JP4201411B2 - Voice recognition device and navigation system - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a voice recognition device that is effective when, for example, a destination setting or the like in a navigation system can be input by voice, and a navigation system including the voice recognition device.
[0002]
[Prior art]
Conventionally, a speech recognition apparatus that compares input speech with a plurality of comparison target pattern candidates stored in advance and uses a recognition result having a high degree of coincidence has already been put into practical use. This is used for a user to input a place name by voice. In particular, when the driver himself / herself uses the in-vehicle navigation system, since it is not accompanied by button operation or screen gaze if it is a voice input, it is effective because it is highly safe even when the vehicle is running.
[0003]
In addition, since it is burdensome to prepare the voice recognition device side to always prepare for voice input, there is a configuration in which the user himself / herself specifies the start and end timing of the period for inputting the voice to be recognized. Often adopted. As means for designating the input period, for example, a PTT (Push-To-Talk) switch or the like 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 necessary is not processed.
[0004]
Thus, although it is a speech input method with high utility value, the following problems will arise if the user is a beginner who is not familiar with the speech recognition system itself. For example, there is a problem that the voice that is inappropriate for the device is appropriately input due to the fact that the usage method is unknown, or the effectiveness is not improved, or the device itself is not used in an extreme case There is. In addition, although the usage method itself is understood to some extent, but is not used to a specific usage method, there is a problem that, for example, a word to be input does not come out immediately and is silent.
[0005]
As a countermeasure for such a beginner, for example, notification of predetermined guide contents may be considered. For example, it is conceivable to guide what commands can be input. Specifically, the guide contents such as “the destination can be set and the map can be enlarged / reduced” are notified. Alternatively, if the user does not know the specific command input method, it may be possible to notify the description of the input method “Please input from the prefecture name when setting the destination” as the guide content.
[0006]
[Problems to be solved by the invention]
However, when measures are taken for beginners in this way, the content of guides useful for beginners is also unnecessary for skilled workers. In other words, if you are familiar with commands and input methods that you can enter without listening to such guide content, you will not be able to input voice while the guide content is being output. .
[0007]
In addition, it is not possible to reach the level of a skilled person who does not need to listen to the guide content at all, but if it is a “intermediate” level that can be handled by yourself after receiving only a rough guide, the guide of the same content as the beginner Is unnecessary. These beginners, intermediate persons, and skilled persons are not necessarily different people, but the same person is a beginner at first, and then steps up with intermediate and skilled persons. Therefore, it is not preferable for the device side to set a fixed system according to the level of the user, such as for beginners, intermediates, and experts, and for beginners to beginners depending on the situation during use. It is expected that the system setting is such that an intermediate input method can be selected arbitrarily for intermediate users, and an input method for intermediate users can be arbitrarily selected by skilled workers.
[0008]
The present invention solves such problems and provides a speech recognition device that is easy to use for each user who has a different level of familiarity with the method of using the speech recognition device, and a navigation system including the speech recognition device. With the goal.
[0009]
[Means for Solving the Problems and Effects of the Invention]
Claim 1 made to achieve the above object. , 7 According to the voice recognition apparatus described in the above, the user inputs voice via voice input means such as a microphone, but the user himself designates the start and end of the period for inputting the voice to be recognized. Therefore, an input period designating unit is provided, and a voice input within the input period designated by the input period designating unit is a recognition target. The recognizing unit compares the input speech with a plurality of comparison target pattern candidates stored in advance in the dictionary unit, and determines the one having a high degree of coincidence as a recognition result, and notifies the recognition result by the notifying unit. Then, when a predetermined confirmation instruction is given after the recognition result is notified, the post-confirmation processing means executes the predetermined post-confirmation process assuming that the recognition result is confirmed.
[0010]
And in the speech recognition apparatus of the present invention, 2 One or more guide request operations are set. This guide request operation is different from the operation for specifying the start and end of the voice input period for the input period specifying means. 2 More than one guide request operation is set This A guide request level corresponding to the degree of familiarity is set for each guide request operation. Then, when a guide request operation is performed by the input period specifying unit, the guide unit notifies a predetermined guide content corresponding to the corresponding guide request level. Here, in the first aspect of the present invention, the guide unit notifies the setting item itself that can be instructed via the voice input unit as the guide content. According to a seventh aspect of the present invention, the predetermined guide content notified by the guide means is a content related to processing in a system in which a voice recognition result by the voice recognition apparatus is used, and the guide means The guide content corresponding to the process execution stage in the system at the time when the guide content of the system is notified is configured, and the guide means executes the process as the guide content corresponding to the process execution stage in the system. In the stage, the setting item itself that can be instructed via the voice input means is notified.
[0011]
Here, “different from the operation for specifying the start and end of the voice input period. Ru The “id request operation” refers to the following case, for example. For example, it is assumed that the operation for specifying the start and end of the voice input period by the input period specifying means is associated with the start and end of the operation when the switch operation starts and ends for a predetermined time or longer. In this case, voice input is performed after the start of the switch operation, and then the operation ends. Therefore, it is difficult to assume that the time during which the switch operation continues is, for example, 1 second or less. Therefore, for example, a so-called “click operation” in which the time from the start to the end of the switch operation is a relatively short click time, such as 0.5 seconds or less, "sound Different from the operation to specify the start and end of the voice input period Guide request It can be set as “operation”. Of course, if the operation is a special operation that cannot be designated to start and end the normal voice input period on the apparatus side, other operations may be operations for requesting a guide. For example, it may be a “double click operation” in which the click operation is continuously performed twice within a predetermined interval.
[0012]
In this way, When two or more guide request operations are set, A user who needs a guide only needs to perform a corresponding guide request operation so that the guide content is at the guide request level according to his / her familiarity level, while a user who does not need a guide performs a guide request operation. Instead, a predetermined voice input may be performed as usual while performing the input operation of the start and end of the voice input period by the input period specifying means.
[0013]
Since there are various possible contents of the predetermined guide in this case, in order to facilitate understanding, here, some explanations are given assuming that a speech recognition device is applied to input a destination in the navigation system. To do.
(1) First, a user who does not know what he / she can input by voice to the navigation system is assumed. In this case, by performing a click operation, for example, it is conceivable to guide the setting items that can be instructed by voice input, such as “You can set the destination”. The contents may be changed depending on which stage of a series of processes in the target system (in this case, the navigation system) instructed by voice input. For example, if the route to the destination is considered as a series of processing, after the destination is set, the conditions for setting the route, such as whether to specify the waypoint, are further specified. There is a case. Therefore, if there is no voice input even after a predetermined time has elapsed since the start of the voice input period described above was specified in the situation where the destination has already been set, this time " The guide content such as “
[0014]
(2) It is also assumed that a user who knows what he / she can input to the navigation system itself but does not know a specific input method. In this case, it is conceivable that the description of the input method is notified as the guide content, such as “Please input from the prefecture name when setting the destination”. Also, if you still cannot fully understand how the user inputs, and if you are unable to input, please enter a specific name such as "Please enter Showacho, Kariya City, Aichi Prefecture". It is conceivable that a simple input example is notified as guide content. As a result, the user knows a specific input method, and if he / she informs a specific example, the user can easily input a destination desired by the user.
[0015]
Of course, the guide contents described in the above (1) and (2) are only examples, and it is only necessary to output appropriate guide contents suitable for the processing of the navigation system to be applied. What is necessary is just to devise so that it may suit the processing of the system.
[0016]
In addition, if there are two beginner level and intermediate level as the target people who need a guide, what kind of guide content will be used at the beginner level, and what kind of guide content will be used in the intermediate level What is necessary is just to set suitably also according to the difficulty of the usage method of the said system. For example, at the beginner level, when there is a guide request operation and the guide contents are notified in the order of A → B → C, at the intermediate level, the guide contents of A, B, and C are collectively notified. It is also possible to end up. Of course, depending on the system to be applied, a target person who needs a guide may be classified into three or more levels.
[0017]
On the other hand, unless the guide request operation is performed, the contents of the guide will not be notified without permission. For users who do not need the guide, the input period specifying means starts and ends the voice input period while performing the specified operation. If the voice input is performed, a desired voice input can be performed in a relatively short time (that is, compared to a state where the guide contents are informed).
[0018]
As described above, according to the speech recognition apparatus of the present invention, usability is improved for each user who has a different level of familiarity with the usage method of the speech recognition apparatus. In addition, a special configuration is not required to accept the guide request operation, but the input period designation means necessary for basic processing for voice input can also be used for the guide request operation, thus simplifying the configuration. It also contributes to
[0019]
Note that each of the guide request operations in the case where the beginner level and the intermediate level are provided as the target persons who need the guide, claim 2. , 8 It can be considered as shown in. That is, it is assumed that the operation for specifying the start and end of the voice input period by the input period specifying means corresponds to the start and end of the operation when the switch operation starts and ends for a predetermined time or longer. As a guide request operation for the level and intermediate level, a click operation and a double click operation are set corresponding to each level operation.
[0020]
Claims 3, 9 As shown in FIG. 2, in the guide for beginners, when the predetermined guide content is notified, and further click operation is performed without voice input, the guide content more detailed than the previously notified guide content is notified. You may do it.
[0021]
Of course, these are only examples, and it is only necessary that the difference in operation contents can be distinguished on the apparatus side. The notification form of the recognition result by the notification means or the notification form of the guide content by the guide means may be any form as long as it can be notified to the user. 4, 10 As shown in FIG. 4, it is considered preferable to perform at least voice notification. For example, when used for in-vehicle equipment such as a car navigation system, the driver does not need to shift the viewpoint to the display device if the sound is output, which is advantageous in terms of further ensuring safe driving. This is because it is. Further, if the recognition result is notified by voice and the guide contents are also notified by voice, the hardware configuration for them can be shared. However, for example, an image may be notified in addition to the sound. Although it has been stated that audio output is advantageous when applied as an in-vehicle device, there are of course situations where the vehicle is not running. Both are possible.
[0022]
Claims 1 to 10 When the voice recognition device according to any one of the above is used for a navigation system, 11 It is possible to configure as shown in FIG. That is, claims 1 to 10 The voice recognition device according to any one of the above and a navigation device, and the voice input means of the voice recognition device includes at least predetermined navigation processing related data that is required to be specified when the navigation device performs the navigation processing. The post-confirmation processing means is configured to output the recognition result by the recognition means to the navigation device. In this case, the “predetermined navigation processing related data” is representative of the destination, but other than that, it is necessary to specify it for navigation processing, such as selecting conditions for route search. Instructions are included.
[0023]
Note that the application destination of the voice recognition device is not limited to the navigation system described above. For example, when the speech recognition apparatus is used for an air conditioning system, it is conceivable to adjust a set temperature, select an air conditioning mode (cooling / heating / dry), or select a wind direction mode by voice input. In this case, the setting item (temperature, air conditioning mode, wind direction mode, etc.) itself is notified as a guide content, or it can be said that “set the set temperature to 25 degrees” or “set the set temperature to 5”. It may be possible to further inform as guide contents whether or not it should be said that “degrade”. The same applies to the air conditioning mode and the wind direction mode.
[0024]
The navigation system and the air conditioning system described above are not limited to being used as in-vehicle devices, but may be, for example, a portable navigation device or an indoor air conditioner. However, as described above, when used for in-vehicle equipment, it is considered that the user is a driver. In that case, driving itself is the most important. It is preferable that there is no hindrance. Therefore, in the case of a speech recognition device based on a navigation system or an air conditioning system as an in-vehicle device, there are further advantages. Of course, from this point of view, it can also be used for in-vehicle devices other than navigation systems and air conditioning systems. For example, car audio equipment is effective. Also, considering a configuration in which a so-called power window opening / closing or mirror angle adjustment is instructed by voice, it is effective even in such a situation.
[0025]
In addition, although it has been described that there is a unique advantage when used for in-vehicle devices, the application of the speech recognition apparatus of the present invention is to execute predetermined processing in accordance with a voice input instruction by a user. If there is, it is 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.
[0026]
DETAILED DESCRIPTION OF THE INVENTION
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, an external memory 12 connected to the control circuit 10, a display device 14, and a remote control sensor 15. And a voice recognition device 30. The control circuit 10 is configured as a normal computer, and includes a well-known CPU, ROM, RAM, I / O, and a bus line for connecting these configurations.
[0027]
The position detector 4 includes a well-known geomagnetic sensor 16, a gyroscope 18, a distance sensor 20, and a GPS receiver 22 for GPS (Global Positioning System) that detects the position of the vehicle based on radio waves from a satellite. ing.
Since these sensors 16, 18, 20, and 22 have errors of different properties, they are configured to be used while being interpolated by a plurality of sensors. Depending on the accuracy, a part of the above may be used, and further, a steering rotation sensor, a wheel sensor of each rolling wheel, or the like may be used.
[0028]
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, a CD-ROM is generally used because of the amount of data, but another medium such as a memory card may be used.
[0029]
The display device 14 is a color display device. On the screen of the display device 14, the vehicle current position mark input from the position detector 4, the map data input from the map data input device 6, and further displayed on the map. Additional data such as guidance routes to be set and landmarks of setting points to be described later can be displayed in an overlapping manner.
[0030]
Further, when the destination position is input from the remote control sensor 15 or the operation switch group 8 via a remote control terminal (hereinafter referred to as a remote controller) 15a, the present car navigation system 2 is moved from the current position to the destination. There is also a so-called route guidance function that automatically selects the optimal route and forms and displays a guidance route. As a method for automatically setting an optimal route, a method such as the Dijkstra method is known. For example, a touch switch or a mechanical switch integrated with the display device 14 is used as the operation switch group 8 and is used for various inputs.
[0031]
The voice recognition device 30 is used for the operation switch group 8 or the remote controller 15a to manually instruct a destination or the like, but when the user inputs a voice, the destination or the like is similarly applied. It is a device for making it possible to instruct.
[0032]
The speech recognition apparatus 30 includes a speech recognition unit 31 as a “recognition unit”, a dialogue control unit 32 as a “post-processing unit”, a speech synthesis unit 33, a speech extraction unit 34, and a “speech input unit”. A microphone 35, a PTT (Push-To-Talk) switch 36 as “input period designating means”, a speaker 37, a control unit 38, a display control unit 39, and a display unit 40.
[0033]
The voice recognition unit 31 performs input voice recognition processing on the voice data input from the voice extraction unit 34 according to an instruction from the dialogue control unit 32, and returns the recognition result to the dialogue control unit 32. That is, the speech data acquired from the speech extraction unit 34 is collated using the stored dictionary data, and the upper comparison target pattern having a higher degree of coincidence than a plurality of comparison target pattern candidates is displayed in the dialog control unit 32. Output to. The recognition of the word sequence in the input speech is performed by sequentially analyzing the speech data input from the speech extraction unit 34 to extract an acoustic feature amount (for example, cepstrum), and at the time of the acoustic feature amount obtained by this acoustic analysis. Get series data. Then, the time series data is divided into several sections by a known DP matching method, HMM (Hidden Markov Model), or a neural network, and it is determined which word is stored as dictionary data. .
[0034]
Based on the recognition result in the voice recognition unit 31 and the instruction from the control unit 38, the dialogue control unit 32 outputs a response voice to the voice synthesis unit 33, outputs a response display to the display control unit 39, or system For example, a process of instructing the control circuit 10 that executes the process itself to notify the destination necessary for the navigation process and execute the setting process is executed. Such a process is a post-confirmation process. As a result, if the voice recognition device 30 is used, the destination of the navigation system can be instructed by voice input without manually operating the operation switch group 8 or the remote controller 15a. Is possible.
[0035]
The voice synthesizer 33 synthesizes a voice based on a response voice output instruction from the dialogue control unit 32 using a voice waveform stored in the waveform database. This synthesized voice is output from the speaker 37. In addition, the display control unit 39 generates a display image based on the response display output instruction from the dialogue control unit 32. This generated image is output to the display unit 40.
[0036]
The voice extraction unit 34 converts the surrounding voice captured by the microphone 35 into digital data and outputs the digital data to the voice recognition unit 31. Specifically, in order to analyze the feature amount of the input voice, for example, a frame signal of a section of about several tens of milliseconds is cut out at a constant interval, and whether the input signal is a voice section including the voice is included. Determine if there is no noise interval. Since the signal input from the microphone 35 includes not only the speech to be recognized but also noise, the speech section and the noise section are determined. Many methods have been proposed as this determination method. For example, the short-time power of the input signal is extracted at regular intervals, and depending on whether or not the short-time power equal to or greater than a predetermined threshold continues for a certain period. A method of determining whether a speech section or a noise section is often used. Then, when it is determined that it is a voice section, the input signal is output to the voice recognition unit 31.
[0037]
In the present embodiment, the user inputs voice through the microphone 35 while pressing the PTT 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 during which the pressed state continues, and if the PTT switch 36 is pressed, the voice extraction unit 34 and the voice person section 31 are instructed to execute the process. On the other hand, when the PTT switch 36 is not pressed, the processing is not executed. Accordingly, voice data input via the microphone 35 while the PTT switch 36 is being pressed is output to the voice recognition unit 31.
[0038]
The control unit 38 can also determine that the PTT switch 36 has been clicked and double-clicked. Specifically, when the PTT switch 36 is turned off in a relatively short time (for example, within 0.5 seconds) after the PTT switch 36 is turned on, it is regarded as a click operation. Then, when the click operation is continuously performed twice within a predetermined interval (for example, within 0.5 seconds), it is regarded as a click operation.
[0039]
Next, the operation of the car navigation system 2 according to the first embodiment will be described. Since the portion related to the speech recognition device 30 is characteristic, the general operation as the car navigation system 2 will be briefly described, and then the operation related to the speech recognition device 30 will be described in detail. .
[0040]
After the car navigation system 2 is turned on, the driver can operate the guide route from the menu displayed on the display device 14 by the remote controller 15a (the operation switch group 8 can also be operated in the same way). When the route information display process is selected for display on the screen, or by inputting a desired menu through the voice recognition device 30 through the microphone 35, the remote control 15a is transferred from the dialogue control unit 32 to the control circuit 10. When the same instruction is given to select via the following, the following processing is performed.
[0041]
That is, when the driver inputs the destination by operating voice or a remote controller based on the map on the display device 14, the current location of the vehicle is obtained based on the satellite data obtained from the GPS receiver 22, and the destination and current location are determined. In the meantime, the cost is calculated by the Dijkstra method, and the shortest route from the current location to the destination is obtained as the guidance route. Then, the guidance route is displayed on the road map on the display device 14 to guide the driver of the appropriate route. Such calculation processing and guidance processing for obtaining a guidance route are generally well-known processing, and thus description thereof is omitted.
[0042]
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-described route guidance is inputted by voice.
First, in the first step S110, it is determined whether or not the PTT switch 36 is turned on (pressed). This determination is made by the control unit 38. When the PTT switch 36 is turned on (S110: YES), it is determined whether or not a click operation is performed in the subsequent S120. This determination is also performed by the control unit 38. Specifically, when the PTT switch 36 is turned off for a relatively short time (for example, within 0.5 seconds), the click operation is performed. I reckon. If a click operation has been performed (S120: YES), it is determined in the subsequent S130 whether the operation is a double click operation. This determination is also performed by the control unit 38. Specifically, if the click operation is performed twice within a predetermined interval (for example, within 0.5 seconds), it is regarded as a double click operation. .
[0043]
If a negative determination is made in S130, it is determined that a click operation has been performed, the process proceeds to S140, and the contents of the guide for beginners are notified. On the other hand, if an affirmative determination is made in S130, it is determined that a double-click operation has been performed, and the process proceeds to S150 to notify the guide content for intermediate players.
[0044]
The contents of the guide for beginners and intermediates will be described later, and the description of the flowchart of FIG. 2 will be continued.
If the negative determination is not made in S120, that is, if it is not a click operation, the PTT switch 36 is kept pressed for a predetermined time or more, so that the process proceeds to S160 to execute voice extraction and recognition processing. The voice extraction unit 34 determines whether the voice segment is a voice segment or a noise segment based on the voice data input via the microphone 35, and outputs the voice segment data to the voice recognition unit. The voice recognition unit 31 collates the voice data acquired from the voice extraction unit 34 using stored dictionary data. Then, the upper comparison target pattern determined by the collation result is output to the dialogue control unit 32 as a recognition result.
[0045]
While the PTT switch 36 is kept on (S170: YES), such voice extraction / recognition (S160) is executed, and when the PTT switch 36 is turned off (S170: NO), it continues. In S180, the recognition result is talkbacked and displayed. That is, the dialogue control unit 32 controls the voice synthesis unit 33 and the display control unit 39 to output the recognized result from the speaker 37 by voice and to display a sentence indicating the recognition result on the display unit 40.
[0046]
Thereafter, in S190, it is determined whether or not the recognition is correct. This is determined according to an instruction from the user. For example, if the recognition is correct, “Yes” is input from the microphone 35, and if it is incorrect, “No” is input. It is possible to keep it. Of course, these instructions may be input via the operation switch group 8.
[0047]
If the recognition is incorrect (S190: NO), the process returns to S110. However, if the recognition is correct (S190: YES), the process proceeds to S200 to determine the recognition result. In subsequent S210, predetermined post-determination processing is executed. The post-determination process in this case is a process of outputting data related to “a destination for route guidance” as a recognition result to the control circuit 10 (see FIG. 1).
[0048]
After such post-determination process (S210) is completed, the process proceeds to S110, and the process returns to the determination process of whether or not the PTT switch 36 is turned on (pressed).
In the case of the present embodiment, the dialogue control unit 32, the voice synthesis unit 33, the control unit 38, the display control unit 39, and the display unit 40 correspond to “guide means”.
[0049]
Here, the content of the guide for beginners and intermediate users notified in S140 and S150 will be described.
First, a beginner's guide will be described.
(1) This guide is intended for users who do not know what they can input by voice to the navigation system. For this reason, for example, it is possible to guide the setting items that can be instructed by voice input, such as “You can set the destination”.
[0050]
Note that the content may be changed depending on which stage in the series of processes in the target system (in this case, the navigation device) instructed by voice input. For example, if the route to the destination is considered as a series of processing, after the destination is set, the conditions for setting the route, such as whether to specify the waypoint, are further specified. There is a case. Therefore, when a click operation is performed in a situation where the destination is already set, it is sufficient to notify the guide content such as “you can specify a waypoint”.
[0051]
{Circle around (2)} It is also assumed that even the user who has been given the above-mentioned guide and knows what to input to the navigation system does not know the specific input method. Therefore, if the click operation is performed without any voice input after the above-mentioned “You can set the destination” guide, “If you want to set the destination, enter the name of the prefecture. For example, it is conceivable to notify the description of the input method as guide contents.
[0052]
Note that even if this is not possible, it is assumed that the user cannot completely understand how to input, so it is assumed that the user cannot input. If the user clicks without any voice input after the guide, please enter a specific input example such as “Please enter Showa-cho, Kariya City, Aichi Prefecture”. It is conceivable to notify the contents. As a result, the user knows a specific input method, and if he / she informs a specific example, the user can easily input a destination desired by the user.
[0053]
Next, the intermediate guide will be described.
In the above-mentioned guide for beginners, every time a destination is clicked, the destination is set step by step, such as “You can set the destination” → “You can specify the waypoint” → Others did. On the other hand, as a guide for intermediate persons, it is also conceivable to report them together. In addition, the basic guide that the destination can be set is not provided, but only the specifiable conditions (that is, the waypoint specification, the road type specification, etc.) at the time of setting may be guided.
[0054]
Also, the beginner's guide as described in (2) above does not need to be reported for intermediate users.
As described above, if the voice recognition device 30 according to the present embodiment is used, a beginner who does not know what to input can be clicked. Because it is done, it is very easy to use. In addition, for intermediate players who know the basics but do not know the details, double-clicking will provide the necessary guides for the “intermediate” in the scene, so it is also very It is easy to use. It's also not confusing because it's not sequential, like a beginner's guide.
[0055]
On the other hand, since the guide contents are not notified without permission unless an operation requesting a guide such as a click or double click operation is performed, for a user who does not require a guide, while the PTT switch 36 is being pressed, If a predetermined voice input is performed, a desired voice input can be performed in a relatively short time (that is, compared to a state where the guide content is informed).
[0056]
As described above, according to the speech recognition apparatus 30 of the present embodiment, usability is improved for each user who has a different level of familiarity with the usage method of the speech recognition apparatus 30. In addition, since a special configuration is not required to accept the guide request operation, the PTT switch 36 and the control unit 38 necessary for basic processing for voice input can also be used for the guide request operation. It also contributes to simplification of the configuration.
[0057]
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.
(1) For example, in the above-described embodiment, the guide content related to destination setting has been described, but other guide content for map enlargement / reduction, direction designation (such as north-up / heading-up), or the like If it is an item that allows voice input in the car navigation system, the contents of the guide can be set similarly.
[0058]
(2) In the above-described embodiment, the long press of the PTT switch 36 is used as an operation for instructing the voice input period. However, a click operation or a double click operation is adopted for the start and end designation operations of the voice input period. Also good. In that case, as the guide request operation, an operation in which the switch operation start to end is a predetermined time or longer is adopted. In this case, the guide content may be started to be notified when the switch operation is continued for a predetermined time, and the guide content notification may be ended when the switch operation is finished. And what is necessary is just to recognize the user's audio | voice input after alert | reporting the content of the guide.
[0059]
(3) Moreover, in the said embodiment, although it was set as two types, a beginner and an intermediate level, as a user level of a guide object, you may set three or more types.
(4) In the above embodiment, the recognition result is notified and the guide content is notified by two types of sound and image. However, any form may be used as long as the user can be notified. If only one is employed, it is preferable to perform voice notification. This is because it is used as an in-vehicle device such as a car navigation system 2, and if it is output by voice, the driver does not have to shift the viewpoint to the display device, and further secures safe driving. This is because it is advantageous in that respect. Of course, as in the above-described embodiment, if the notification is made by both sound and image, the driver can perform both confirmation by display and confirmation by sound.
[0060]
(5) Further, the application destination of the voice recognition device 30 is not limited to the navigation system described above. For example, when the speech recognition apparatus is used for an air conditioning system, it is conceivable to adjust a set temperature, select an air conditioning mode (cooling / heating / dry), or select a wind direction mode by voice input. In this case, the setting item (temperature, air conditioning mode, wind direction mode, etc.) itself is notified as a guide content, or it can be said that “set the set temperature to 25 degrees” or “set the set temperature to 5”. It may be possible to further inform as guide contents whether or not it should be said that “degrade”. The same applies to the air conditioning mode and the wind direction mode.
Furthermore, the present invention is not limited to the case where the navigation system or the air conditioning system is used as an in-vehicle device, and may be used other than the in-vehicle device such as a portable navigation device or an indoor air conditioner. However, as described above, when used for in-vehicle devices, it is considered that the user is a driver. In that case, driving itself is the most important, and operations for other in-vehicle devices are as much as possible. It is preferable that there is no trouble in driving. Therefore, in the case of the speech recognition apparatus 30 based on the car navigation system 2 or the air conditioning system as the in-vehicle device, there are further advantages.
[0061]
Of course, from this point of view, it can be used in the same way for in-vehicle devices other than the navigation system and the air conditioning system. For example, a car audio device is effective. In addition, if a configuration in which so-called power window opening / closing and mirror angle adjustment are instructed by voice is considered, it can be similarly applied to such a control target and is also effective.
[0062]
In addition, although it has been described that there is a unique advantage when it is used for in-vehicle devices, the application destination of the speech recognition device 30 may be any one that executes predetermined processing in accordance with a voice input instruction by a user. 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.
[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 flowchart showing processing executed by the speech recognition apparatus.
[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 ... Dialog control unit
33 ... Speech synthesis unit 34 ... Speech input unit
35 ... Microphone 36 ... PTT switch
37 ... Speaker 38 ... Control unit
39 ... Display control unit 40 ... Display unit

Claims (11)

Voice input means for inputting voice;
An input period designating unit for performing a predetermined operation for the user to designate the start and end of a period for inputting a speech to be recognized using the voice input unit;
The voice inputted through the voice input means within the input period designated by the input period designating means is compared with a plurality of comparison target pattern candidates stored in advance in the dictionary means, and has a high degree of coincidence A recognition means as a recognition result;
Notification means for notifying the recognition result by the recognition means;
When a predetermined confirmation instruction is given after the recognition result is notified by the notification means, a post-confirmation processing means for executing a predetermined post-confirmation process as confirming the recognition result;
A speech recognition device comprising:
In the input period specifying means, two or more guide request operations different from the start and end specifying operations of the voice input period are set, and a guide request corresponding to the degree of familiarity is set for each of the guide request operations. Level is set,
When a guide request operation is performed by the input period specifying means, the guide means for notifying a predetermined guide content according to the corresponding guide request level,
The voice recognition apparatus characterized in that the guide means notifies the setting item itself that can be instructed via the voice input means as the guide content. The speech recognition apparatus according to claim 1,
The operation for specifying the start and end of the voice input period by the input period specifying means corresponds to the operation start and end when the switch operation start to end is a predetermined time or more, respectively.
On the other hand, the guide request level includes two levels, a beginner level and an intermediate level, and the guide request operation for the two levels includes a click operation in which the start and end of the switch operation are performed within a predetermined click time, A speech recognition apparatus, wherein a double-click operation in which a click operation is continuously performed twice within a predetermined interval corresponds to an operation at any level. The speech recognition device according to claim 2,
In the guide for beginners, the guide means notifies the guide contents in more detail than the guide contents previously notified when a click operation is performed without voice input after notifying the predetermined guide contents. A speech recognition apparatus characterized by: The speech recognition device according to any one of claims 1 to 3,
The voice recognition characterized in that the notification means is configured to notify the recognition result at least by voice, and the guide means is configured to notify the predetermined guide content at least by voice. apparatus. The speech recognition apparatus according to any one of claims 1 to 4,
The voice recognition apparatus characterized in that the predetermined guide contents notified by the guide means are contents relating to processing in a system in which a voice recognition result by the voice recognition apparatus is used. The speech recognition apparatus according to claim 5.
The speech recognition apparatus, wherein the guide means is configured to notify guide content corresponding to a process execution stage in the system at the time when the predetermined guide content is notified. Voice input means for inputting voice;
An input period designating unit for performing a predetermined operation for the user to designate the start and end of a period for inputting a speech to be recognized using the voice input unit;
The voice inputted through the voice input means within the input period designated by the input period designating means is compared with a plurality of comparison target pattern candidates stored in advance in the dictionary means, and has a high degree of coincidence A recognition means as a recognition result;
Notification means for notifying the recognition result by the recognition means;
When a predetermined confirmation instruction is given after the recognition result is notified by the notification means, a post-confirmation processing means for executing a predetermined post-confirmation process as confirming the recognition result;
A speech recognition device comprising:
In the input period specifying means, two or more guide request operations different from the start and end specifying operations of the voice input period are set, and a guide request corresponding to the degree of familiarity is set for each of the guide request operations. Level is set,
When a guide request operation is performed by the input period specifying means, the guide means for notifying a predetermined guide content according to the corresponding guide request level,
The predetermined guide content notified by the guide means is content related to processing in a system in which a speech recognition result by the speech recognition apparatus is used,
The guide means is configured to notify the guide content corresponding to the process execution stage in the system at the time when the predetermined guide content is notified,
A voice recognition apparatus characterized in that the guide means informs a setting item itself that can be instructed via the voice input means in the process execution stage as guide contents corresponding to the process execution stage in the system. . The speech recognition apparatus according to claim 7.
The operation for specifying the start and end of the voice input period by the input period specifying means corresponds to the operation start and end when the switch operation start to end is a predetermined time or more, respectively.
On the other hand, the guide request level includes two levels, a beginner level and an intermediate level, and the guide request operation for the two levels includes a click operation in which the start and end of the switch operation are performed within a predetermined click time, A speech recognition apparatus, wherein a double-click operation in which a click operation is continuously performed twice within a predetermined interval corresponds to an operation at any level. The speech recognition apparatus according to claim 8.
In the guide for beginners, the guide means notifies the guide contents in more detail than the guide contents previously notified when a click operation is performed without voice input after notifying the predetermined guide contents. A speech recognition apparatus characterized by: The speech recognition apparatus according to any one of claims 7 to 9 ,
The voice recognition characterized in that the notification means is configured to notify the recognition result at least by voice, and the guide means is configured to notify the predetermined guide content at least by voice. apparatus. A voice recognition device according to any one of claims 1 to 10 and a navigation device,
The voice input means of the voice recognition device is used for a user to input by voice an instruction of predetermined navigation processing related data that needs to be specified at least when the navigation device performs a navigation process. The navigation system is characterized in that the post-determination processing means is configured to output a recognition result by the recognition means to the navigation device.

Images