JP4694017B2 - In-vehicle speech recognition device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a vehicle-mounted speech recognition apparatus that controls the start and end of speech recognition by a switch operation.
[0002]
[Prior art]
In general, an in-vehicle voice recognition device having a function of enabling voice recognition when an operator presses a voice recognition control switch is known. This type of device has an advantage of enabling stable recognition because it can prevent erroneous recognition of noise and the like, compared to a vehicle-mounted speech recognition device that is always in a speech recognition state. Conventionally, as means for notifying an operator of a state in which voice recognition is possible, a method for displaying a symbol indicating that recognition is possible as image information on a display of an information device or tilting a doll's ear has been proposed. . Also, there is a method of notifying the state where voice recognition is possible with a display lamp, as in the invention described in Japanese Patent Laid-Open No. 7-250171.
[0003]
[Problems to be solved by the invention]
However, in-vehicle information devices, such as in-vehicle navigation devices, can display symbols that can be recognized as image information, tilt a doll's ears, or be recognized by a display lamp to ensure safe driving of the vehicle. It is not possible to adopt a method based on visual information such as notification.
[0004]
On the other hand, if the in-vehicle speech recognition device is always operated, it will cause malfunction due to noise in the vehicle and malfunction due to utterance during conversation other than voice commands, so an algorithm to avoid it is necessary and control is required. To be complicated.
[0005]
Accordingly, an object of the present invention is to provide an in-vehicle voice recognition device that solves the above-described problems of the prior art and enables an operator to recognize the status of the in-vehicle voice recognition device by a method that is not visual information. It is in.
[0006]
[Means for Solving the Problems]
The invention according to claim 1 is an in-vehicle speech recognition apparatus including a speech recognition unit that recognizes speech and a switch that instructs to start speech recognition, and includes a force application unit that applies force to the switch. The voice recognition unit is configured to perform voice recognition while the button is continuously pressed, and during the activation time of the voice recognition unit generated immediately after the switch is pressed, During the period in which the switch is kept pressed, the force acting unit is operated during a state in which speech recognition cannot be performed in accordance with execution of a process corresponding to a voice command by the voice recognition unit .
[0007]
The invention described in claim 2 is characterized in that the switch is installed on a handle .
[0009]
According to a third aspect of the present invention, in the first or second aspect of the present invention, the force acting portion is a vibrator.
[0010]
According to a fourth aspect of the present invention, in the first or second aspect of the present invention, the force acting portion is an actuator.
[0011]
The invention according to claim 5 has a sound generator that generates sound in the invention according to any one of claims 1 to 4 , and the sound generator when the voice recognizer becomes capable of voice recognition. Emits sound.
[0014]
The invention according to any one of claims 1 to 5 has the following effects.
[0015]
When a voice recognition start operation is performed with a switch, the operator recognizes the status of the on-vehicle speech recognition device by a method that is not visual information depending on the state of the force applied to the switch according to the status of the on-vehicle speech recognition device. Can do.
[0018]
The invention according to claim 5 has the following effects.
[0019]
When a voice recognition start operation is performed with the switch, the operator can recognize the status of the in-vehicle voice recognition device by a method that is not visual information based on the sound information corresponding to the status of the in-vehicle voice recognition device.
[0020]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[0021]
[A] First Embodiment FIG. 1 shows an on-vehicle speech recognition apparatus according to a first embodiment. This in-vehicle voice recognition device is attached to an in-vehicle information device and includes a switch unit 1 for voice recognition control, a voice recognition control unit 2, a voice recognition unit 3, and a system control unit 4. Has been. The switch unit 1 includes a switch 5 and a vibrator 6 and is connected to the voice recognition control unit 2 by wire or wirelessly. This switch part 1 is installed in the handle | steering-wheel of a vehicle, for example so that attachment or detachment is possible, and removes it when unnecessary. The system control unit 4 is connected to a sound generating unit (for example, a chime 7) that emits sound.
[0022]
The voice recognition control unit 2 has a function of enabling voice recognition of voice commands when the operator turns on the switch 5 and ending voice recognition of voice commands when the operator turns off the switch 5. Configured. Here, the switch 5 is turned on when the operator continues to press the switch 5, and the switch 5 is turned off when the operator stops pressing the switch 5.
[0023]
In the above configuration, when the switch 5 is turned on as shown in FIG. 2A, the speech recognition unit 3 is activated by the speech recognition control unit 2. As shown in FIG. 2B, the activation of the voice recognition unit 3 requires an activation time t. During the activation time t, speech recognition is impossible. In response to the switch 5 being turned on and the voice recognition unit 3 is in a state where voice recognition is impossible as shown in FIG. 2B, the system control unit 4 turns on the vibrator 6 of the switch unit 1 as shown in FIG. 2C. Is controlled to vibrate the switch 5.
[0024]
When the voice recognition unit 3 is in a state where voice recognition is possible as shown in FIG. 2B, the system control unit 4 stops the vibration of the vibrator 6 of the switch unit 1 and vibrates the switch 5 as shown in FIG. 2C. At the same time, the sound information is provided by the chime 7 as shown in FIG. Then, when receiving the voice command issued by the operator, the voice recognition unit 3 starts processing according to the voice command, and as shown in FIG. When the voice recognition unit 3 becomes capable of voice recognition again as shown in FIG. 2B, the above operation is repeated.
[0025]
When the switch 5 is turned off as shown in FIG. 2A, the voice recognition unit 3 is in a state where voice recognition is not possible and voice is not received, and the vibrator 6 of the switch unit 1 is not vibrated.
[0026]
With the configuration as described above, the above embodiment has the following effects (1) to (3).
[0027]
(1) When the operator turns on the switch 5, the operator can recognize the state in which the voice recognition unit 3 cannot recognize the voice by tactile information such as the vibration of the switch 5 by the vibrator 6. Further, the operator can recognize the state in which the voice recognition unit 3 can recognize the voice by providing tactile information such as stop of the vibration of the switch 5 by the vibrator 6 and the sound information of the chime 7. As a result, the operator can recognize the situation of the in-vehicle voice recognition device by a method that is not visual information.
[0028]
(2) Since the switch 5 is installed at the handle and at hand, when the driver of the vehicle is an operator, the tactile information of the switch 5 is not visual information, but the user does not take his hand off the handle while driving the vehicle. The situation of the in-vehicle voice recognition device can be recognized by the method according to the above.
[0029]
(3) Since the switch unit 1 can be attached to and detached from the handle, the switch unit 1 can be detached from the handle when the driver does not operate or when a person other than the driver becomes the operator.
[0030]
[B] Second Embodiment FIG. 3 shows an in-vehicle speech recognition apparatus according to the second embodiment. This in-vehicle speech recognition apparatus is, for example, in-vehicle as an example of in-vehicle information equipment having a remote controller. The case where it is mounted on a navigation device is shown. In the second embodiment, the same parts as those in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.
[0031]
In FIG. 3, the in-vehicle navigation device 10 includes an in-vehicle navigation device body 11 and a remote controller 12. The voice recognition control unit 2, the voice recognition unit 3, and the system control unit 4 of the in-vehicle voice recognition device are provided in the in-vehicle navigation device body 11. The switch unit 1 of the on-vehicle voice recognition device includes a switch 5 and an actuator 13, and is connected to the voice recognition control unit 2 by wire or wirelessly and is mounted on the remote controller 12. The system control unit 4 is connected to a sound generating unit (for example, a chime 7) that emits sound.
[0032]
In the above configuration, when the switch 5 is turned on as shown in FIG. 4A, the voice recognition unit 3 is activated by the voice recognition control unit 2. As shown in FIG. 4B, the activation of the voice recognition unit 3 requires an activation time t. During the activation time t, speech recognition is impossible. In response to the switch 5 being turned on, the system control unit 4 turns the actuator 13 of the switch unit 1 as shown in FIG. 4C when the speech recognition unit 3 is in a state where speech recognition is impossible as shown in FIG. 4B. The switch 5 is operated so that a repulsive force is applied to the switch 5.
[0033]
When the voice recognition unit 3 is in a state where voice recognition is possible as shown in FIG. 4B, the system control unit 4 stops the operation of the actuator 13 of the switch unit 1 and repels the switch 5 as shown in FIG. 4C. At the same time, the sound information of the chime 7 is provided by the system control unit 4 as shown in FIG. 4D. Then, when receiving the voice command issued by the operator, the voice recognition unit 3 starts processing according to the voice command, and as shown in FIG. When the voice recognition unit 3 becomes capable of voice recognition again as shown in FIG. 4B, the above operation is repeated.
[0034]
When the switch 5 is turned off as shown in FIG. 4A, the voice recognition unit 3 is in a state where voice recognition is not possible without accepting voice, and the operation of the actuator 13 of the switch unit 1 is also stopped and the repulsive force is applied to the switch 5 Is stopped.
[0035]
With the configuration described above, the above embodiment has the following effects (1) and (2).
[0036]
(1) When the operator turns on the switch 5, the operator can recognize the state in which the voice recognition unit 3 cannot recognize the voice by tactile information such as the repulsive force of the switch 5 by the actuator 13. Further, the operator can recognize the state in which the voice recognition unit 3 can recognize the voice by providing tactile information such as the stop of the repulsive force to the switch 5 by the actuator 13 and the sound information of the chime 7. As a result, the operator can recognize the situation of the in-vehicle voice recognition device by a method that is not visual information.
[0037]
(2) Since the switch 5 of the in-vehicle voice recognition device is mounted on the remote controller 12 of the in-vehicle navigation device 10, the remote controller 12 can operate the switch 5 of the in-vehicle voice recognition device and visually The situation of the in-vehicle voice recognition device can be recognized not by the information but by the tactile information of the switch 5 of the remote controller 12.
[0038]
As mentioned above, although this invention was demonstrated based on one Embodiment, this invention is not limited to this.
[0039]
For example, the case where the vibrator 6 or the actuator 13 is used and the chime 7 is used has been described. However, the operator recognizes that the voice recognition unit 3 can recognize the voice using only the vibrator 6 or the actuator 13. Alternatively, the operator may recognize that the voice recognition unit 3 is capable of voice recognition only with the chime 7.
[0040]
Moreover, although the case where chime 7 was installed in the vehicle-mounted information equipment side was demonstrated, you may install in switch part 1 and remote control 12 which were installed in the handle.
[0041]
Further, the case where the switch 5 is turned on by continuing to press the switch 5 and the switch 5 is turned off by stopping pressing the switch 5 has been described. However, the initial state is, for example, the off state. Each time the switch 5 is pressed such that when the switch 5 is pressed, the switch is turned on and the on state is maintained, and when the switch 5 is pressed again, the switch 5 is switched off and the off state is maintained. Alternatively, the on / off state may be switched.
[0042]
【The invention's effect】
In the present invention, the operator can recognize the situation of the in-vehicle voice recognition device by a method that is not visual information, and the operator can operate the in-vehicle voice recognition device without any stress. can get.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a first embodiment of an in-vehicle speech recognition device according to the present invention.
FIG. 2 is a time chart of the in-vehicle speech recognition apparatus shown in FIG.
FIG. 3 is a block diagram showing a second embodiment of the in-vehicle speech recognition device according to the present invention.
4 is a time chart of the in-vehicle speech recognition apparatus shown in FIG.
[Explanation of symbols]
3 Voice recognition unit 5 Switch 6 Vibrator 7 Chime (Sound generation unit)
10 In-vehicle navigation system (in-vehicle information equipment)
12 Remote controller 13 Actuator

Claims (5)

A voice recognition unit for voice recognition;
In a vehicle-mounted speech recognition device having a switch for instructing the start of speech recognition,
Providing a force acting portion for applying force to the switch;
As long as the switch is kept pressed, voice recognition by the voice recognition unit is performed,
During the activation time of the voice recognition unit that occurs immediately after the switch is pressed, the force acting unit is operated, and the voice command by the voice recognition unit corresponds to the period during which the switch is kept pressed. A vehicle-mounted speech recognition apparatus that operates the force acting unit during a state in which speech recognition cannot be performed in accordance with execution of processing . The in-vehicle voice recognition apparatus according to claim 1, wherein the switch is installed on a handle. Vehicle speech recognition apparatus according to claim 1 or 2, wherein the force acting portion is characterized by a vibrator. Vehicle speech recognition apparatus according to claim 1 or 2, characterized in that the force acting portion is an actuator. Has a sound generator for generating a sound, when said voice recognition unit has become possible speech recognition, mounted on a car according to any one of claims 1 to 4 wherein the tone generating section is characterized by emitting a sound Voice recognition device.

Images