JP4458037B2 - Information input device - Google Patents

Description

  The present invention relates to an information input device, and more particularly to an information input device capable of sequentially inputting a series of information by manual operation and voice input.

  2. Description of the Related Art As an information input device, a device that can input various information by two means of manual operation and voice input is widely known. For example, the apparatus described in Patent Document 1 is this.

  The information input device described in Patent Document 1 is for a vehicle, and in the case of an information input device for a vehicle, it is dangerous to manually input information while the vehicle is running. Can often be entered.

  There are various types of information to be input to the information input device. For example, when inputting information for setting a destination to a navigation device as an information input device, setting of the destination is usually started. Therefore, a predetermined command is input as information, and then information for narrowing down the destination is input. If the address is taken as an example as information for narrowing down the destination, it is necessary to input the name of the prefecture, then the name of the municipality, and then the address and the like. Also, in the case of music playback, it is necessary to select a source such as CD, MD, etc., and then select a song. Necessary. Thus, it may be necessary to sequentially input a series of information to the information input device.

  When a series of information is sequentially input, it is natural that a certain amount of time is required from the start of the input of the series of information to the end. Therefore, if a series of information input is started manually while waiting for a signal at an intersection or the like, the information input may not be completed while waiting for the signal.

  Therefore, in Patent Document 1, the vehicle traveling speed is acquired, and it is determined whether or not the vehicle is currently traveling. When it is determined that the vehicle has started to travel, input of information by manual operation is prohibited, and the continuation is performed by voice input. In this way, when the input method is switched from manual operation to voice input, the operation performed halfway by manual operation can be saved.

  As described above, when the continuation of the manual operation is performed by voice input, the operation step by the voice input goes through the same steps as when the operation is continued by the manual operation. In the case of voice input, a recognition dictionary for recognizing voice is selected according to the operation step.

A technique is also known in which both manual input of information and voice input can be mixed to compensate for both drawbacks (for example, Patent Document 2).
JP-A-9-16891 JP 2003-5897 A

  When inputting information by voice, it is not always necessary to go through the same steps as in manual operation, and a function unique to voice recognition that is not usually in manual operation is provided. As a function specific to this voice input, for example, in the case of the above-described navigation device, at the initial point of the start of voice recognition, by saying “Return to home”, the destination, that is, the setting of the home, the route to the home There is a function that a route from the current location to the home is set and a route guidance is started with a single utterance without performing a plurality of operations such as setting and starting a route guidance.

  By the way, in the apparatus described in the above-mentioned Patent Document 1, when switching from manual operation to voice input, the operation performed by manual operation is always continued. For this reason, for example, when music playback was performed manually while waiting for a signal, but the signal changed and the vehicle had to be driven, I wanted to rush to start route guidance to my home. However, the route guidance to the home could not be started using the above-mentioned functions specific to voice input.

  As described above, in the conventional technology, although a series of information input by manual operation can be continued by voice input, in that case, a function unique to voice input cannot be used, and voice input is not possible. The advantage was impaired.

  The present invention has been made on the basis of this circumstance, and the object of the present invention is to allow a continuous input of a series of information by voice operation to be continued by voice input, while not losing the advantages of voice input. It is to provide an information input device.

  In order to achieve the object, the invention according to claim 1 includes a manual operation input unit for manually inputting information and a voice input unit for inputting information by voice in order to sequentially input a series of information. A recognition dictionary for recognizing voice input from the voice input unit is an information input device set according to information that can be input from the voice input unit, and the manual operation input unit is used as the recognition dictionary. There is a selection means for the user to select whether to use a continuous recognition dictionary corresponding to information that can be input following the information input from, or to use an initial recognition dictionary for recognizing a predetermined initial command. It is characterized by that.

  In this way, when the user selects to use the continuous recognition dictionary as the recognition dictionary by the selecting means, it is possible to continue inputting a series of information by manual operation by voice input. Thus, when the user selects to use the initial recognition dictionary as the recognition dictionary by the selection means, the initial command can be recognized, so that the advantage of voice input is not impaired.

  The selection means includes a continuation mode selection switch for selecting the continuation recognition dictionary and an initial mode selection switch for selecting the initial recognition dictionary, as described in claim 2. it can.

  However, it is not always necessary to provide two mode selection switches. As described in claim 3, the selection means selects a continuous mode selection switch for selecting the continuous recognition dictionary or the initial recognition dictionary. In a state where voice recognition is possible and the continuous mode selection switch or the initial mode selection switch is not operated, a mode selection switch of the continuous recognition dictionary and the initial recognition dictionary is provided. It is also possible to use a recognition dictionary opposite to the side selected by operating.

  As described above, when either the continuous mode selection switch or the initial mode selection switch is provided, the user operates the selection switch to enter the recognition mode using the continuous recognition dictionary or use the initial recognition dictionary. It is possible to freely select the recognition mode.

  Here, when the information input device is for a vehicle and has two mode selection switches as in claim 2, a display screen for displaying an information input guidance screen is provided as in claim 4. It is preferable that the continuation mode selection switch is displayed on the display screen.

  In this way, when the information input guidance screen is displayed on the display screen, the user usually looks at the display screen when the information is input by operating the manual operation input unit. it is conceivable that. Therefore, as described in claim 4, if the continuation mode selection switch is selected on the display screen, a user who wants to perform a continuation operation by voice input can easily notice the switch.

  Further, when the continuous mode selection switch is provided on the display screen as described in claim 4, the display is displayed on the display screen when the input of a series of information is not completed as in claim 5. While the continuous mode selection switch is operable, it is preferable to disable the continuous mode selection switch when the input of the series of information is completed. In this way, it is possible to prevent the continuation mode selection switch from being operated when unnecessary.

  According to a sixth aspect of the present invention, it is preferable that the initial mode selection switch is provided on a steering wheel.

  In this way, it is possible to shorten the time that the driver holding the steering wheel has to release his hand from the steering wheel, which is preferable in terms of safe driving.

  The invention according to claim 7 is the information input device according to any one of claims 1 to 6, further comprising vehicle travel determination means for determining whether or not the vehicle is traveling, the vehicle travel state Based on the fact that the vehicle is determined to be in the running state from the stop state by the determination means, the input operation from the manual operation input unit is restricted and the input from the voice input unit is made possible. Features.

  As described above, it is preferable from the viewpoint of safety that the input operation from the manual operation input unit is restricted while the vehicle is running so that the voice input unit can input.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a vehicle information input device to which the present invention is applied.

  This information input device is a device for an occupant to input various information to an external device 200 (navigation device, air conditioner, audio device, etc.) mounted on the vehicle, and serves as an input unit for the occupant to input. The operation key group 10 and the microphone 12 are provided.

  The operation key group 10 corresponds to a manual operation input unit in which information is manually input by an occupant, such as a mechanical key arranged at a predetermined part of the dashboard, a key provided on a remote controller (not shown), These are keys displayed on the display screen of the display device 14.

  The microphone 12 is a voice input unit that allows the passenger to input information by voice, and is provided in a portion where the driver's voice can be detected.

  Information input from the operation key group 10 and the microphone 12 is output to the ECU 100. The ECU 100 is a so-called computer and includes a CPU, a ROM, a RAM, an I / O port, and the like. And that CPU implement | achieves the function mentioned later by processing the signal input into ECU100 according to the program previously memorize | stored in ROM, utilizing the temporary storage function of RAM.

  The display device 14 is, for example, a liquid crystal display, and is disposed at an intermediate position between the driver seat and the passenger seat of the instrument panel. The display device 14 displays various information such as an information input guidance screen on its display screen in accordance with a signal from the ECU 100. The guidance screen is, for example, a screen that displays keys that are operated according to the state of the external device 200, or a screen that displays some or all of the recognized words that can be recognized at that time when voice input is possible. is there.

  The speaker 16 outputs a predetermined sound based on a signal from the ECU 100. The vehicle speed sensor 18 detects the vehicle speed and outputs a signal representing the detected vehicle speed to the ECU 100.

  The continuation mode selection switch 20 and the initial mode selection switch 22 are both switches that are operated when voice operation is started. In the present embodiment, the continuation mode selection switch 20 is a switch displayed on the display screen of the display device 14. The continuation mode selection switch 20 is selectable from the start of a predetermined series of operations by the operation key group 10 to the end thereof, but is displayed gray after the series of operations is completed. The display is not selectable such as, or is not displayed. On the other hand, the initial mode selection switch 22 is disposed at a predetermined part of the steering such as the center of the steering.

  The recognition dictionary group 24 includes a large number of recognition dictionaries corresponding to the operating state of the external device 200. For example, a recognition dictionary corresponding to the destination setting mode of the navigation device, a recognition dictionary corresponding to the audio song selection mode, a recognition dictionary corresponding to the air conditioning setting operation mode, and the like are provided. In some cases, the external device 200 may need to input a series of commands in order, such as a destination setting operation of the navigation device, and the recognition dictionary included in the recognition dictionary group 24 is a sequence of commands. A recognition dictionary for recognizing a command input first, and a continuation recognition dictionary for recognizing a continuation command input following the command. The recognition dictionary group 24 also includes an initial recognition dictionary that recognizes a predetermined initial command. This initial recognition dictionary is a voice command that designates which of a plurality of external devices 200 is an operation target, and a part of the external devices 200 has one command having the same function as a series of commands. The recognition vocabulary for recognizing the voice command (for example, “going home” described above) is included.

  The acoustic model 26 stores feature quantities that take into account the continuation of syllables such as the Japanese syllabary. The recognition dictionary group 24 and the acoustic model 26 are stored in a predetermined storage device such as a ROM.

  Next, the configuration of the ECU 100 will be described. The ECU 100 includes a vehicle travel determination unit 102, an input means determination unit 104, a device state analysis unit 106, a screen control unit 108, a manual input signal processing unit 109, and a voice input signal processing unit 110.

  The vehicle travel determination unit 102 corresponds to the vehicle travel determination means in the claims, and determines whether the vehicle is in a traveling state or in a stopped state based on a signal representing the vehicle speed supplied from the vehicle speed sensor 18. To do.

  When the vehicle travel determination unit 102 determines that the vehicle is stopped, the input means determination unit 104 outputs a signal permitting input of information by the operation key group 10 to the manual input signal processing unit 109. When the vehicle traveling determination unit 102 determines that the vehicle is in a traveling state, a signal for prohibiting input of information by the operation key group 10 is output to the manual input signal processing unit 109 and voice input is permitted. The signal is output to the voice input signal processing unit 110.

  Based on the signal from the external device 200, the device state analysis unit 106 determines what kind of signal is being processed in the operation state of the external device 200. This determination includes determining whether or not the external device 200 is in the middle of executing a predetermined series of processes. Then, a signal indicating the operation state of the external device 200 is output to the screen control unit 108 and the voice recognition processing control unit 113.

  The screen control unit 108 displays a guidance screen for guiding information input in the state according to the state of the external device 200 analyzed by the device state analysis unit 106. It also controls whether the continuation mode selection switch 20 is a selectable display or a non-selectable display.

  The manual input signal processing unit 109 processes a signal input from the operation key group 10 according to the operation state of the external device 200 analyzed by the device state analysis unit 106, and outputs a control signal to a predetermined external device 200 To do.

  The voice input signal processing unit 110 includes a voice start information analysis unit 111, a recognition engine 112, a voice recognition processing control unit 113, and a recognition result output unit 114.

  The voice start information analyzing unit 111 receives the signal indicating that the mode selection switch has been operated from the continuous mode selection switch 20 or the initial mode selection switch 22, and performs voice recognition to the voice recognition processing control unit 113. Output a signal to start. Further, by determining which mode selection switch 20 or 22 is the signal, a signal for instructing whether the speech recognition processing is to be the continuous mode or the initial mode is also sent to the speech recognition processing control unit 113. Output.

  When a signal instructing voice recognition start is input from the voice start information analysis unit 111, the voice recognition processing control unit 113 operates the recognition engine 112 and the operation of the external device 200 supplied from the device state analysis unit 106. A signal representing the state is output to the recognition engine 112.

  The recognition engine 112 selects a predetermined recognition dictionary from the recognition dictionary group 24 based on a signal representing the operation state of the external device 200 supplied from the speech recognition processing control unit 113, and the selected recognition dictionary and acoustic model 26 are selected. Is used to recognize which one of the voice commands included in the recognition dictionary is generated by the occupant input from the microphone 12. The voice command recognized here is output to the voice recognition processing control unit 113 and sent from the voice recognition processing control unit 113 to the recognition result output unit 114.

  The recognition result output unit 114 outputs the recognition result in the recognition engine 112 sent via the voice recognition processing control unit 113 from the speaker 16 and the display device 14 and outputs the recognition result to the external device 200.

  2 and 3 are flowcharts showing the main part of the processing contents in the ECU 100. FIG. The flowchart of FIG. 2 is executed when it is determined that the vehicle is temporarily stopped.

  First, in step S21 of FIG. 2, the vehicle speed is detected based on a signal from the vehicle speed sensor 18. In the subsequent step S22, the vehicle speed detected in step S21 is compared with a predetermined judgment reference speed (for example, 5 to 10 km / h) set near the lower limit speed that can be detected by the vehicle speed sensor 18. Then, it is determined whether or not the vehicle has resumed running. Steps S <b> 21 and S <b> 22 are processes in the vehicle travel determination unit 102.

  If the determination in step S22 is negative, step S21 and subsequent steps are executed again. On the other hand, if step S22 is affirmative, in step S23, input of signals from the operation key group 10 is prohibited, while voice input is enabled, and a series of processing shown in FIG. 3 is executed.

  In FIG. 3, first, in step S30, it is determined whether or not a series of operations are being performed on the external device 200 by manual operation. This determination is a process in the device state analysis unit 106, based on a signal from the external device 200, determines whether or not a series of operations are being performed, and based on a signal from the audio input signal processing unit 110. Then, by determining whether or not the voice input signal processing unit 110 is operating, it is determined whether or not a series of operations is a manual operation.

  If it is determined in step S30 that the operation is not in the middle of manual operation, step S31 is executed, and the continuation mode selection switch 20 is displayed as an unselectable display. Note that, while the vehicle is stopped, the continuation mode selection switch 20 is selectable until step S31 is executed.

  On the other hand, if it is determined in step S30 that the manual operation is in progress, step S32 is executed and the continuation mode selection switch 20 remains in a selectable display. These steps S31 and S32 are processes in the screen control unit 108.

  Then, after step S31 or S32 is executed, it is determined in step S33 whether or not an operable selection switch has been operated. The selectable switches that can be operated are the continuous mode selection switch 20 and the initial mode selection switch 22 when Step S32 is executed, but only the initial mode selection switch 22 when Step S31 is executed. The process in step S33 is a process in the voice start information analysis unit 111, and the voice recognition process is started by operating these selection switches 20 and 22. Accordingly, the two selection switches 20 and 22 function as switches that instruct the start of voice recognition.

  Note that step S33 is executed when the vehicle travel is resumed, but the initial mode selection switch 22 can be operated at all times, not only when the vehicle travel is resumed, and when the initial mode selection switch 22 is other than when the vehicle travel is resumed. When operated, a predetermined voice recognition process determined according to the operation state of the external device 200 at that time is executed.

  If the determination in step S33 is negative, step S33 is repeatedly executed. On the other hand, if the determination in step S33 is affirmative, it is further determined in step S34 whether or not the selection switch operated by the occupant is the continuation mode selection switch 20. If this determination is affirmative, that is, if the operated selection switch is the continuation mode selection switch 20, in step S35, from the recognition dictionary group 24, based on the operating state of the external device 200 at that time. The fixed continuous recognition dictionary is set as a recognition dictionary used by the recognition engine 112.

  On the other hand, if the determination in step S34 is negative, that is, if the operated selection switch is the initial mode selection switch 22, in step S36, a preset initial command recognition dictionary is set from the recognition dictionary group 24. Is set as a recognition dictionary used by the recognition engine 112.

  In step S37, the speech recognition process is executed using the recognition dictionary set in step S35 or S36. In a succeeding step S38, a function for the result recognized in the recognition process in the step S37 is executed for a predetermined external device 200.

  In the subsequent step S39, it is determined whether or not a series of processing has been completed by executing a predetermined function in step S38. If this determination is affirmative, the process in FIG. 3 ends. On the other hand, if the determination is negative, step S37 and subsequent steps are repeatedly executed until a series of processing ends. In the second and subsequent executions of step S37, the recognition dictionary is changed according to the operating state of the external device 200.

  As described above, according to the present embodiment described above, when the vehicle resumes running from a temporarily stopped state, the occupant can input voice by operating the continuous mode selection switch 20 or the initial mode selection switch 22. Become. When the continuation mode selection switch 20 is operated in a state where a predetermined series of operations are performed by the operation key group 10, a continuation recognition dictionary is used as a recognition dictionary. Information input can be continued by voice input. On the other hand, when the occupant operates the initial mode selection switch 22, the initial recognition dictionary is used as the recognition dictionary. Therefore, when the use is selected, the same function as a series of commands is realized with one command. Since the initial command including the voice command can be recognized, the advantage of the voice input is not impaired.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to the above-mentioned embodiment, The following embodiment is also contained in the technical scope of this invention, and also the summary other than the following is also included. Various modifications can be made without departing from the scope.

  For example, in the above-described embodiment, two mode selection switches, the continuous mode selection switch 20 and the initial mode selection switch 22, are provided, and the recognition dictionary is set based on the operation of one of the mode selection switches. However, only one of the mode selection switches may be provided. For example, when only the initial mode selection switch 22 is provided, if the determination in step S30 is affirmative, the continuous recognition dictionary may be used unless the initial mode selection switch 22 is operated.

  In the above-described embodiment, voice input is possible when it is determined that the vehicle has traveled, but voice input may be possible even when the vehicle is stopped. In this case, the voice operation may be started based on the operation of the mode selection switches 20 and 22, or the voice input is automatically performed based on the state of the external device 200 regardless of the operation from the passenger. May be possible.

  In the above-described embodiment, the continuous mode selection switch 20 is displayed on the display screen of the display device 14, while the initial mode selection switch 22 is provided on the steering wheel. 22 may be provided on the display screen. In this case, it is easy to understand that two modes can be selected. Further, both switches 20 and 22 may be provided on the steering. Also in this case, it is easy to understand that two modes can be selected, and it is also preferable for safe driving.

  Further, in the above-described embodiment, the manual input operation is prohibited when the vehicle resumes traveling. However, some manual input operations may be possible even while the vehicle is traveling.

  In the above-described embodiment, the selection means is the switches 20 and 22, that is, the means for the occupant to manually select, but the occupant is inquired about which mode to select, and as a result, is input from the microphone. The recognition dictionary may be selected by voice.

It is a block diagram which shows the structure of the information input device for vehicles to which this invention was applied. It is a flowchart which shows the principal part of the processing content in ECU100 of FIG. FIG. 3 is a flowchart executed following FIG. 2. FIG.

Explanation of symbols

10: Operation key group (manual operation input part)
12: Microphone (voice input unit)
14: Display device 20: Continue mode selection switch 22: Initial mode selection switch 24: Recognition dictionary group 102: Vehicle travel determination unit (vehicle travel determination means)
200: External device

Claims (7)

In order to sequentially input a series of information, a manual operation input unit that inputs information manually and a voice input unit that inputs information by voice,
A recognition dictionary for recognizing a voice input from the voice input unit is an information input device set according to information that can be input from the voice input unit,
Whether the user uses a continuous recognition dictionary corresponding to information that can be input following the information input from the manual operation input unit or an initial recognition dictionary for recognizing a predetermined initial command as the recognition dictionary. An information input device comprising selection means for selecting.   2. The information according to claim 1, comprising: a continuation mode selection switch for selecting the continuation recognition dictionary and an initial mode selection switch for selecting the initial recognition dictionary as the selection means. Input device. As the selection means, comprising a continuous mode selection switch for selecting the continuous recognition dictionary, or an initial mode selection switch for selecting the initial recognition dictionary,
In a state in which voice recognition is possible, when the continuous mode selection switch or the initial mode selection switch is not operated, the continuous selection dictionary and the initial recognition dictionary are selected by operating the mode selection switch. 2. The information input device according to claim 1, wherein a recognition dictionary opposite to the side is used. The information input device according to claim 2, wherein the information input device is for a vehicle.
It has a display screen that displays an information input guidance screen,
The information input device, wherein the continuation mode selection switch is displayed on a display screen thereof.   When the input of the series of information is not finished, the continuous mode selection switch displayed on the display screen can be operated. On the other hand, when the input of the series of information is finished, the continuous mode selection switch The information input device according to claim 4, wherein the operation is disabled.   6. The information input device according to claim 4, wherein the initial mode selection switch is provided on a steering wheel. Vehicle travel determining means for determining whether or not the vehicle is traveling,
A state in which an input operation from the manual operation input unit is restricted and an input from the voice input unit is possible based on the vehicle running state determination means determining that the vehicle has changed from a stopped state to a traveling state The information input device according to claim 1, wherein the information input device is an information input device.

Images