JP3677833B2 - Navigation device, navigation method, and automobile - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
  The present invention displays a road map or the like mounted on a car, for example.NaThe present invention relates to a navigation device, a navigation method, and an automobile on which these devices are mounted.
[0002]
[Prior art]
Conventionally, various navigation devices mounted on automobiles and the like have been developed. This navigation device includes, for example, a large-capacity data storage means such as a CD-ROM in which road map data is stored, a current position detection means, and data obtained by reading a road map near the detected current position from the data storage means. And a display device that displays based on the above. In this case, the current position detection means is based on information using a positioning system using a positioning artificial satellite called GPS (Global Positioning System), and information such as the traveling direction and traveling speed of the vehicle. There are things such as autonomous navigation that tracks changes in the current position from the starting point.
[0003]
Moreover, as a map displayed on the display device, by performing key operations, a map at a desired position can be displayed as long as map data is prepared in addition to the vicinity of the current position. It is.
[0004]
In the case of such a navigation device, for example, in the case of an automobile, a display device is installed in the vicinity of the driver's seat so that the driver can see a map in the vicinity of the current position while driving or during a temporary stop such as a signal stop. It is common to do so.
[0005]
[Problems to be solved by the invention]
By the way, such a navigation device needs to be able to be operated without interfering with driving of the automobile, and for example, complicated operations are prohibited during traveling. That is, when such a navigation device is installed in a vehicle, it is detected that the vehicle is stopped due to the state of the detection unit connected to some kind of traveling state detection unit (for example, a parking brake switch of an automobile). Only when the vehicle is in operation, it is set so that all operations can be performed, and in a state where the vehicle is not stopped (that is, during running), complicated key operations are prohibited.
[0006]
However, it is inconvenient that operations such as switching the display map cannot be performed while traveling, and it is requested that advanced operations can be performed without disturbing driving even while traveling. Yes.
[0007]
SUMMARY OF THE INVENTION The present invention has been made in view of the above, and an object of the present invention is to make it possible to easily perform advanced operations of various devices such as a navigation device without obstructing driving of an automobile.
[0008]
[Means for Solving the Problems]
  The present inventionThe navigation apparatus of the present invention creates a video signal for creating a video signal for displaying a recognition target word candidate recognized by the audio processing unit, and when creating a video signal for a recognition target word candidate by the video signal creation means, The candidate recognition target words are classified into a word indicating a place name and a word giving a command, and each of the classifications is provided with display control means for making a video signal to be displayed in a different display mode It is.
[0013]
According to the navigation device of the present invention, since the display state of the recognition target word candidates is different for each category of the candidate target words, the candidates for the same category are easy to understand and the display state is easy to see.
[0014]
  In the navigation method of the present invention, when candidates for recognition target words recognized by speech are displayed, classification of recognition target words as candidates is displayed.However, it is divided into words that specify place names and words that give orders.Are displayed in different display modes.
[0015]
According to the navigation method of the present invention, since the display state of the recognition target word candidates is different for each candidate target word category, the candidates for the same category are easily understood and the display state is easy to see.
[0016]
  In addition, the automobile of the present invention is a vehicle provided with a device for displaying a map on the basis of recognition of input speech on display means arranged at a predetermined position in the vehicle. Video signal creation means for creating a video signal to be displayed and supplying it to the display means, and classification of recognition target words as candidates when the video signal creation means creates a candidate video signal for the recognition target wordHowever, it is divided into words that specify place names and words that give orders.And a display control means for making a video signal to be displayed in a different display mode.
[0017]
According to the automobile of the present invention, since the display state of the recognition target word candidate is different for each category of the candidate target word, the candidates for the same category are easily understood and the display state is easy to see.
[0018]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.
[0019]
In this example, the present invention is applied to a navigation device mounted on an automobile. First, an installation state of the apparatus of this example in an automobile will be described with reference to FIGS. As shown in FIG. 2, the vehicle 50 has a handle 51 attached to the front of a driver seat 52, and basically a driver seated in the driver seat 52 operates a navigation device. However, other passengers in the car 50 may operate. The navigation device main body 20 and the voice recognition device 10 connected to the navigation device main body 20 are installed in an arbitrary space in the automobile 50 (for example, in the trunk at the rear), and a positioning signal receiving antenna 21 described later is provided. It is attached to the outside of the vehicle body (or inside the rear window).
[0020]
As shown in the vicinity of the driver's seat in FIG. 3, a talk switch 18 and an operation key 27 of the navigation device which will be described later are disposed beside the handle 51, and these switches and keys are operated during driving. Is arranged so that there is no hindrance. In addition, the display device 40 connected to the navigation device is disposed at a position that does not obstruct the driver's front view. Further, a speaker 32 that outputs a voice signal synthesized in the navigation device 20 is attached to a position where the output voice reaches the driver (for example, the side of the display device 40).
[0021]
In addition, the navigation device of this example is configured to allow voice input, and the microphone 11 for that purpose is attached to a sun visor 53 disposed on the front windshield in front of the driver seat 52 and is seated on the driver seat 52. The driver's voice is picked up.
[0022]
The navigation device body 20 of this example is connected to the engine control computer 54 of the automobile, and a pulse signal proportional to the vehicle speed is supplied from the engine control computer 54.
[0023]
Next, the internal configuration of the navigation device of this example will be described with reference to FIG. 1. In this example, the voice recognition device 10 is configured to be connected to the navigation device 20. The microphone 11 is connected. As the microphone 11, for example, a microphone whose directionality is set to be relatively narrow and picks up only the voice of a person seated in the driver's seat of the automobile is used. For example, a talk switch 18 described later is pressed and turned on. The power is turned on and the operation of picking up the sound is performed only during the state.
[0024]
The audio signal picked up by the microphone 11 is supplied to the analog / digital converter 12 and converted into a digital audio signal having a predetermined sampling frequency. The digital audio signal output from the analog / digital converter 12 is supplied to a digital audio processing circuit 13 having an integrated circuit configuration called a DSP (digital signal processor). In the digital voice processing circuit 13, the digital voice signal is converted into vector data by processing such as band division and filtering, and this vector data is supplied to the voice recognition circuit 14.
[0025]
A speech recognition data storage ROM 15 is connected to the speech recognition circuit 14 and performs a recognition operation according to a predetermined speech recognition algorithm (for example, HMM: Hidden Markov Model) with vector data supplied from the digital speech processing circuit 13. Then, a plurality of candidates are selected from the speech recognition phoneme models stored in the ROM 15, and the character data stored corresponding to the phoneme model having the highest degree of coincidence among the candidates is read out. Note that the voice recognition circuit 14 of this example also functions as a control unit that controls processing of each unit in the voice recognition device 10, and the voice recognition circuit 14 also operates the talk switch 18 described later. Is to judge.
[0026]
Here, the data storage state of the voice recognition data storage ROM 15 of this example will be described. In this example, only the place name and the words for instructing the operation of the navigation device are recognized. As shown in the storage area setting state in FIG. 4, only the names of prefectures and cities in Japan are registered. For each prefecture and city, the character code of the place name and the place name A phoneme model, which is data for recognizing a voice, is stored.
[0027]
For example, in the case of Japan, the number of municipalities in the whole country is about 3500, and about 3500 place names are stored. However, in the case of the place name “XX town”, both data when pronounced as “xxx gusset” and data when pronounced as “xxx butterfly” are stored. Similarly, in the case of the place name of “XX village”, both data when pronounced as “xxx son” and data when pronounced as “xxx unevenness” are stored.
[0028]
In addition, city names that are likely to be misunderstood, such as municipalities located adjacent to the borders of prefectures, are registered with the name of the prefecture that is likely to be mistaken. . That is, for example, the correct example “Kanagawa Ken Kawasaki (Kawasaki City, Kanagawa Prefecture)” is registered, and the wrong example of the neighboring prefecture name “Tokyo Kawasaki City (Tokyo Kawasaki City)” is also registered. .
[0029]
In addition, words to instruct operation of the navigation device include words indicating the display position such as “Destination”, “Departure Point”, “Via-route”, “Home”, and “What time is it now” (Listing the current time) Command), “Where is now” (command to listen to the current position), “Next” (command to listen to the next intersection), “How much” (command to listen to the distance to the destination), “Speed is” (current speed) , "Altitude" (command to listen to the current altitude), "Progression direction" (command to listen to the direction of travel), "List" (command to display a list of recognizable commands on the display) The character code of a word for performing various other operation commands such as) and the phoneme model corresponding to the word are stored.
[0030]
If the character code corresponding to the phoneme model that matches the recognition result obtained from the input vector data through the predetermined speech recognition algorithm is the character code of the place name in the speech recognition circuit 14, The code is read from the ROM 15. The read character code is supplied to the longitude-latitude conversion circuit 16. A longitude / latitude conversion data storage ROM 17 is connected to the longitude / latitude conversion circuit 16, and the latitude / longitude data corresponding to the character data supplied from the voice recognition circuit 14 and its associated data are read from the ROM 17.
[0031]
Note that the speech recognition circuit 14 of this example is provided with a memory (not shown) for temporarily storing the recognition result, and the recognition result is stored as a history list in this memory. Also, during the recognition process, data from the voice with the highest matching degree to the voice that matches to some extent in order is stored as a candidate list. The history list and candidate list are deleted after a certain amount of time has elapsed since they were stored.
[0032]
Here, the data storage state of the longitude-latitude conversion data storage ROM 17 of this example will be described. In the case of this example, a storage area is stored for each character code that is the same as the character code of the place name stored in the voice recognition data storage ROM 15. As shown in FIG. 5, for each character code, the latitude and longitude data of the place name indicated by the character and display scale data are stored as accompanying data. The character code read from the voice recognition data storage ROM 15 is a katakana character code. In the longitude-latitude conversion data storage ROM 17, in addition to the katakana character code whose pronunciation is represented by a character string, Character codes using kanji, hiragana, katakana, etc. for display are also stored.
[0033]
In the case of this example, the latitude and longitude data for each place name includes latitude and longitude data indicating the absolute location of the local government office (city hall, ward office, town hall, village hall) indicated by the place name. It is as. Further, as accompanying data, display character code and display scale data are output together with latitude and longitude data. The display scale data is display scale data set according to the size of the area indicated by the place name. For example, the display scale data is data indicating the display scale in several stages.
[0034]
Then, the latitude / longitude data read from the longitude / latitude conversion data storage ROM 17 and its accompanying data are supplied to the output terminal 10 a as the output of the speech recognition device 10. Further, the character code data of the input speech whose match is detected by the speech recognition circuit 14 is supplied to the output terminal 10 b as the output of the speech recognition device 10. Data obtained at the output terminals 10 a and 10 b is supplied to the navigation device 20.
[0035]
The speech recognition device 10 of this example is connected to a talk switch 18 that is an open / close switch that is not locked (ie, a switch that is turned on only when it is pressed), and the talk switch 18 continues for at least 300 milliseconds. Only the audio signal picked up by the microphone 11 while being pressed is processed by the circuit from the analog / digital converter 12 to the latitude-longitude conversion circuit 16 as described above. The processing in the voice recognition device 10 is performed based on the control of the voice recognition circuit 14, and the voice recognition circuit 14 also determines the state of the talk switch 18.
[0036]
In this example, when the speech recognition circuit 14 performs the recognition processing of the input speech again within a predetermined time (for example, within 10 seconds), the speech recognized at this time is stored in the memory in the speech recognition circuit 14. Is stored in the history list, the recognized speech is deleted from the history list, and it is determined that the speech stored in the highest rank in the deleted history list is recognized as speech. In addition, when such a process is continuously performed a plurality of times (for example, five times), candidate recognition voice data is read from the candidate list, supplied to the navigation device 20 side, and connected to the navigation device 20. The candidate list is displayed on the display device 40. Details of these processes will be described later.
[0037]
In addition, various kinds of control data other than the character codes described above can be transmitted from the voice recognition circuit 14 in the voice recognition apparatus 10 of this example to the navigation apparatus 20 via the terminal 10b. Control data for interrupting the map data creation process may be sent to the navigation device 20 side.
[0038]
Next, the configuration of the navigation device 20 connected to the voice recognition device 10 will be described. The navigation device 20 includes a GPS antenna 21. The current position detection circuit 22 receives and processes a positioning signal from a GPS satellite received by the antenna 21, analyzes the received data, and analyzes the current position. Is detected. The detected current position data is latitude and longitude data that are absolute positions at that time.
[0039]
The detected current position data is supplied to the arithmetic circuit 23. The arithmetic circuit 23 is a circuit that functions as a system controller that controls the operation of the navigation device 20. A CD-ROM (optical disc) in which road map data is stored is set, and the stored data in the CD-ROM is read out. A CD-ROM driver 24, a RAM 25 for storing various data necessary for data processing, a vehicle speed sensor 26 for detecting the movement of the vehicle on which the navigation device is mounted, and an operation key 27 are connected. When coordinate data of longitude and latitude such as the current position is obtained, the CD-ROM driver 24 is controlled to read road map data in the vicinity of the coordinate position. Then, the road map data read by the CD-ROM driver 24 is temporarily stored in the RAM 25, and display data for displaying the road map is created using the stored road map data. At this time, the display data is such that the map is displayed on a display scale (scale) set by operating the operation key 27 arranged at a predetermined position in the automobile.
[0040]
Then, the display data created by the arithmetic circuit 23 is supplied to the video signal generation circuit 28. The video signal generation circuit 28 generates a video signal of a predetermined format based on the display data, and the video signal is output to the output terminal. 20c.
[0041]
The video signal output from the output terminal 20c is supplied to the display device 40, and the display device 40 performs an image receiving process based on the video signal to display a road map or the like on the display panel of the display device 40.
[0042]
In addition to displaying a road map in the vicinity of the current position, a road map at a position instructed by operating the operation key 27 can be displayed based on the control of the arithmetic circuit 23. In addition, based on the operation of the operation key 27 and the like, specific coordinate positions such as “Destination”, “Departure Point”, “Route”, and “Home” can be registered. When the specific coordinate position is registered, the registered coordinate position data (longitude and latitude data) is stored in the RAM 25.
[0043]
Further, when the vehicle speed sensor 26 detects the traveling of the automobile, the arithmetic circuit 23 does not accept an operation other than a relatively simple operation among the operations of the operation keys 27.
[0044]
In addition, the navigation device 20 includes an autonomous navigation unit 29, calculates an accurate traveling speed of the automobile based on a pulse signal corresponding to the vehicle speed supplied from an engine control computer or the like on the automobile side, and autonomous navigation. The traveling direction is detected based on the output of the gyro sensor in the unit 29, and the current position is measured by autonomous navigation from the position determined based on the speed and traveling direction. For example, when the current position detection circuit 22 becomes incapable of position detection, positioning by autonomous navigation is performed from the position finally detected by the current position detection circuit 22.
[0045]
Also, a speech synthesis circuit 31 is connected to the arithmetic circuit 23, and when the arithmetic circuit 23 needs some instruction by voice, the voice synthesis circuit 31 executes a voice synthesis process for instructing the voice synthesis circuit 31. Sound is output from the speaker 32 connected to the circuit 31. For example, various instructions necessary for a navigation device such as “I approached the destination” and “The traveling direction is left” are given by voice. In the speech synthesis circuit 31, the speech recognized by the speech recognition device 10 is subjected to speech synthesis processing based on the supplied character data and output from the speaker 32 as speech. This process will be described later.
[0046]
Here, the navigation device 20 includes input terminals 20a and 20b to which longitude and latitude data output from the output terminals 10a and 10b of the voice recognition device 10, its associated data, and character code data are supplied. The longitude / latitude data obtained at 20a and 20b, the accompanying data and the character code data are supplied to the arithmetic circuit 23.
[0047]
When the longitude / latitude data and the like are supplied from the voice recognition device 10 side, the arithmetic circuit 23 performs control to read road map data in the vicinity of the longitude and latitude from the disk by the CD-ROM driver 24. Then, the road map data read by the CD-ROM driver 24 is temporarily stored in the RAM 25, and display data for displaying the road map is created using the stored road map data. At this time, the display data is displayed at the center of the supplied longitude and latitude, and the display data is such that the map is displayed at the scale (scale) indicated by the display scale attached to the longitude and latitude data.
[0048]
Based on this display data, the video signal generation circuit 28 generates a video signal and causes the display device 40 to display a road map at a coordinate position instructed from the voice recognition device 10.
[0049]
Further, when a character code of a word instructing the operation of the navigation device is supplied from the output terminal 10b of the voice recognition device 10, when the character code of the word instructing the operation is determined by the arithmetic circuit 23, the corresponding control is performed. Is performed by the arithmetic circuit 23. In this case, if the character code is a word code indicating a display position such as “destination”, “departure place”, “route”, or “home”, whether the coordinates of this display position are registered in the RAM 25. If it is registered after the determination, the CD-ROM driver 24 controls to read the road map data in the vicinity of the position from the disk.
[0050]
When character code data indicating the pronunciation of the recognized speech is supplied from the speech recognition device 10 to the arithmetic circuit 23, the speech synthesis circuit 31 synthesizes the words indicated by the character code, and the speech synthesis circuit The sound is output from the speaker 32 connected to 31. For example, when the speech recognition apparatus 10 recognizes speech as “Tokyo Bunkyo (Bunkyo-ku, Tokyo)”, a synthesis process for generating a speech signal that produces “Tokyo Bunkyo” based on the recognized character string data. Is performed by the voice synthesis circuit 31 and the generated voice signal is output from the speaker 32.
[0051]
In this case, in this example, when speech recognition is performed by the speech recognition device 10, the longitude and latitude data are supplied to the terminal 20 a of the navigation device 20, and the character indicating the pronunciation of the speech recognized at the terminal 20 b. The code data is supplied almost at the same time, but the arithmetic circuit 23 first performs speech synthesis on the words recognized by the speech synthesis circuit 31, and then the road based on the longitude and latitude data. A process for creating map display data is executed.
[0052]
Next, an operation in the case of performing road map display or the like using the voice recognition device 10 and the navigation device 20 of this example will be described. First, when the voice recognition operation in the voice recognition apparatus 10 is shown in the flowchart of FIG. 6, it is first determined whether or not the talk switch 18 is on (step 101), and it is determined that the talk switch 18 is turned on. In this case, the audio signal picked up by the microphone 11 during the ON period is sampled by the analog / digital converter 12, processed by the digital audio processing circuit 13, and converted into vector data (step 102). Based on this vector data, the speech recognition circuit 14 performs speech recognition processing (step 103).
[0053]
Here, it is determined whether or not the voice of the place name (that is, the place name registered in advance) stored in the voice recognition data storage ROM 15 is recognized (step 104), and when the voice of the registered place name is recognized, Character data for generating the recognized place name is read from the ROM 15 and output from the output terminal 10b (step 105), and the longitude and latitude data of the recognized place name is converted to the longitude-latitude conversion circuit 16 connected to the longitude-latitude conversion circuit 16. Reading from the storage ROM 17 (step 106). As the speech recognition of the place name here, the place name registered in the ROM 15 of this example is the name of the prefecture and the municipality in the country. For example, the voice “XX prefecture XX city” The voice “XX city XX ward” (here, in the case of a ward, it can be recognized even if the prefecture is omitted) is recognized.
[0054]
Then, the longitude and latitude data read out based on the recognized voice and the accompanying data are output from the output terminal 10a (step 107).
[0055]
If the voice of the registered place name cannot be recognized in step 104, it is determined whether or not the registered specific voice other than the place name has been recognized (step 108). Here, when the registered specific voice other than the place name is recognized, the character code corresponding to the identified voice is discriminated (step 109), and the discriminated character code is output from the output terminal 10b (step 110). ).
[0056]
If the registered specific voice other than the place name cannot be recognized in step 108, the process at this time is terminated. Alternatively, it is instructed to the navigation device 20 that voice recognition has failed, and a warning is given by voice synthesis in the voice synthesis circuit 31 or characters displayed on the display device 40.
[0057]
Next, when the operation on the navigation device 20 side is shown in the flowchart of FIG. 7, the arithmetic circuit 23 first determines whether or not the display mode of the current position is set (step 201). When it is determined that the current position display mode is set, the current position detection circuit 22 performs positioning of the current position (step 202), and the road map data in the vicinity of the determined current position is CD-ROM. (Step 203), a road map display process based on the read road map data is performed, and a road map at a coordinate position corresponding to the display device 40 is displayed (step 204).
[0058]
When it is determined in step 201 that the current position display mode is not set, or when the display of the road map at the current position in step 204 ends and the road map is displayed. Next, it is determined whether or not longitude and latitude data are supplied from the speech recognition device 10 via the input terminals 20a and 20b (step 205). Here, when it is determined that the longitude / latitude data and the accompanying character data are supplied, the phonetic synthesis character code supplied via the terminal 20b is first supplied to the voice synthesis circuit 31 for voice recognition. The speech recognized by the apparatus 10 is synthesized and output from the speaker 32 (step 206). Subsequently, road map data in the vicinity of the position indicated by the longitude and latitude data is read from the CD-ROM (step 207), road map display processing based on the read road map data is performed, and the display device 40 is displayed. A road map at the corresponding coordinate position is displayed (step 208).
[0059]
Then, when it is determined in step 205 that the longitude and latitude data are not supplied from the voice recognition device 10, or the display processing of the road map of the designated place name in step 208 is finished, and the road map is displayed. When it is determined, it is determined whether or not a character code that directly indicates the display position is supplied from the voice recognition device 10 via the input terminal 20b (step 209). When it is determined that the character code is supplied from the terminal 20b, the character code is supplied to the voice synthesis circuit 31, and the voice recognized by the voice recognition device 10 is output from the speaker 32 (step 210). Next, when it is determined in step 209 that the character code that directly indicates the display position (that is, words such as “Destination”, “Departure”, “Via”, “Home”, etc.) is indicated, these characters are indicated. It is determined whether or not the coordinate position is registered in the RAM 25 (step 211). If registered, the road map data in the vicinity of the position indicated by the longitude and latitude data as the registered coordinate position is obtained. The information is read from the CD-ROM (step 212), the road map is displayed based on the read road map data, and the road map at the coordinate position corresponding to the display device 40 is displayed (step 213). In the state of being performed, the process returns to the determination in step 201.
[0060]
When it is determined in step 209 that the character code that directly designates the display position is not supplied from the speech recognition apparatus 10, the arithmetic circuit 23 determines whether or not there is an operation for designating the display position by operating the operation key 27. (Step 214). If there is an operation for designating the display position, the detection data of the vehicle speed sensor 26 is determined to determine whether or not the vehicle is currently traveling (step 215). When the arithmetic circuit 23 determines that the vehicle is traveling, the operation at that time is invalidated and the process returns to the determination in step 201 (at this time, some warning may be performed).
[0061]
Then, when it is determined that the vehicle is not running, the process proceeds to step 211, and after determining whether or not there is a registered coordinate, if there is a registered coordinate position, display processing of the road map at that position After performing (steps 212 and 213), the process returns to the determination of step 201.
[0062]
If there is no registration of the coordinates of the corresponding position such as “Destination”, “Departure”, “Via”, “Home”, etc. in step 211, the speech synthesis by the speech synthesis circuit 31 or the display device 40 is performed. With the character display at, an unregistered warning is issued (step 216), and the process returns to the determination at step 201.
[0063]
In the flowchart of FIG. 7, processing related to map display has been described. However, when a character code based on a result of recognizing a voice instructing an operation other than map display is supplied from the voice recognition device 10 side, Based on the control of the arithmetic circuit 23, the corresponding processing is performed. For example, when the character code is supplied by recognizing “Imananji” or the like, the voice synthesizing circuit 31 synthesizes the sound that sounds the current time based on the control of the arithmetic circuit 23 and outputs it from the speaker 32. is there. For other commands, the voice of the answer is synthesized by the voice synthesizing circuit 31 and output from the speaker 32, or the display device 40 performs a corresponding display.
[0064]
By processing as described above, the display position can be freely set anywhere in the country by voice input, and a road map at a desired position can be easily displayed. That is, for example, the operator simply presses the talk switch 18 and speaks “XX prefecture XX city” or “XX city XX city” to the microphone 11 to recognize the voice and Since the road map is displayed, there is no need to give a position instruction or the like by key operation, and the navigation device can be operated even in a situation where key operation is difficult, for example. In this case, in this example, the place names recognized by the speech recognition device 10 are limited to the names of prefectures and municipalities in the country, so the number of recognized sounds is relatively small (about 3500). The time required for the place name to be recognized by the speech recognition circuit 14 in the speech recognition apparatus 10 in a short time with a relatively small amount of processing and for the map indicated by the input speech to be displayed is limited. It can be shortened, and the recognition rate itself is improved by limiting the number of place names to be recognized.
[0065]
Here, in this example, when the voice input described above is performed after the voice input described above is performed, the past recognition result is referred to during the recognition process. The process is shown in the flowchart of FIG.
[0066]
First, when a sufficient time (for example, several minutes) has elapsed since the previous speech recognition process, the history list in the speech recognition circuit 14 is cleared (step 401), and then the utterance starts, that is, the talk switch 18 Is determined to be on (step 402). If it is determined that the utterance has started, it is determined whether a predetermined time Th (here, 10 seconds) has elapsed since the previous utterance (step 403). If it has elapsed, the history list in the speech recognition circuit 14 is cleared (step 404). When the predetermined time Th has not elapsed since the previous utterance, the history list is not cleared.
[0067]
Then, based on the control of the voice recognition circuit 14, the input voice is recognized (step 405). Then, the candidate voice data obtained as a result of the recognition is collated with the voice data in the history list, and if the same data exists in the history list, the data is deleted from the recognized candidates ( Step 406). Next, it is determined whether or not the number of items in the history list is N (here, 5) or more (step 407). If it is not N or more (that is, if no utterance has been made N times consecutively), the process moves to step 408, and the recognition degree (matching degree) is the highest among the remaining candidate data at this time. The high data is supplied to the speech synthesis circuit 31 of the navigation device 20 as a recognized result, and is output from the speaker 32 as speech. If the recognized result is a voice indicating a region (that is, in the case of this example, a prefecture name and a city name), a map for displaying the city is displayed in the navigation device 20. In this process, the image is displayed on the display device 40 (step 409). Then, the result recognized at this time is added to the history list (step 410), and the process returns to step 402 and waits until the next utterance starts.
[0068]
When it is determined in step 407 that the number of items in the history list is N (that is, when utterances are made N times consecutively), the process proceeds to step 411 to display a candidate list. That is, the candidate data recognized in the recognition processing so far is read from the candidate list memory in the speech recognition circuit 14, and this data is supplied to the navigation device 20 and the video signal generation circuit 28 in the navigation device 20. Then, the video signal of the candidate list is generated, the video signal is supplied to the display device 40, and the candidate list is displayed on the display device 40.
[0069]
The candidate list at this time is displayed as shown in FIG. 9, for example. That is, the first to fifth candidates are displayed in descending order of the degree of coincidence (the lower candidates may be displayed by scrolling or the like). At this time, the place name candidates and the command candidates are displayed differently (for example, the display color of the characters is changed). In the example of FIG. 9, the font is changed and displayed.
[0070]
Then, at the first stage when this candidate list is displayed, a mark a indicating that it has been selected is assigned to the first candidate among the candidates in this list. The mark a indicating the candidate to be selected can be moved by a scroll operation by operating the operation key 27. Next, it is determined whether or not this scroll operation has been performed (step 412). Here, when the scroll operation is performed, the position of the mark a given to the candidate to be selected is moved (step 413).
[0071]
In this state, it is determined whether or not the determination button in the operation key 27 has been pressed (step 414). When it is determined that the determination button has been pressed, it is determined that the candidate indicated by the mark a has been selected, and data relating to the candidate (data on longitude and latitude, character data for voice output, etc.) is read out. An instruction is given to the voice recognition device 10 side, and the read data is supplied to the navigation device 20 side. Then, based on the supplied data, the speech synthesis circuit 31 performs speech synthesis processing to output the place name as speech from the speaker 32 (step 415). Then, based on the supplied longitude and latitude data, a video signal for displaying the road map at the corresponding position is created, and the selected candidate map is displayed on the display device 40 (step 416). Then, the result selected at this time is added to the history list (step 417), and the process returns to step 402 to wait until the next utterance starts.
[0072]
If it is determined in step 414 that the decision button is not pressed, then it is determined whether or not the utterance is started, that is, whether or not the talk switch 18 is turned on (step 418), and it is determined that the utterance has started. Then, the display of the candidate list is stopped, and the process returns to step 403. If it is determined in step 418 that the utterance is not started, whether or not a predetermined time Td (this time Td is about 10 seconds) has elapsed since the display of the candidate list in step 411 is started. Determination is made (step 419), and if the time Td has not elapsed, the process returns to step 412 to continue the state where the candidate list is displayed. If it is determined in step 419 that the predetermined time Td has elapsed, it is determined in step 412 whether or not a scroll operation has been performed (step 420). If a scroll operation has been performed, the process returns to step 412. The state where the candidate list is displayed is continued.
[0073]
When it is determined in step 420 that the scroll operation is not performed, the process proceeds to step 408, where the first result of the candidate list is output by voice, and the map of the first place name is displayed.
[0074]
By being controlled in this way, when the utterance is continuously performed within a certain time (for example, within 10 seconds), it is regarded as being rephrased, and the first candidate of the previous recognition result is excluded from the recognition target word. In other words, even if it is rephrased, the wrong place name is recognized again, and an accident in which the desired place name is not recognized can be prevented. For example, “Yokohama City Kanagawa Ward” and “Yokohama City Kanazawa Ward” exist as similar place names. Suppose it is recognized. At this time, if you do not deal with anything by repeating the same pronunciation, there is a high possibility that it will be mistakenly recognized as “Kanazawa Ward, Yokohama City” again. Since the pronunciation of “Kanazawa Ward” is already present, “Kanazawa Ward in Yokohama City” is excluded from the recognition target words. And when “Yokohama City Kanagawa Ward” was the second candidate, this “Yokohama City Kanagawa Ward” was moved up to the first candidate, and it was judged that “Kanagawa Ward Yokohama City” was recognized, When rephrased as a result, erroneous recognition is prevented, and the recognition rate can be improved accordingly.
[0075]
And, when there is repeated voice input for a predetermined time (here, 5 times) in a short time, the recognition target words recognized by the continuous input voice signal at this time are listed in descending order of recognition degree, The recognition state at that time can be easily determined, and words can be selected from the displayed list, so that it is possible to easily cope with a case where recognition by voice input is difficult by a simple operation.
[0076]
In this example, as a list display of recognition target word candidates at this time, a display state in the case where the recognition target word is a place name speech (displayed by normal characters in FIG. 9), and a command such as some command Since the display state in this case (display by white characters in FIG. 9) is changed, each type of sound can be quickly determined from the display. In the example of FIG. 9, the state of the character is changed. For example, the display color of the character (or around the character) in the case of a place name candidate and the character (or around the character) in the case of a command candidate The display color may be changed.
[0077]
In addition to changing the display state by the place name and the command as described above, the place name may be divided for each region and the display state may be changed for each division. That is, for example, the display color may be changed for each prefecture, or the display color may be changed for each region such as the Kanto region and the Tohoku region.
[0078]
In the flowchart of FIG. 8, the case where the selected candidate is a place name and the map display is performed based on the place name has been described. However, when the selected candidate is any command (command), a map is displayed. Instead of display, the corresponding command is executed.
[0079]
When the candidate list is displayed as a list as shown in FIG. 9, the recognition target words displayed in the list are sequentially output as speech from the speaker 32 by the speech synthesis process in the speech synthesis circuit 31. May be. By doing in this way, even if it does not look at the display of the display apparatus 40, the candidate of a recognition object word is known and the usability as a navigation apparatus improves.
[0080]
In the above-described embodiment, the place names recognized by the speech recognition apparatus are limited to the names of prefectures and municipalities in the country. However, more detailed place names and target names may be recognized. However, if the number of place names that can be recognized is increased, the amount of processing and processing time required for speech recognition are increased, and it is most preferable to limit the name to the name of the municipality in order to increase the recognition rate.
[0081]
In the above-described embodiment, the coordinates of the center for each name are used as latitude and longitude data indicating the absolute position of the local government office (city hall, ward office, town hall, village hall), but other positions are indicated. It may be data of latitude and longitude. For example, the latitude and longitude data of the center of the area (city / town / village) may be simply used.
[0082]
Further, instead of storing the latitude and longitude data of the center as described above, the coordinate position data of the east, west, north, and south ends of the area may be stored. In this case, it is only necessary to have four data of east-west longitude and north-south latitude.
[0083]
In the above embodiment, the recognized voice is converted into a character code by the voice recognition circuit 14 in the voice recognition device, and the character code is converted into longitude and latitude data by the longitude-latitude conversion circuit 16. However, the recognized voice may be directly converted into data of longitude and latitude. Even when the data is not directly converted into longitude and latitude data as described above, the ROM 15 and the ROM 17 for storing the conversion data may be configured by the same memory, for example, so as to share the storage area of the place name. .
[0084]
In the above embodiment, the present invention is applied to a navigation device using a positioning system called GPS, but it is needless to say that the present invention can also be applied to a navigation device using other positioning systems.
[0085]
【The invention's effect】
  Of the present inventionAccording to the navigation device, the display state of the recognition target word candidates is different for each candidate target word category, so that the candidates for the same category are easily understood and the display state is easy to see. For example, the display of the place name for displaying the map and the display of the command for instructing the operation etc. are displayed in different modes, so that the place name and the command are necessary from the display of the recognition target word candidates. It is possible to easily search for candidates to be performed, and the usability as a navigation device is improved.
[0088]
In addition, according to the navigation method of the present invention, the display state of recognition target word candidates is different for each candidate target word category, so that the candidates for the same category can be easily understood and displayed easily. . For example, the display of the place name for displaying the map and the display of the command for instructing the operation etc. are displayed in different modes, so that the place name and the command are necessary from the display of the recognition target word candidates. It is possible to easily search for candidates to be performed, and the usability as a navigation device is improved.
[0089]
Further, according to the automobile of the present invention, the display state of the recognition target word candidates is different for each category of the candidate target words, so that the candidates for the same classification are easy to understand, and the display state is easy to see. Even if it is difficult to see the display for a long time due to the driving situation of the car, it becomes easy to find the candidate you need, and it is possible to perform a good operation while ensuring the safety of driving the car Become.
[Brief description of the drawings]
FIG. 1 is a configuration diagram showing an embodiment of the present invention.
FIG. 2 is a perspective view showing a state in which the apparatus of one embodiment is incorporated in an automobile.
FIG. 3 is a perspective view showing the vicinity of a driver's seat when the device of one embodiment is incorporated in an automobile.
FIG. 4 is an explanatory diagram showing a storage area configuration of a speech recognition memory according to an embodiment.
FIG. 5 is an explanatory diagram showing a storage area configuration of a longitude / latitude conversion memory according to an embodiment;
FIG. 6 is a flowchart illustrating processing by speech recognition according to an embodiment.
FIG. 7 is a flowchart showing display processing in the navigation device according to the embodiment.
FIG. 8 is a flowchart showing processing when voice recognition is executed a plurality of times in one embodiment.
FIG. 9 is an explanatory diagram illustrating a display example of a candidate list according to an embodiment.
[Explanation of symbols]
10 Voice recognition device
11 Microphone
12 Analog / digital converter
13 Digital audio processing circuit (DSP)
14 Speech recognition circuit
15 Voice recognition data storage ROM
16 Longitude and latitude conversion circuit
17 Longitude and latitude conversion data storage ROM
18 Talk switch
20 Navigation device
23 Arithmetic circuit
24 CD-ROM driver
25 RAM
26 Vehicle speed sensor
27 Operation keys
28 Video signal generation circuit
31 Speech synthesis circuit
32 Speaker
40 Display device
50 cars

Claims (7)

Audio signal input means;
A speech processing unit for recognizing speech of a plurality of predetermined recognition target words including speech of a specific place name from the speech signal input to the speech signal input means;
A conversion unit that converts data of a specific place name recognized by the voice processing unit into absolute coordinate position data indicated by the place name;
Means for storing map data;
The map data at the position indicated by the coordinate position data converted by the conversion unit is read out from the storage means to create a map display video signal, and the recognition target word candidates recognized by the voice processing unit are displayed. Video signal creating means for creating a video signal;
When the video signal creation means creates a candidate video signal of the recognition target word, the classification of the recognition target word as the candidate is divided into a word indicating a place name and a word giving a command. navigation apparatus and a display control means for the video signal to be displayed in a manner different for each. The display mode that is different for each of the above categories is displayed with different character types.
The navigation device according to claim 1. Different display modes for each of the above categories are displayed in different display colors.
The navigation device according to claim 1. From the input voice signal, the voice of a plurality of recognition target words including a voice indicating a specific place name is recognized and processed,
This recognized place name data is converted into absolute coordinate position data indicated by this place name,
While displaying the map of the position shown by this converted coordinate position data,
Display the recognized recognition target word candidates,
When displaying the recognition target word candidates, each recognition target word category is classified into a word indicating a place name and a word giving a command, and each category is displayed in a different display mode. The navigation method to let you do. The display mode that is different for each of the above categories is displayed with different character types.
The navigation method according to claim 4. Different display modes for each of the above categories are displayed in different display colors.
The navigation method according to claim 4. In a vehicle equipped with a device for displaying a map on display means arranged at a predetermined position in the vehicle,
Audio signal input means;
A speech processing unit for recognizing speech of a plurality of predetermined recognition target words including speech of a specific place name from the speech signal input to the speech signal input means;
A conversion unit that converts data of a specific place name recognized by the voice processing unit into absolute coordinate position data indicated by the place name;
Means for storing map data;
The map data at the position indicated by the coordinate position data converted by the conversion unit is read out from the storage means to create a map display video signal, and the recognition target word candidates recognized by the voice processing unit are displayed. Creating a video signal and supplying the video signal to the display means;
When the video signal creation means creates a candidate video signal of the recognition target word, the classification of the recognition target word as the candidate is divided into a word indicating a place name and a word giving a command. A vehicle provided with display control means for making video signals to be displayed in different display modes.

Images