JP2000338993A - Voice recognition device and navigation system using this device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To perform a command input even if a user does not precisely memorize a command to improve the user-friendliness by storing a word dictionary data having the corresponding relation to each key word in a dictionary means. SOLUTION: A voice data inputted through a microphone 31 is outputted from an input signal processing part 32 to a recognition processing part 33. The recognition processing part 33 performs a collation by use of a dictionary data set in a dictionary management part 34 to execute a recognition processing. A word dictionary data having the corresponding relation to each key word is stored in the dictionary stored in the directionary management part 34. A recognition control part 35 performs the set of a key word related dictionary when the function of a navigation system cannot be driven from the recognition result, and retrieves operable commands from the key word relation. The retrieved operable commands are notified to an operation control part 15 and displayed on a display. A user selects the one desired by him from the operable commands and sounds it again.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a speech recognition apparatus which is effective for, for example, enabling a destination setting or the like in a navigation system to be input by speech, and a navigation system having the speech recognition apparatus.

[0002]

2. Description of the Related Art Conventionally, there has been proposed a speech recognition apparatus which compares an inputted speech with a plurality of pattern candidates to be compared which are stored in advance and determines a speech having a high degree of coincidence as a recognition result. It has already been put into practical use, and is used by a user to input a predetermined command by voice, such as an instruction to enlarge or reduce a map displayed in a navigation system, a destination setting, a route setting, and the like. ing. In particular, when the driver uses the in-vehicle navigation system, voice input does not involve button operation or screen gaze, so that it is effective because the safety is high even when the vehicle is running.

For example, as a specific example of setting a destination, consider a case where a voice input of "go to Nagoya Station" is required to instruct and input a command for setting a destination to Nagoya Station. In this case, it is troublesome for the user to have to pronounce each predetermined unit based on words such as “Nagoya Station”, “Ni”, and “Go”. Going to the station "is being considered. In this case, a dictionary for each command “go to Nagoya Station” is provided in the recognition dictionary.

However, in speech recognition, words that are not registered in the dictionary are not recognized, so that a desired operation cannot be instructed without correctly inputting the above-mentioned command. Of course, there is no problem if the user can input commands correctly, but if the contents of commands are complicated and diverse, there may be situations in which they cannot be remembered. In such a case, it is very inconvenient to refer to a manual or the like each time.

Accordingly, the present invention solves such a problem. Even if the user does not memorize the command accurately, if only the main part of the command content can be input by voice, the final command input is triggered by that. It is an object of the present invention to provide a speech recognition device with improved usability.

It is another object of the present invention to provide a navigation system using the voice recognition device.

[0007]

Means for Solving the Problems and Effects of the Invention In order to achieve the above object, according to the first aspect of the present invention, in the speech recognition apparatus, the dictionary means uses a comparison target pattern corresponding to each word as word dictionary data. When the user inputs a voice through the voice input unit, the recognition unit compares the input voice with a plurality of comparison target pattern candidates stored in the dictionary unit and has a high matching degree. The thing is regarded as the recognition result. Then, the recognition control unit outputs at least a recognition result obtained by the recognition unit to the external device.

[0008] Here, the dictionary means is adapted to divide a command content necessary for specifying a function to be executed by an external device into two types of keywords, ie, an operation target command and an operation detail command, and correspond to each keyword. Word dictionary data is stored with a relationship. The operation target command is a command for specifying an operation target, and conceptually corresponds to “what” of “what to do”. On the other hand, the operation detailed command is a command for specifying the content to be performed by the operation target, and conceptually corresponds to “what to do” of “what to do”. However, various classification methods are conceivable. For example, in terms of navigation,
"Nagoya Station (place name)" is the operation target command,
There is a general command that uses “go” as an operation detail command, and a seemingly “VICS display” keyword in which an operation target command and an operation detail command are combined can also be treated as an operation detail command. . A plurality of operation details commands such as “display traffic jam”, “display empty road”, and “display parking lot” can be associated with the operation target command “display VICS”.

The determination means in the recognition control means determines whether or not the function of the external device can be executed only by the recognition result by the recognition means. If it is determined that the function of the external device can be executed, And outputs only the recognition result to the external device. On the other hand, if it is determined that the command cannot be executed, an operation target command or an operation detailed command corresponding to the recognition result is extracted based on the correspondence between the keywords in the dictionary unit. For example, when the external device is a navigation device and the “VICS display” in the above example is input by voice, the function cannot be driven by itself, so “VIS display” is used.
An operation detailed command (for example, the above-described “congestion display”, “vacant road display”, “parking lot display”, etc.) corresponding to the operation target command “CS display” is extracted. And
Either the user is notified via the notification means of the voice recognition device itself, or an instruction is given to the external device to notify the user via the notification means of the external device.

It is conceivable to use a means for notifying by display as the notifying means. Of course, a voice or other notification method may be adopted. However, when there are a plurality of corresponding operation detailed commands as described above, a list thereof is displayed to make it easier for the user to select from the list. Is preferred.

The operation target command can be traced in reverse from the operation detailed command. For example, if a keyword classified as the above-described operation detail command “parking lot display” is input by voice, if the correspondence is traced in reverse, “parking lot information provided as VICS information” Whether the display is "display", "parking space fully equipped in a restaurant", or "parking near the current location" is displayed. Therefore, it is sufficient to notify the user by displaying them in a list in the same manner.

As described above, according to the voice recognition device of the present invention, when one of the operation target command and the operation detail command is input by voice by the user, the corresponding operation detail command or operation target command is output. To notify the user, the user who has recognized the notification result can input a desired command again. In other words, even if the user does not memorize the command accurately, if only the main part of the command content can be input by voice, the user can input the final command as a trigger, thereby improving usability.

When the determining means determines whether or not the function of the external device can be executed only by the recognition result by the recognizing means, the determination is made based on the state of the external device. Can be considered. For example, when the external device is a navigation device and is set to a mode for providing VICS information, even if only the operation detailed command of “display parking lot” described above is input by voice, the operation target is set to VICS display. Therefore, it is determined that the function can be driven as it is. Similarly, if the navigation device is in the destination setting mode, it is determined that the function can be driven only by the operation target command “Nagoya Station”.

When the function of the external device cannot be executed only by the recognition result, the recognition control means operates the command or the operation target corresponding to the recognition result based on the correspondence between the keywords in the dictionary means. The detailed command is extracted. At this time, the following dictionary management may be performed by the dictionary management unit provided in the recognition control unit. That is, of the word dictionary data stored in the dictionary means, only the word dictionary data corresponding to the operation target command or the operation detail command extracted based on the correspondence relationship between the keywords is recognized by the recognition means. The dictionary to be validated as data is narrowed down. In this way, erroneous recognition for a second speech input is reduced, and more appropriate speech recognition can be realized.

If the dictionary management means narrows down the dictionary and then performs normal speech recognition, the data is not appropriate word dictionary data. When it is determined that the function of the external device can be executed only by the determination unit, the dictionary narrowing may be canceled.

When the speech recognition device according to any one of claims 1 to 4 is used for a navigation system, it is conceivable that the speech recognition device is configured as shown in claim 5. In other words, the voice recognition device according to any one of claims 1 to 4 and a navigation device are provided, and the voice input means of the voice recognition device needs to be specified at least when the navigation device performs a navigation process. This is used for the user to input an instruction of predetermined navigation processing-related data by voice.

In this case, the "predetermined navigation processing-related data" may be a typical destination. The destination may be a place name itself, or a facility or store name. In some cases. Also,
In addition, various instructions that need to be specified in performing the navigation process, such as selection of conditions related to route search and the above-described VICS display, are included.

Particularly, since a general navigation device can display a map or a menu on a display device, the general navigation device can display an operation target command or a command in response to a notification instruction from a voice recognition device. It is conceivable to make it function as a notifying means for notifying the operation detailed command. In this case, the voice recognition device itself does not need to have the notification unit.

[0019]

Embodiments of the present invention will be described below with reference to the drawings. It is needless to say that the embodiments of the present invention are not limited to the following examples, and can take various forms as long as they belong to the technical scope of the present invention.

FIG. 1 is a block diagram showing a schematic configuration of an on-vehicle navigation system 1 to which the voice recognition device 30 is applied. The navigation system 1 includes an operation switch unit 4 including a voice recognition device 30, a mechanism switch 2, and a remote control switch 3, and an operation control unit that inputs an operation state and the like from the operation switch unit 4 and controls the entire navigation system. 5. Current position calculation unit 6 for calculating the current position of the vehicle, route calculation unit 7 for calculating an appropriate route (recommended route) to the destination based on the destination set by the user, and route calculation unit 7 Based on the calculated recommended route, a guidance control unit 8, which performs a control process of providing a user with guidance necessary for smooth driving of the vehicle by voice or a simple map, a map data search unit 9, external information input / output The apparatus includes a device 10, an audio output control unit 11, a speaker 12, a display control unit 13, and a display 14. The operation control unit 5 is configured as a normal computer, and includes a well-known CPU, ROM, RAM, I / O, and a bus line for connecting these components.

The current position calculating section 6 detects a vehicle position based on radio waves from a well-known gyroscope, a distance sensor and a satellite, for example.
), and a GPS receiver for the itioning system). Since each of these sensors and the like has an error having a different property, a plurality of sensors are used while interpolating each other. It should be noted that depending on the accuracy, it may be constituted by a part of the above, and furthermore, a geomagnetic sensor, a rotation sensor for steering, a wheel sensor for each rolling wheel, or the like may be used.

The map data search unit 9 is a device for inputting various data including so-called map matching data, map data and landmark data for improving the accuracy of position detection. As a medium, CD-R
Generally, an OM or a DVD is used, but another medium such as a memory card may be used.

On the other hand, the external information input / output device 10 receives an FM broadcast signal via a radio antenna (not shown), or a VICS (Vehicle Information Format) disposed near a road.
ion and Communication System) Receives a radio beacon signal and an optical beacon signal from a fixed station for service. The received information is sent to the operation control unit 5 and processed. In addition, information can be transmitted to the outside.

The display 14 is constituted by, for example, a color display. The screen displays a vehicle current position mark input from the current position calculation unit 6, a map data input from the map data search unit 9, and a map data. It is possible to superimpose and display additional data such as a guidance route displayed above and a mark of a set point described later.

As the mechanism switch 2, for example, a touch switch or a mechanical switch integrated with the display 14 is used, and is used for a destination for route calculation and various inputs. Further, the same instruction input as that of the mechanism switch 2 can be input via the remote control switch 3. In the voice recognition device 30, the mechanism switch 2 or the remote control switch 3 is used to manually specify a destination or the like, whereas the user can similarly input a destination by voice. This is a device that allows the user to give an instruction. Note that the operation switch unit 4 does not necessarily have to include all of the voice recognition device 30, the mechanism switch 2, and the remote control switch 3, and any one of them can input a desired instruction. However, in the present embodiment, it is assumed that three are provided for convenience.

Next, the speech recognition device 30 constituting a part of the operation switch section 4 will be described in more detail with reference to FIG. The voice recognition device 30 includes a microphone 31 as “voice input means”, an input signal processing unit 32 that converts a voice signal input via the microphone 31 into a form capable of data processing by A / D conversion or the like, and “ A recognition processing unit 33 as a "recognition unit", a dictionary management unit 34 as a "dictionary unit" and a "dictionary management unit", and a recognition control unit 35 as a "recognition control unit" are provided.

Although not shown in FIG. 2, the voice input method according to the present embodiment uses a PTT (Push-To-
Talk) inputting a voice via the microphone 31 while pressing the switch. Specifically, the input signal processing unit 32 determines whether or not the PTT switch has been pressed. If the PTT switch has been pressed, the input signal processing unit 32 executes a voice input process via the microphone 31. If not, the voice input process is not executed. Therefore, only the voice data input via the microphone 31 while the PTT switch is pressed is output to the recognition processing unit 33.

The recognition processing unit 33 compares the voice data input from the input signal processing unit 32 with the comparison target pattern candidates in the set dictionary data, and determines a higher comparison target pattern having a high degree of coincidence with the recognition control unit 35. Output to The recognition of the word sequence in the input speech is performed by sequentially performing acoustic analysis on the speech data input from the input signal processing unit 32 to extract an acoustic feature (for example, cepstrum), and the acoustic feature obtained by the acoustic analysis. Get time series data. And the well-known D
This time series data is divided into several sections by the P matching method, and it is determined which word each section corresponds to stored in the dictionary data.

It should be noted that the recognition processing unit 33 switches the recognition control unit 35
Is not necessarily one. For example, there may be a plurality of vocabulary words ranked higher in the similarity determination result in the recognition processing unit 33 or a plurality of recognized vocabulary words. Since the voice recognition technology is a pattern matching between a registered recognition target word and a fetched voice, it is common to output a plurality of words having a high degree of matching as a recognition result. In addition, the recognition processing unit 33 outputs to the recognition control unit 35 a "recognition degree" set for each recognition result. For example, when a prefecture name is used as a recognition dictionary, if the patterns of "Wakayamaken" and "Okayamaken" are similar, the above two may be output as a recognition result in response to a user utterance of "Okayama Prefecture". In that case, "Wakayamaken" is 90%,
"Okayamaken" is 80%. In addition,
This specific number does not represent the actual recognition level,
It is used only for convenience of explanation.

Then, the recognition control unit 35 outputs the recognition result to the operation control unit 5, and acquires the state from the operation control unit 5. This state means that the navigation system 1
Gets the setting status of the current state. Then, based on the acquired state, the recognition processing unit 3
It is determined whether or not the navigation function can be driven based on the recognition result from 3.

The recognition control unit 35 includes a dictionary management unit 34
Request an operation candidate corresponding to the recognition result. Here, the dictionary stored in the dictionary management unit 34 will be described. This dictionary stores word dictionary data having a correspondence relationship between each keyword when command contents necessary for driving the navigation function are divided into two types of keywords, an operation target command and an operation detail command. Have been. Specifically, as shown in FIG. 3B, the operation target commands include a map display, a VICS display, a restaurant display, a station display, an estimated arrival time display, a destination display, a search screen display, a peripheral facility display, and the like. is there. On the other hand, detailed operation commands include traffic jam display, empty road display, regulation display, parking lot display, all road display, high speed limitation, general limitation, and the like. FIG. 3B shows that the VICS display corresponds to the above-described map display, VICS display, restaurant display, and the like.
Correspondence is set for each of the other operation target commands such as map display and restaurant display.
As a matter of course, the parking lot display of the operation detailed command has a correspondence relationship not only with the VICS display of the operation target command but also with the restaurant display and the peripheral facility display.

When requested by the recognition control unit 35 for an operation candidate corresponding to the recognition result, the dictionary management unit 34 presents the corresponding operation candidate to the recognition control unit 35 based on the correspondence between the keywords. Then, the recognition control unit 35
The presented operation candidate is further notified to the operation control unit 5. Then, the operation control unit 5 displays the notified operation candidates on the display 14 to notify the user.

Next, the operation of the navigation system 1 of this embodiment will be described. In addition, since the part related to the voice recognition device 30 is a feature, the general operation of the navigation system will be briefly described, and then the operation of the part related to the voice recognition device 30 will be described in detail.

When the driver selects the route information display processing from the menu displayed on the display 14 by using the mechanism switch 2 or the remote control switch 3 after the power-on of the navigation system 1 to display the guide route on the display 14. Alternatively, by inputting a desired menu by voice through the microphone 31 through the voice recognition device 30, the same instruction as that selected through the switches 2 and 3 described above is operated and controlled by the recognition control unit 35. When the processing is performed on the unit 5, the following processing is performed.
That is, when the driver inputs the destination by voice or switch operation based on the map on the display 14, the current position of the vehicle is obtained by the current position calculation unit 6, and the distance between the destination and the current position is calculated by the Dijkstra method. The cost is calculated, and a process of obtaining the shortest route from the current position to the destination as a guidance route is performed. Then, the guidance route is displayed on the road map on the display 14 to guide the driver to an appropriate route. The calculation process and the guidance process for obtaining such a guide route are generally well-known processes, and a description thereof will be omitted.

The operation control unit 5 also performs processing based on information received from a VICS service fixed station via the external information input / output device 10. For example, it performs traffic regulation, traffic congestion, guidance on vacant roads, and parking lot guidance. In addition,
In this case, it is conceivable that only one-way information transmission from the VICS service fixed station to the navigation system 1 side is considered. However, the current position is notified from the navigation system 1 side to the service fixed station, and the service fixed station side is notified. , The above traffic restrictions in effect at the notified location,
It is also preferable that traffic jams, vacant roads and parking lots are selected and transmitted to the navigation system 1 side. This is because it is possible to more accurately obtain truly necessary information.

Next, the operation of the speech recognition apparatus 30 will be described with reference to the flowchart of FIG. In the first step S10 upon activation, the state of the navigation system 1 is captured. For example, a state where a screen is displayed for setting a destination, a state where a user is requested to input a destination by voice, and the like are captured.

Then, in S20, it is determined whether or not the operation detailed command is currently being recognized. S9 to be described later
0, the operable command is notified to the operation control unit 5, and the notification of the requested function in S100 has not been made to the operation control unit 5 after that. Is ".

If the operation detailed command is currently being recognized (S20: YES), the dictionary for voice recognition in the dictionary management unit 34 is narrowed down (S30). (S20: NO), normal dictionary setting is performed without narrowing down the dictionary for voice recognition in the dictionary management unit 34 (S35). The narrowing down of the recognition dictionary in S30 will be described later.

When the preparation for speech recognition is completed, speech recognition is performed in S40, and it is determined in S50 whether the speech recognition has been successful. The voice recognition is performed as follows. As described above, only the audio data input via the microphone 31 while the PTT switch (not shown) is being pressed is output from the input signal processing unit 32 to the recognition processing unit 33. Therefore, when voice data is input from the input signal processing unit 32, the recognition processing unit 33 performs matching by using the dictionary data set by the dictionary management unit 34 and executes recognition processing. Generally, a plurality of recognition results are output as described above.
Are also output as a set.

Then, there is an abnormality in taking in the audio data.
Alternatively, as a result of the collation using the dictionary data, if a defect such as no match is detected, the speech recognition is determined to have failed (S50: NO), and the processing routine is terminated as it is. On the other hand, if the speech recognition is successful (S
50: YES), the recognition control unit 35 determines whether the function of the navigation system 1 can be driven based on the recognition result (S60). For example, the navigation system 1
When the user is in the destination setting mode at that time, if "Nagoya Station" is voice-inputted, it is determined that the function can be driven only by the recognition result of Nagoya Station (S60: Y
ES). Therefore, the process shifts to S100 to notify the required function. In this case, only the recognition result of "Nagoya Station" need be sent.

However, in the same situation (when the destination setting mode is set), even if only "VICS display" is input by voice, the function cannot be driven as it is. Therefore, when the function cannot be driven only from the recognition result (S60:
NO), the process proceeds to S70, a keyword-related dictionary is set, and a search for an operation detailed command is performed in S80.

This point will be specifically described with reference to FIG. As shown in FIG. 4A, when a voice input of “VICS display” is made by the user, FIG.
By referring to the recognition dictionary as shown in FIG.
As shown in (c), a recognition result of “VICS display” is obtained. However, in this case, "VICS display"
Since the function cannot be driven only by the recognition result of
An operable command is searched from the keyword relation shown in FIG. More specifically, in FIG. 4B, “congestion display”, “free road display”, “regulation display”, “parking lot display”, and “all roads” are linked to the keyword “VICS display”. “Signage”, “high-speed limited”, and “general limited” are searched (see FIG. 4D). Therefore, in S90 of the flowchart of FIG. 3, the retrieved operable command is notified to the operation control unit 5, and the present processing routine is ended once.

The operation control unit 5 displays the notified operable command on the display 14 and presents it to the user. The user who sees the presentation selects a desired one from the operable commands and speaks again.
In this situation, since an affirmative determination is made in S20 of the flowchart in FIG. 3, the recognition dictionary is narrowed down in S30. In other words, in this case, "congestion display", "vacant road display", which is linked to "VICS display",
Only "regulation display", "parking lot display", "all road display", "high speed limited", and "general limited" are prepared as dictionaries to be recognized. Since the recognition process of S40 is performed in this state, erroneous recognition hardly occurs.

As shown in FIG. 4E, when the user utters "congestion display", the recognition process is performed by referring to the narrowed down dictionary as shown in FIG. 4F.
It is possible to appropriately obtain the recognition result of the traffic jam display. Since the "congestion display" as the recognition result in this case is "VICS congestion display" as the operation command, S1
At 00, the required function is notified to the operation control unit 5.

As described above, in the voice recognition device 30 of the navigation system 1 of the present embodiment, even if the navigation function cannot be driven only by the content of the first voice input, the input content and the keyword related An operable command is searched for, displayed on the display 14 and presented to the user. Therefore, the user who saw the displayed content,
The desired command among them can be input again by voice. In other words, even if the user does not memorize the command accurately, if only the main part of the command content can be input by voice, the user can input the final command as a trigger, thereby improving usability.

Incidentally, in the case of this embodiment, S30 in FIG.
When the dictionary is narrowed down in step S5, and then when normal speech recognition is performed (S20: NO), the normal dictionary is set in step S35, so that there is no problem. Further, in the specific example shown in FIG. 4, when only the operation target command “VICS display” is input by voice, an operation detailed command (for example, the “congestion display” described above,
Although “vacant road display” and “parking lot display” are extracted, the operation target command can be traced from the operation detailed command. For example, the above-mentioned "parking lot display"
Is input, the correspondence is reversed.
In FIG. 4B, only the correspondence between the operation target command “VICS display” and the operation detail command is explicitly shown,
Correspondence with the operation detailed command is similarly set for other operation target commands such as map display, restaurant display, station display, and peripheral facility display.

Therefore, for example, when a parking lot is displayed in the corresponding operation detail command for the restaurant display, the station display, and the peripheral facility display, when a voice input of “parking lot display” is input, a keyword is displayed. By tracing the relation in reverse, it is possible to display “parking information provided as VICS information”, “parking provided at a restaurant”, or “parking existing around the current location”.
Can be searched for an operable command. Therefore, if the information is similarly displayed on the display 14 and presented to the user, the user who has viewed the displayed content will
A desired command among them can be input again by voice.

[Others] (1) In the above-described embodiment, when the navigation function cannot be driven only by the content first input by voice, an operable command having a keyword relationship with the input content is searched in the dictionary and displayed. Although the information is displayed on the display 14, for example, the notification may be made by voice from the speaker 12. However, when notifying a plurality of corresponding operable commands as described above, it is considered preferable that a list is displayed on the display 14 so that the user can easily select the command from the viewpoint of usability.

(2) In the above-described embodiment, an example in which the voice recognition device 30 is applied to the on-vehicle navigation system 1 has been described. However, the application destination is not limited to the on-vehicle navigation system. Other systems are also conceivable.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a schematic configuration of a navigation system as an embodiment.

FIG. 2 is a block diagram illustrating a schematic configuration of a speech recognition device according to the embodiment.

FIG. 3 is a flowchart illustrating a process performed by the voice recognition device according to the embodiment;

FIG. 4 is an explanatory diagram showing transition of a voice dialogue.

[Explanation of symbols]

Reference Signs List 1 navigation system 2 mechanism switch 3 remote control switch 4 operation switch unit 5 operation control unit 6 current position calculation unit 7 route calculation unit 8 guidance control unit 9 map data search unit 10 external information input / output Unit 11 Voice output control unit 12 Speaker 13 Display control unit 14 Display 30 Voice recognition device 31 Microphone 32 Input signal processing unit 33 Recognition processing unit 34 Dictionary management unit 35 Recognition control unit

──────────────────────────────────────────────────の Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G10L 21/06 G10L 3/00 S 5J062 15/00 551Q 9A001 // G01S 5/14 F-term (Reference) 2C032 HC16 HC21 2F029 AA02 AB01 AB07 AB09 AC02 AC04 AC13 AC14 AC18 5D015 AA04 KK01 LL05 LL06 5D045 AB17 5H180 AA01 BB02 BB04 BB12 BB13 EE01 FF04 FF05 FF12 FF13 FF22 FF25 FF27 AH05 FF10 AH05 FF10

Claims (6)

[Claims] 1. A dictionary means for storing a comparison target pattern corresponding to each word as word dictionary data, a voice input means for inputting a voice, and a voice input via the voice input means. A recognition unit that compares a pattern with a high degree of coincidence with a plurality of comparison target patterns stored in advance in the dictionary unit as a recognition result; and a recognition unit capable of executing at least a process of outputting the recognition result by the recognition unit to an external device. A voice recognition device including a control unit, wherein the dictionary unit divides a command content necessary for specifying a function to be executed in the external device into two types of keywords, an operation target command and an operation detail command. The word dictionary data is stored so as to have a correspondence relationship between the respective keywords in the case, and the recognition control unit controls only the recognition result by the recognition unit. And determining means for determining whether or not the function of the external device is executable. If the determining means determines that the function of the external device is executable, only the result of the recognition is determined. Output to an external device, while if it is determined that it is not executable,
Based on the correspondence between the keywords in the dictionary means, extract the operation target command or operation detailed command in correspondence with the recognition result, and notify the user via the notification means of the voice recognition device itself, Alternatively, a voice recognition device for instructing the external device to notify a user via a notification unit included in the external device. 2. The speech recognition device according to claim 1, wherein the determination unit determines whether or not the function of the external device can be executed only by a recognition result by the recognition unit based on a state of the external device. A speech recognition device characterized by performing. 3. The speech recognition device according to claim 1, wherein said recognition control means further extracts, based on a correspondence relationship between said keywords, from word dictionary data stored in said dictionary means. Speech recognition characterized by comprising dictionary management means for narrowing down a dictionary for validating only word dictionary data corresponding to the operation target command or the operation detail command as word dictionary data at the time of recognition by the recognition means. apparatus. 4. The speech recognition apparatus according to claim 3, wherein said dictionary management means is adapted to execute the function of said external device only when a result of recognition by said recognition means is executable by said determination means. Is a speech recognition device for canceling the dictionary narrowing down. 5. The voice recognition device according to claim 1, further comprising: a navigation device as the external device to which the voice recognition device outputs a recognition result. The voice input means is used by a user to input at least an instruction of predetermined navigation processing-related data which needs to be specified when the navigation device performs the navigation processing. A navigation system characterized by the following. 6. The navigation system according to claim 5, wherein the navigation device is capable of displaying a map or a menu on a display device, and the display device is configured to control the operation target in response to a notification instruction from the voice recognition device. A navigation system characterized by functioning as a notifying means for notifying a command or an operation detailed command.