subsequently, the cell 403 of Aichi prefecture, the cell 405 of Kariya city, and the cell 415 of castle town are specified from the administrative division hierarchy data 401, and the cell of castle town is extracted among them. Then, the voice pattern 303 “Shiromachi” is specified from the voice recognition data 301 using the pair of the administrative division name of the cell and the reference point. Finally, the voice data 201 is generated by combining “Kariya city, Aichi” with the voice pattern 303 “Shiromachi”.
[0035]
When the generation of the read-aloud data is completed in this way, the voice is output to the voice output section 27 based on the generated read-aloud data (S130). As an example, the content is such as "Is the destination at Kariya Stadium in 1-49, Jomachi, Kariya City, Aichi Prefecture?"
[0036]
Subsequently, information on the operation performed by the occupant corresponding to the voice output in S130 is obtained (S135). The operation information is operation information of the operation switch group 22 and the remote controller 23a operated by the user to determine the destination or to cancel the destination.
[0037]
Subsequently, the process branches depending on whether or not the operation information acquired in S130 is information for determining a destination. If the information indicates that the destination is determined, the destination is determined and the process (destination setting process) ends. On the other hand, if the information is to cancel, the process returns to the first step (S105) of the destination setting process.
[0038]
So far, the audio output for confirming a point has been described by taking the destination setting processing as an example. However, the following effects can be obtained by the navigation device 20 of the present embodiment.
The navigation device 20 performs voice output using the voice pattern 303 used for voice recognition. For this reason, it is not necessary to newly prepare voice output data storing the administrative division names and facility names as dedicated data. Therefore, any navigation device having a voice recognition function like the navigation device 20 can be easily realized. In addition, since the administrative division name or facility name (that is, the audio pattern 303) of the voice recognition data 301 and the positional information (that is, the reference position 307) are accurately associated, for example, the administrative division name of the same kanji may be different depending on the region. Even if the reading is different, the voice can be output accurately.
[0039]
In addition, since the set destination is output as voice in the form of an address, the user can easily confirm the position of the destination.
Further, among the administrative division names scheduled to be read out, those that exist as the audio data 201 are used for audio output. Therefore, fluent voice output is made, and the user can easily understand.
[0040]
Hereinafter, other embodiments will be described. In the above-described embodiment, the audio output for confirming a point has been described with reference to the destination setting processing. However, audio processing for confirmation and the like is performed by the same processing in processing other than the destination setting processing. Is also good. For example, when a memory location is set or when facility information is searched, the facility name or address may be output as voice for confirmation.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating a configuration of a navigation device according to an embodiment.
FIG. 2 is a data example for explaining voice recognition data.
FIG. 3 is an example of data for explaining administrative division hierarchy data.
FIG. 4 is a flowchart illustrating a destination setting process.
[Explanation of symbols]
Reference Signs List 20 navigation device, 21 position detector, 21a GPS receiver, 21b gyroscope, 21c distance sensor, 21d geomagnetic sensor, 22 operation switch group, 23a remote control, 23b remote control sensor, 24 external Information input / output unit, 25: map data input unit, 26: display unit, 27: voice output unit, 28: microphone, 30: storage medium, 200: map data, 201: voice data, 301: voice recognition data, 401 ... Administrative division hierarchy data

Claims (5)

Speech recognition data for acquiring speech recognition data from a speech recognition data storage medium storing speech recognition data in which a speech pattern for recognizing an administrative section name and position data indicating a reference position of the administrative section are stored. Acquisition means;
Audio output means for outputting audio based on the audio pattern;
Control means for searching a voice pattern corresponding to position information input by a user from the voice recognition data obtained by the voice recognition data obtaining means, and outputting the searched voice pattern to the voice output means as voice When,
A navigation device having a voice recognition function, comprising: The navigation device according to claim 1,
The voice recognition data obtained by the voice recognition data obtaining means further includes data in which a voice pattern for recognizing a facility name and position data indicating the location of the facility are paired,
The control means searches for a voice pattern corresponding to the position information input by the user from the voice recognition data obtained by the voice recognition data obtaining means, and outputs the searched voice pattern to the voice output means. A navigation device characterized in that it is output as a message. The navigation device according to claim 1 or 2,
Further, from an administrative division data storage medium in which positional data of administrative divisions and hierarchical data indicating the hierarchical relation of administrative divisions are stored, the administrative division data acquisition means for acquiring the position data and the hierarchical data,
The control means, based on the position data and the hierarchical data obtained by the administrative division data acquisition means, specified an address consisting of a plurality of administrative division names corresponding to the input location information, and specified. A navigation device, wherein the voice patterns corresponding to each administrative section are combined from the voice recognition data, and the combined voice pattern is output as voice to the voice output means. In the navigation device according to any one of claims 1 to 3,
Further, the audio data storage means for obtaining audio data from an audio data storage medium that stores audio data recorded in advance,
The control means, if the voice data corresponding to the voice pattern to be output as voice to the voice output means in the voice data obtained by the voice data obtaining means, replaces the voice pattern. Wherein said audio data is output to said audio output means. A program for causing a computer to function as control means for the navigation device according to claim 1.

Images