JPH1138995A - Speech recognition device and navigation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow an unaccustomed user to easily use a speech recognition device by informing the user of contents of a predetermined guide when there is no speech input even if a predetermined time has passed from a point in time when a speech input period is specified to start. SOLUTION: Having informed of contents A of a guide, a control part 38 judges whether or not a push-to-talk(PTT) switch 36 is turned on, and following this, it judges whether it is a click operation. When it judges that it is not a click operation, it judges whether there is a speech input. When there is no speech input, the control part judges whether PTT switch 36 has been turned off, and if it remains being turned on, it is judged whether a predetermined time Ta has passed. And, if the predetermined time Ta has passed, the contents C of the guide are informed. Concrete contents of the contents C of this guide are 'Please, start with a prefecture name when you input your destination'. Thus, a user, who wants to set a destination, is informed of an input method.

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, for example, for a user to input a destination name to be set in a navigation system by voice. 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.

In particular, since it is burdensome for the voice recognition apparatus to always prepare for voice input, the user himself / herself specifies the start and end timings of the period for inputting the voice to be recognized. Such a configuration is often employed. As a means for specifying the input period, for example, a PTT (Push-To-Talk) switch is used. That is, the recognition process for the input voice is executed only when the PTT switch is pressed, and the input voice that is not actually required is not processed.

[0004] Such a speech input method having a high value of use has the following problems if the user is not accustomed to the speech recognition system itself. For example, there is a problem that the sound is inappropriately input to the device due to the lack of understanding of the usage method, and the effectiveness is not improved, or a problem that the device itself is not used in extreme cases. There is. In addition, since the user understands the usage method to some extent but is not familiar with the specific usage method, for example, there is a problem that words to be input do not immediately appear and the user is silent.

The present invention solves such a problem, and a user-friendly voice recognition device which can be easily used even by a user unfamiliar with the method of using the voice recognition device, and a voice recognition device which is more convenient. An object of the present invention is to provide a navigation system provided with the navigation system.

[0006]

According to a first aspect of the present invention, there is provided a voice recognition apparatus for inputting a voice, and the voice recognition apparatus uses the voice input means. Input period specifying means provided for the user himself to specify the start and end of the period for inputting the voice to be recognized, and the voice input means within the input period specified by the input period specifying means. A recognition unit that compares a voice input through a plurality of comparison target pattern candidates stored in advance in a dictionary unit and determines a recognition result having a high degree of coincidence, and a notification that notifies the recognition result by the recognition unit Means, and when a predetermined confirmation instruction is given after the recognition result is notified by the notifying means, a fixed post-processing means for executing a predetermined post-confirmation processing assuming that the recognition result is fixed. A voice recognition device comprising: a predetermined guide when there is no voice input via the voice input means even when a predetermined time has elapsed after the start of the voice input period is specified by the input time period specifying means. It is characterized by having guide means for informing the contents.

[0007] According to the voice recognition device of the first aspect,
The user inputs voice through voice input means such as a microphone, for example. However, an input period specifying means is provided for the user to specify the start and end of the period for inputting the voice to be recognized. The voice input during the input period specified by the input period specifying means is to be recognized. Then, the recognizing means compares the input voice with a plurality of comparison target pattern candidates stored in the dictionary means in advance, and determines a recognition result having a high degree of coincidence, and reports the recognition result by the notifying means. And
If a predetermined confirmation instruction is issued after the notification of the recognition result, the post-confirmation processing means executes the predetermined post-confirmation processing assuming that the recognition result has been confirmed.

When such basic speech recognition processing is executed, the voice input via the voice input means continues even if a predetermined time has elapsed after the start of the voice input period is specified by the input period specifying means. When there is no such information, the guide means notifies at least the predetermined guide content by voice. In other words, the fact that the start of the voice input period is specified by the input period specifying means is inferred that the user intends to input voice. Therefore, as one of the reasons why there is no voice input even after the lapse of a predetermined time even in such a state, the user wants to perform voice input, but how to input is desired. The understanding may not be enough. For this reason, a predetermined guide content is notified to a user who is having difficulty in using the guide.

[0009] In this case, there are various types of predetermined guide contents. Therefore, here, some examples will be described on the assumption that a voice recognition device is applied for voice input of a destination or the like in a navigation system. First, if you do not know what you can input by voice to the navigation system, for example, a setting that can be instructed by voice input, such as "You can set the destination" One that guides the item itself is conceivable. In this case, the content may be changed depending on the stage of a series of processes in the system (in this case, the navigation device) to be instructed by voice input. For example, assuming that setting a route to a destination is a series of processing, after the above-described destination is set, for example, a condition for setting a route such as whether to specify a waypoint is further specified. May be. Therefore, if the destination has already been set and there is no voice input within the specified time after the start of the above-mentioned voice input period has been specified, the message "You can specify the waypoint What is necessary is just to inform the guide contents such as ".

[0010] Further, it is assumed that the user knows what he / she can input to the navigation system by voice, but does not know the specific input method. In this case, it is conceivable that the explanation of the input method is reported as the guide content, such as "Please input from the prefecture name when setting the destination".
Also, even if the user still does not fully understand how to enter, and if it is not possible to enter it, please specify, for example, "Please enter Showa-cho, Kariya city, Aichi prefecture" It is conceivable to report a simple input example as guide content. This allows the user to know the specific input method,
If the user is notified of a specific example, he or she can easily input a desired destination.

Of course, the contents of the guide described above and above are merely examples, and it is sufficient to provide appropriate guide contents suitable for the processing of the navigation system to be applied. What is necessary is just to devise it so that it may adapt to processing.

As described above, according to the speech recognition apparatus of the present invention, even a user who is not used to using the speech recognition apparatus can easily use the speech recognition apparatus, and is more user-friendly. An excellent device can be provided. In order to provide a guide function for a user who is not accustomed to the usage method, as described above, the voice input unit is not used even if a predetermined time has elapsed after the start of the voice input period is specified by the input period specifying unit. Instead of notifying the guide contents when a situation where there is no voice input via the terminal occurs, it may be possible to cope with a case where the user actively wants to know the guide contents.

According to a second aspect of the present invention, there is provided a voice recognition apparatus for inputting a voice and starting a period for inputting a voice to be recognized using the voice input means. And an input period specifying means provided for the user himself to specify the end, and a voice input through the voice input means within the input period specified by the input time specifying means, is previously stored in the dictionary means. Recognition means for recognizing a result having a high degree of coincidence with a plurality of stored comparison target pattern candidates as a recognition result, notification means for notifying the recognition result by the recognition means, and a recognition result notified by the notification means. And a post-confirmation processing means for executing predetermined post-confirmation processing assuming that the recognition result has been finalized when a predetermined finalization instruction is issued after the input. When a predetermined guide request other than the designation of the start and end of the normal voice input period is made by the interval designating unit, there is provided a guide unit for notifying the predetermined guide content according to the guide request. .

According to the second aspect of the present invention, the user inputs the voice through the voice input means such as a microphone. The start and end of the period for inputting the voice to be recognized. Is provided by the user himself / herself, and the voice input during the input period specified by the input period specifying means is to be recognized. Then, the recognizing means compares the input voice with a plurality of comparison target pattern candidates stored in the dictionary means in advance, and determines a recognition result having a high degree of coincidence, and reports the recognition result by the notifying means. Then, when a predetermined confirmation instruction is given after the recognition result is notified, the post-confirmation processing means executes the predetermined post-confirmation processing assuming that the recognition result has been confirmed.

When performing such basic speech recognition-related processing, if a predetermined guide request other than the designation of the start and end of a normal speech input period is made by the input period designating means, a guide is issued. The means notifies predetermined guide contents according to the guide request. here,
"When a predetermined guide request other than the designation of the start and end of the normal voice input period is made" means, for example, the following case. To specify the start and end of the normal voice input period, voice input is performed after the start is specified, and then the end is specified. Therefore, the interval from the start to the end is set to, for example, 1 second or less. It is hard to imagine that.
Therefore, for example, in the case of a so-called “click operation” in which the interval from the start designation to the end designation is relatively short (for example, 0.5 seconds or less), it is not the designation of the start and end of the voice input period, but the guide It is determined that the operation is for the request. Of course, if the device side is a special operation that cannot be designated as the start and end of the normal voice input period, any other operation may be an operation for a guide request. For example, a so-called "double click" can be applied.

According to the speech recognition apparatus of the second aspect,
If the user wants to know the contents of the guide positively, a predetermined guide request may be made by the input period designating means, and a guide function for a user unfamiliar with the use method can be exhibited. In addition, a special configuration is not required only for specifying the guide request, and the input period specifying means required for basic processing for voice input can be used for specifying the guide request. Also contributes to simplification.

There are various types of predetermined guide contents in this case. However, the above description and the description given on the assumption that the voice recognition device is applied to input a destination or the like in the navigation system by voice are described. In this case, it is considered that the contents indicated by are particularly effective. In other words, if you do not know what you can input by voice to the navigation system, the setting items that can be instructed by voice input, such as "You can set the destination" It is for guiding. Also in this case, the content may be changed depending on the stage of the series of navigation processing. In addition, examples of the guide contents shown in parentheses) are not particularly excluded. For example, when entering a destination, enter the prefecture name, or enter, for example, Showa-cho, Kariya city, Aichi prefecture. May be notified.

In the above-described voice recognition device, the user's intention to input a voice is inferred, but there is actually no voice input, and how the input should be performed. Since it is considered that the user does not understand enough, predetermined guide contents have been determined from the viewpoint of instructing a user who is having trouble using the system, particularly, "how to input". On the other hand, in the voice recognition device according to the second aspect, since the user makes a guide request not in the situation where the user is trying to perform voice input but in the situation before that, as described above,
The guide contents such as guiding the setting items that can be instructed by voice input such as “can set the destination” are suitable. However, since it is only necessary to determine the situation where the guide request is made and to notify the appropriate guide content in that situation, the content itself is not particularly limited.

Further, as a voice recognition device having both of the above two functions, the configuration described in claim 3 can be considered. That is, in the voice recognition device according to claim 1, when the input period specifying unit issues a predetermined guide request other than the designation of the start and end of the normal voice input period, the guide unit responds to the guide request. It is characterized in that it is configured to notify at least a predetermined guide content corresponding thereto by voice.

According to the speech recognition apparatus in this case, the guide means determines the following two situations and executes the corresponding processing. In other words, one is to notify a predetermined guide content when there is no voice input via the voice input means even when a predetermined time has elapsed after the start of the voice input period is specified by the input period specifying means. The other is that when a predetermined guide request other than the specification of the start and end of the normal voice input period is made by the input period specifying means, a predetermined guide content corresponding to the guide request is notified. That is.

Therefore, it is possible to exhibit an appropriate guide function according to each of the two kinds of situations of the user who is not used to the above-mentioned use method. The notification form of the recognition result by the notification unit or the guide form of the guide content by the guide unit may be any form as long as the user can be notified. It is considered preferable to provide at least notification by voice. This is advantageous in terms of further ensuring safe driving when used for on-vehicle equipment such as a car navigation system, since the driver does not need to shift his or her viewpoint to the display device if it is output in voice. This is because of that. Further, if the notification of the recognition result is performed by voice and the notification of the guide content is also performed by voice, the hardware configuration for them can be shared. However, the notification may be made by, for example, an image in addition to the sound. It was mentioned that voice output is advantageous when applied as an in-vehicle device, but of course there are also situations where the vehicle is not running, so if both the voice and the image are used, the driver can confirm with the display and with the voice Both are possible.

When the voice recognition device according to any one of claims 1 to 6 is used for a navigation system, it is conceivable that the voice recognition device is configured as shown in claim 7. That is, a voice recognition device according to any one of claims 1 to 6 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. The user is used to input an instruction of predetermined navigation-related data by voice, and the post-confirmation processing means includes:
It is configured to output the result of recognition by the recognition means to the navigation device. In this case, the “predetermined navigation processing-related data” is a typical destination, but other than that, it is necessary to specify the navigation processing, such as selecting conditions for a route search. Instructions are included.

The application destination of the speech recognition apparatus is not limited to the navigation system described above. For example, when the voice recognition device is used for an air conditioning system, it is conceivable to adjust the set temperature, select an air conditioning mode (cooling / heating / dry), or select a wind direction mode by voice input. In this case, the setting items (temperature, air-conditioning mode, wind direction mode, etc.) themselves are reported as guide contents, or
It is conceivable that the guide content may further inform the user of whether to say "set the set temperature to 25 degrees" or "set the set temperature to 5 degrees". The same applies to the air conditioning mode and the wind direction mode.

The above navigation system and air conditioning system are not limited to the case where they are used as on-vehicle equipment, but may be, for example, a portable navigation device or an indoor air conditioning device. However, as described above, when used for in-vehicle equipment, the user may be a driver. In that case, driving itself is the most important. For other in-vehicle equipment, drive as much as possible. Preferably, there is no hindrance. Therefore, in the case of a voice recognition device on the premise of a navigation system or an air conditioning system as an in-vehicle device, there is a further advantage. Of course, from such a viewpoint, the present invention can be similarly applied to in-vehicle devices other than the navigation system and the air conditioning system. For example, a car audio device is effective. Also, considering a configuration in which opening and closing of the power window and adjustment of the mirror angle are instructed by voice, it is effective even in such a situation.

Although it has been described that there is an advantage unique to the in-vehicle device, the voice recognition device of the present invention is applied to a device that executes a predetermined process according to a voice input instruction from a user. If it does, the same can be considered. For example, the present invention can be similarly applied to a portable information terminal device or an information terminal device set in a street or a parking area.

[0026]

FIG. 1 is a block diagram showing a schematic configuration of a car navigation system 2 to which a voice recognition device 30 according to an embodiment of the present invention is applied. The car navigation system 2 includes a position detector 4, a map data input device 6,
An operation switch group 8, a control circuit 10 connected thereto,
External memory 12 connected to control circuit 10, display device 1
4 and a remote control sensor 15 and a voice recognition device 30. The control circuit 10 is configured as a normal computer, and has a well-known CPU, ROM, R
A bus line for connecting AM, I / O, and these components is provided.

The position detector 4 is a well-known geomagnetic sensor 1.
6. GPS (Gl) for detecting the position of the vehicle based on radio waves from the gyroscope 18, the distance sensor 20, and satellites
GPS receiver 22 for obal Positioning System)
have. These sensors and the like 16, 18, 20, 2
2 is configured to be used while interpolating each with a plurality of sensors because each has an error having a different property. It should be noted that depending on the accuracy, a part of the above-described components may be used, and a rotation sensor for the steering wheel, a wheel sensor for each rolling wheel, or the like may be used.

The map data input device 6 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
Although OM is generally used, another medium such as a memory card may be used.

The display device 14 is a color display device. On the screen of the display device 14, the current vehicle position mark input from the position detector 4, the map data input from the map data input device 6, and the 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.

The car navigation system 2
Is input from the remote control sensor 15 via a remote control terminal (hereinafter referred to as a remote control) 15a or the position of the destination by the operation switches 8;
It also has a so-called route guidance function that automatically selects an optimal route from the current position to the destination and forms and displays a guidance route. As a technique for automatically setting the optimum route, a technique such as the Dijkstra method is known.
The operation switch group 8 is, for example, a touch switch integrated with the display device 14 or a mechanical switch, and is used for various inputs.

The voice recognition device 30 is used when the operation switch group 8 or the remote controller 15a is manually operated to indicate a destination or the like, and similarly, when the user inputs voice. This is a device that allows the user to specify a destination or the like.

The speech recognition device 30 includes a speech recognition unit 31 as "recognition means", a dialog control unit 32 as "post-determination processing means", a speech synthesis unit 33, and a speech extraction unit 34.
A microphone 35 as an “audio input unit”, a PTT (Push-To-Talk) switch 36 as an “input period designating unit”, a speaker 37, a control unit 38, and a display control unit 3.
9 and a display unit 40.

The voice recognition unit 31 performs a voice recognition process on the voice data input from the voice extraction unit 34 according to an instruction from the dialog control unit 32, and returns the recognition result to the dialog control unit 32. That is, the voice data acquired from the voice extraction unit 34 is collated using the stored dictionary data, and a higher-level comparison target pattern having a higher degree of coincidence with a plurality of comparison target pattern candidates is compared with the dialogue control unit 32. Output to The recognition of the word sequence in the input speech is performed by the speech extraction unit 3
The sound data inputted from the step 4 are sequentially subjected to acoustic analysis to extract an acoustic feature (for example, cepstrum), and to obtain acoustic feature time-series data obtained by the acoustic analysis. The time-series data is divided into several sections by a well-known DP matching method, an HMM (Hidden Markov Model), a neural network, or the like, and a word corresponding to each section stored as dictionary data is obtained. .

The dialogue control unit 32 outputs a response voice output instruction to the voice synthesis unit 33 and a response display output instruction to the display control unit 39 based on the recognition result of the voice recognition unit 31 and the instruction from the control unit 38. Alternatively, the control circuit 10 executes a process of instructing the control circuit 10 executing the process of the system itself to execute a setting process by notifying a destination required for the navigation process, for example. Such processing is post-confirmation processing, and as a result, if this voice recognition device 30 is used, the destination of the navigation system can be indicated by voice input without manually operating the operation switch group 8 or the remote controller 15a. It becomes possible.

The speech synthesizing unit 33 uses the speech waveform stored in the waveform database, and
Synthesizes a voice based on a response voice output instruction from the user. This synthesized voice is output from the speaker 37.
Further, the display control unit 39 generates a display image based on a response display output instruction from the dialog control unit 32. This generated image is output to the display unit 40.

The voice extracting unit 34 converts the surrounding voice captured by the microphone 35 into digital data and outputs the digital data to the voice recognizing unit 31. Specifically, in order to analyze the feature amount of the input voice, a frame signal in a section of, for example, about several tens of ms is cut out at regular intervals, and the input signal is
It is determined whether the section is a speech section containing speech or a noise section containing no speech. Since the signal input from the microphone 35 contains not only the speech to be recognized but also noise, the speech section and the noise section are determined. As this determination method, many methods have been proposed as compared with the related art. A technique of determining whether a section is a speech section or a noise section is often adopted. When it is determined that the input signal is in the voice section, the input signal is output to the voice recognition unit 31.

Also, in the present embodiment, the user
This is a usage method in which a voice is input via the microphone 35 while pressing the TT switch 36. Specifically, the control unit 38 monitors the timing when the PTT switch 36 is pressed, the timing when the PTT switch 36 is returned, and the time when the pressed state continues, and when the PTT switch 36 is pressed, the voice extracting unit 34 is instructed to execute processing. On the other hand, PT
If the T switch 36 is not pressed, the processing is not executed. Therefore, the voice data input via the microphone 35 while the PTT switch 36 is pressed is output to the voice recognition unit 31. In addition, the control unit 38 is also configured to input a determination result of a voice section or a noise section in the voice extraction unit 34. For example, although the PTT switch 36 is pressed, there is no voice input. It can also be determined that the state has continued for a predetermined time.

Next, the operation of the car navigation system 2 according to the first embodiment will be described. In addition, since a portion related to the voice recognition device 30 is a feature, a general operation of the car navigation system 2 will be briefly described, and then, an operation of a portion related to the voice recognition device 30 will be described in detail. .

After the power of the car navigation system 2 is turned on, the driver can change the guide route from the menu displayed on the display device 14 by using the remote controller 15a (the same operation can be performed with the operation switches 8; the same applies to the following description). When the route information display process is selected to be displayed on the display device 14, or when a desired menu is voice-inputted via the microphone 35 via the voice recognition device 30, the dialogue control unit 32 sends a message to the control circuit 10. When the same instruction is given via the remote controller 15a, the following processing is performed.

That is, when the driver inputs a destination by voice or an operation of a remote controller or the like based on the map on the display device 14, the current position of the vehicle is obtained based on the satellite data obtained from the GPS receiver 22. A process is performed between the ground and the current location to calculate the cost by the Dijkstra method and determine the shortest route from the current location to the destination as a guidance route. And the display device 1
4. A guidance route is displayed on the road map above 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.

Next, the operation of the voice recognition device 30 will be described by taking as an example the case where the destination for the above-mentioned route guidance is input by voice. When the ignition switch 3 is operated and the engine is turned on (S100: YES),
When the power of the car navigation system 2 is turned on, the guide content A is first notified (S110). here,
The dialogue control unit 32 instructs the speech synthesis unit 33 to synthesize and output the guide content A by voice, and instructs the display control unit 39 to display and output the guide content A as an image. A synthesized voice according to the instruction is output from the speaker 37, and an image according to the instruction is output to the display unit 40. Hereinafter, the notification form is the same for the guide content B and thereafter. The specific content of this guide content A is "Voice input is possible. Click to explain." In other words, the user is notified that the input can be made by voice, and the user does not know the input itself. Then, the user who wants further explanation is urged to perform the click operation.

After notifying the guide content A in S110, it is determined in S120 whether the PTT switch 36 is turned on (pressed). This judgment is made by the control unit 3
8 is performed. If it is turned on (S12
0: YES), and in subsequent S130, it is determined whether or not a click operation has been performed. This determination is also performed by the control unit 38. Specifically, when the PTT switch 36 is turned off within a relatively short time (for example, within 0.5 seconds) after the PTT switch 36 is turned on, a click operation is performed. Regard it.

If it is determined that the operation is a click operation (S130: YES), the flow shifts to S140 to notify the guide content B. The specific content of the guide content B is that "destination setting, enlargement, reduction, etc. can be performed." That is, the user is notified of what kind of voice input is possible. After the notification of the guide content B, the process returns to S120.

On the other hand, if it is determined that the operation is not a click operation (S130: NO), the flow shifts to S150 to determine whether there is a voice input. As described above, the voice extracting unit 34 determines whether the voice section is a voice section or a noise section based on the voice data input via the microphone 35, and the determination result is input to the control unit 38. The unit 38 determines whether there is a voice input based on the determination result.

If there is a voice input (S150: YE
S), the process proceeds to S260 in FIG. 4, and the processes after S260 will be described later. On the other hand, if there is no voice input (S
150: NO), it is determined whether or not the PTT switch 36 is turned off (S160).
If the FF has been performed (S160: YES), the process returns to S120. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S160: N
O), it is determined whether a predetermined time Ta has elapsed (S)
170).

If the predetermined time Ta has not elapsed (S170: NO), the process returns to S150 and waits for voice input, but if the predetermined time Ta has elapsed (S17).
0: YES), proceeds to S180 and notifies guide content C. The specific content of the guide content C is "When setting a destination, input from the prefecture name." That is, an affirmative determination in S170 means that there is no voice input until the predetermined time Ta has elapsed even though the PTT switch 36 has been turned on, and therefore, it is desired to set a destination. It informs the user of the input method.

After informing the guide content C in S180, the process shifts to S190 to determine whether there is a voice input. If there is a voice input (S150: YES),
The process proceeds to S260 in FIG. The processing after S260 will be described later. On the other hand, when there is no voice input (S190:
NO), it is determined whether or not the PTT switch 36 has been turned off (S200). If the PTT switch 36 has been turned off (S200: YES), the process returns to S120 in FIG. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S200: NO),
It is determined whether the predetermined time Ta has elapsed (S21).
0).

If the predetermined time Ta has not elapsed (S210: NO), the flow returns to S190 and waits for voice input, but if the predetermined time Ta has elapsed (S21).
0: YES), and proceeds to S220 to notify the guide content D. The specific content of this guide content D is "Please input, for example, Showa-cho, Kariya-shi, Aichi."
That is, a positive determination in S210 means that P
Even if the TT switch 36 is turned on, there is no voice input until the predetermined time Ta has elapsed. Considering the progress before that, even though the guide content C was informed that "When setting a destination, please input from the name of the prefecture." It has been done. This is an explanation of the input method as a guide content, but it is presumed that the user still cannot fully understand how to input and cannot input, so a more specific input example By notifying the guide content D, it is possible to easily input a desired destination in accordance with the notification.

After informing the guide contents D in S220, the flow shifts to S230 to determine whether or not there is a voice input. If there is a voice input (S230: YES),
The process proceeds to S260 in FIG. The processing after S260 will be described later. On the other hand, when there is no voice input (S230:
NO), it is determined whether or not the PTT switch 36 has been turned off (S240). If the PTT switch 36 has been turned off (S240: YES), the process returns to S120 in FIG. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S240: NO),
It is determined whether the predetermined time Ta has elapsed (S25).
0).

If the predetermined time Ta has not elapsed (S250: NO), the flow returns to S230 to wait for voice input, but if the predetermined time Ta has elapsed (S25).
0: YES), and returns to S120 of FIG. In the processing so far, when the predetermined time Ta elapses without a voice input, the predetermined guide content is notified, but here, the guide content is not notified, and the process returns to S120. This is because the user does not make a voice input even if the guide contents D listed up to the specific example of the input are notified, so that it is estimated that there is no intention to make a voice input itself, and the guide is temporarily stopped at this point.

Subsequently, S150, S190, S
A description will be given of the processing after step S260 in which a determination is made in the affirmative at 230, that is, when there is a voice input. S26
At 0, a recognition process is performed on the input voice. This voice recognition processing is executed by the voice recognition unit 31. Specifically, the obtained voice data is collated using stored dictionary data. And
The higher-order comparison target pattern determined by the collation result is output to the dialog control unit 32 as a recognition result.

In subsequent S270, the recognition result is talked back and displayed. That is, the dialogue control unit 32 controls the speech synthesis unit 33 and the display control unit 39 to output the recognized result from the speaker 37 by voice, and causes the display unit 40 to display a sentence indicating the recognition result.

Thereafter, it is determined in S280 whether the recognition is correct. This is determined according to an instruction from the user. For example, if the recognition is correct, the voice input of "Yes" is input from the microphone 35, and if the recognition is incorrect, the voice input of "No" is input. It is conceivable to keep it. Of course, these instructions may be input via the operation switch group 8.

If the recognition is incorrect (S280:
NO) The process returns to S120 in FIG. 2, but if the recognition is correct (S280: YES), the process proceeds to S290 to determine the recognition result. Then, in subsequent S300, predetermined post-determination processing is executed. The post-determination process in this case is a process of outputting data relating to the “destination for route guidance” as a recognition result to the control circuit 10 (see FIG. 1).

After the post-determination process (S300) is completed, the flow shifts to S310 to determine whether or not the PTT switch 36 has been turned on (pressed). If it is turned on (S310: YES), the subsequent S
At 320, it is determined whether there is a click operation. If it is determined that the click operation is performed (S320: YES), S3
Then, the process goes to 30 to notify the guide content E. The specific content of the guide content E is "Route search, enlargement, reduction, etc. can be performed." That is, since the setting of the destination has been completed in the processing so far, the user is informed that the route search, which is the next processing in the overall navigation processing, can be performed. After the guide content E is notified, the process returns to S310. On the other hand, if it is determined that the operation is not a click operation (S320: NO), FIG.
The process proceeds to S340 to determine whether there is a voice input. If there is a voice input (S340: YES),
The process proceeds to S410 in FIG. The processing after S410 will be described later. On the other hand, when there is no voice input (S340:
NO), it is determined whether or not the PTT switch 36 has been turned off (S350). If the PTT switch 36 has been turned off (S350: YES), the process returns to S310 in FIG. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S350: NO),
It is determined whether the predetermined time Ta has elapsed (S36).
0).

If the predetermined time Ta has not elapsed (S360: NO), the flow returns to S340 to wait for voice input, but if the predetermined time Ta has elapsed (S35).
0: YES), the process proceeds to S360, and the guide content F is notified. The specific content of the guide content F is "Please input route search when you want to search for a route." This assumes a situation in which the user is wondering how to input even if he / she wants to search for a route, and in that case, is notified that the user may input "route search".

After informing the guide contents F in S370, the flow shifts to S380 to determine whether or not there is a voice input. If there is a voice input (S380: YES),
The process proceeds to S410 in FIG. The processing after S410 will be described later. On the other hand, when there is no voice input (S380:
NO), it is determined whether the PTT switch 36 has been turned off (S390). If the PTT switch 36 has been turned off (S390: YES), the process returns to S310 in FIG. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S390: NO),
It is determined whether the predetermined time Ta has elapsed (S40).
0).

If the predetermined time Ta has not elapsed (S400: NO), the flow returns to S380 to wait for voice input, but if the predetermined time Ta has elapsed (S40).
0: YES), and returns to S310 of FIG. In this case,
The user does not input a voice even though the guide content F was informed (S370) that "Please enter route search when you want to search for a route." In this case, do not give any further guidance. I have to.

Subsequently, affirmative determination is made in S340 and S380 described above, that is, the processing shifts to when there is a voice input.
The processing after 410 will be described. The speech recognition process in S410 and the talkback / display of the recognition result in S420 are the same as the processes in S260 and S270 described above. Then, in S430, it is determined whether the recognition is correct, as in S280 described above. If the recognition is incorrect (S430: NO), the process returns to S310 in FIG. 4. If the recognition is correct (S430: YES), S44.
The process proceeds to 0 to determine the recognition result. And the following S450
, A predetermined post-determination process is executed. The post-determination process in this case is a process of outputting data relating to the “instruction to search for a route” as a recognition result to the control circuit 10 (see FIG. 1).

After the completion of the post-determination process (S450), the flow shifts to S460 to determine whether or not the PTT switch 36 has been turned on (pressed). If it is turned on (S460: YES), the subsequent S
At 470, it is determined whether or not a click operation has been performed. If it is determined that the click operation has been performed (S470: YES), S4
The process proceeds to 80 to notify the guide content G. The specific content of the guide content G is "change of conditions for route search can be performed." That is, since the instruction to perform the route search is input by voice, if the user wants to change the condition, the user is notified that the condition can be changed. After informing the guide content G, the process returns to S460.

On the other hand, if it is determined that the operation is not a click operation (S470: NO), the flow shifts to S490 to determine whether there is a voice input. If there is a voice input (S490: YES), the flow shifts to S520 to perform voice recognition processing. This voice recognition processing is performed in S260 or S
Since it is the same as 410, it will not be repeated here. Also,
The same applies to talkbacks and the like of recognition results thereafter.

On the other hand, when there is no voice input (S49)
0: NO), it is determined whether the PTT switch 36 is turned off (S500), and the PTT switch 36 is turned off.
If it has been performed (S500: YES), the process returns to S460. On the other hand, if the PTT switch 36 is not turned off, that is, remains in the ON state (S500: NO),
It is determined whether the predetermined time Ta has elapsed (S51).
0).

If the predetermined time Ta has not elapsed (S510: NO), the flow returns to S490 and waits for voice input. When the predetermined time Ta has elapsed (S51)
0: YES), which is not shown here, performs predetermined processing such as notifying another guide content or waiting for voice input.

In the present embodiment, the dialogue control unit 32 and the control unit 38 correspond to "guide means", and the processing of the parts not related to voice recognition during the processing shown in FIGS. It corresponds to processing. By executing such processing, the speech recognition device 30 of the present embodiment exhibits the following effects.

(1) First, when the engine is turned on, a guide content A of "voice input is possible. Click to explain." That is, since the user is notified that the instruction to the navigation device can be input by voice, it is possible to cope with the case where the user does not know the fact.

(2) The user is also informed that the user who wants to ask for the explanation actively is required to click. When the click operation is performed, for example, a guide content B that "can set destination, enlarge, reduce, etc."
Or a guide content E indicating that "route search, enlargement, reduction, etc. can be performed." This allows the user to understand the contents to be instructed. In order to cope with a user who wants to actively ask for an explanation as described above, for example, a plurality of types of click operations are set, and, for example, when a double-click operation is performed, a more detailed explanation is provided. It is also possible. That is, it is possible to respond according to the user's understanding level.

(3) Even if the user actually tries to give an instruction by voice input, he / she may not know how to input the voice when he / she tries to input voice. In such a situation, the user's intention to input a voice by pressing the PTT switch 36 can be inferred, but no voice may be actually input. Therefore, in such a case, for example, a guide content C such as "Please input from the name of prefecture when setting a destination" or "Please input route search when you want to search a route." The guide content F is notified. As a result, a guide can be realized for a user who wants to input voice but does not fully understand how to input.

(4) Furthermore, even if the above-mentioned guide content C stating that "when setting a destination, start with the name of the prefecture" is notified, there may be a situation where voice input is still not possible. Therefore, as a follow-up in that case, in the present embodiment, the guide content D of "Please input, for example, Showa-cho, Kariya-shi, Aichi" is notified. By notifying a specific input example as a guide content in this way, the user can know the specific input method, and if the user is notified of the specific example, the user can easily find the desired destination according to the input method. Can be entered.

As described above, the voice recognition device 3 of the present embodiment
According to the car navigation system 2 to which 0 is applied,
Even a user who is not accustomed to using the voice recognition device 30 can easily use the voice recognition device 30, and can provide a more user-friendly user-friendly surface.

As described above, the present invention is not limited to such an embodiment, and can be implemented in various forms without departing from the gist of the present invention. For example, in the above-described embodiment, the notification of the recognition result and the notification of the guide content are performed by two types of voice and image. However, any form may be used as long as the notification can be performed to the user. If only one is used, it is preferable to perform notification by voice. This is in consideration of being used as an in-vehicle device called a car navigation system 2,
This is because the driver does not need to shift his / her viewpoint to the display device if the voice is output, which is advantageous in terms of further ensuring safe driving. Of course, as in the above-described embodiment, if the notification is made by both the voice and the image, the driver can perform both the confirmation by the display and the confirmation by the voice.

The application of the speech recognition apparatus is not limited to the above-mentioned navigation system. For example, when the voice recognition device is used for an air conditioning system, it is conceivable to adjust the set temperature, select an air conditioning mode (cooling / heating / dry), or select a wind direction mode by voice input. In this case, the setting items (temperature, air-conditioning mode, wind direction mode, etc.) themselves are reported as guide contents, or
It is conceivable that the guide content may further inform the user of whether to say "set the set temperature to 25 degrees" or "set the set temperature to 5 degrees". The same applies to the air conditioning mode and the wind direction mode.

Further, the use of the navigation system or the air conditioning system as a vehicle-mounted device is not limited. For example, the navigation system or the air-conditioning system may be used other than the vehicle-mounted device such as a portable navigation device or an indoor air conditioner. However, as described above, when used for in-vehicle equipment, the user is considered to be a driver. In that case, driving itself is the most important. It is preferable that there is no problem in driving.
Therefore, in the case of the voice recognition device 30 on the premise of the car navigation system 2 and the air conditioning system as on-vehicle devices, there is a further advantage.

Of course, from such a point of view, the present invention can be similarly applied to in-vehicle devices other than the navigation system and the air conditioning system. For example, a car audio device is effective. In addition, in addition to the above, if a configuration in which opening and closing of the power window and adjustment of the mirror angle are instructed by voice is considered,
The same can be applied to such a controlled object, which is also effective.

Although it has been described that there is an advantage peculiar to the in-vehicle device, the speech recognition device 30 is applied to a device which executes a predetermined process in accordance with a voice input instruction from a user. If so, it can be considered similarly. For example, the present invention can be similarly applied to a portable information terminal device or an information terminal device set in a street or a parking area.

[Brief description of the drawings]

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

FIG. 2 is a part of a flowchart showing processing executed by the voice recognition device.

FIG. 3 is a part of a flowchart showing processing executed by the voice recognition device.

FIG. 4 is a part of a flowchart showing processing executed by the voice recognition device.

FIG. 5 is a part of a flowchart showing processing executed by the speech recognition device.

FIG. 6 is a part of a flowchart showing processing executed by the speech recognition device.

[Explanation of symbols]

2 ... Car navigation system 4 ... Position detector 6 ... Map data input device 8 ... Operation switch group 10 ... Control circuit 12 ... External memory 14 ... Display device 15 ... Remote control sensor 15a ... Remote control 16 ... Geomagnetic sensor 18 ... Gyroscope 20 ... Distance sensor 22 GPS receiver 30 Voice recognition device 31 Voice recognition unit 32 Dialogue control unit 33 Voice synthesis unit 34 Voice input unit 35 Microphone 36 PTT switch 37 Speaker 38 Control unit 39 Display control Part 40 ... Display part

Continued on the front page (51) Int.Cl. ⁶ Identification code FI G08G 1/0969 G08G 1/0969 G09B 29/00 G09B 29/00 F 29/10 29/10 A

Claims (7)

[Claims] 1. A voice input unit for inputting voice, and an input period provided for a user himself to designate a start and an end of a period for inputting a voice to be recognized using the voice input unit. Specifying means for comparing a voice input through the voice input means within the input period specified by the input period specifying means with a plurality of comparison target pattern candidates previously stored in the dictionary means, Recognizing means for recognizing the recognition result by the recognizing means; and notifying means for notifying the recognition result by the recognizing means. When a predetermined confirmation instruction is given after the recognizing result is notified by the notifying means, the recognition result is obtained. And a post-confirmation processing means for executing a predetermined post-confirmation process as a pre-determined one, wherein a start of a voice input period is designated by the input period designation means. A voice recognition device, comprising: a guide unit for notifying predetermined guide content when there is no voice input via the voice input unit even after a predetermined time has elapsed from a point in time. 2. A voice input means for inputting voice, and an input period provided for the user himself to designate a start and an end of a period for inputting a voice to be recognized using the voice input means. Specifying means for comparing a voice input through the voice input means within the input period specified by the input period specifying means with a plurality of comparison target pattern candidates previously stored in the dictionary means, Recognizing means for recognizing the recognition result by the recognizing means; and notifying means for notifying the recognition result by the recognizing means. When a predetermined confirmation instruction is given after the recognizing result is notified by the notifying means, the recognition result is obtained. And a post-confirmation processing means for executing a predetermined post-confirmation process as a pre-determination of the speech recognition device, wherein the input period designation means starts and ends a normal speech input period. A voice recognition device comprising: a guide unit that, when a predetermined guide request other than the designation of the end of the guide is made, notifies a predetermined guide content corresponding to the guide request. 3. The voice recognition device according to claim 1, wherein the guide unit is configured to execute a predetermined guide request which is not a designation of a start and an end of a normal speech input period by the input period designation unit. A voice recognition device configured to notify predetermined guide content according to the guide request. 4. The voice recognition device according to claim 1, wherein said notifying unit is configured to notify the recognition result by at least voice, and said guide unit is configured to control said predetermined guide. A speech recognition apparatus characterized in that the content is notified at least by voice. 5. The voice recognition device according to claim 1, wherein the predetermined guide content notified by the guide means is processed in a system using a voice recognition result by the voice recognition device. A speech recognition device, characterized in that the content is related to 6. The voice recognition device according to claim 5, wherein the guide unit is configured to notify a guide content corresponding to a processing execution stage in the system at a time of notifying the predetermined guide content. A speech recognition device characterized in that: 7. The voice recognition device according to claim 1, further comprising: a navigation device, wherein the voice input unit of the voice recognition device performs at least navigation processing by the navigation device. The user uses a voice to input an instruction of predetermined navigation processing-related data that needs to be specified, and the post-confirmation processing means sends the recognition result by the recognition means to the navigation device. A navigation system configured to output.