JP2009025715A - In-vehicle device and speech recognition method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an in-vehicle device 20 in which, according to a position in a vehicle where a passenger is seated, an operation command which is permitted for the crew who is seated at the position can be set, in the in-vehicle device 20 for performing processing according to the operation command which is input by speech. <P>SOLUTION: The in-vehicle device 20 of the invention 20 in which an operation command permitted for each seat position is determined beforehand, specifies the speech generation position of speech corresponding to the speech signal from the speech signal collected via a plurality of microphones 11, when the operation command is input by speech, and performs processing corresponding to the operation command, when the operation command by the speech is the one permitted at the generation position. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an apparatus that is mounted on a vehicle and executes processing in accordance with an operation command input by voice.

  Patent Document 1 discloses an in-vehicle navigation device that permits all operations when the vehicle is stopped, and permits only predetermined operations when the vehicle is running. Thereby, it is possible to prevent the driver from operating an operation that needs to be performed while gazing at the screen while the vehicle is traveling, and the driver can be concentrated on driving. Patent Document 2 discloses a voice recognition device that is mounted on a vehicle and performs processing according to an operation command input by voice.

JP-A-7-270173 Japanese Patent Laid-Open No. 11-15494

  By the way, during traveling of the vehicle, a passenger other than the driver may want to use the function of the in-vehicle device. Since the passenger is not driving, even if he / she performs an operation that needs to be performed while gazing at the screen, it does not hinder driving. However, conventionally, when the vehicle is running, only predetermined operations are permitted, which is inconvenient for passengers. This was the same when inputting an operation command by voice.

  The present invention has been made in view of the above circumstances, and an object of the present invention is an in-vehicle device that performs processing according to an operation command input by voice, depending on the position in the vehicle where the occupant is sitting, It is to be able to set an operation command to be permitted for a passenger sitting at the position.

  In order to solve the above-described problem, the in-vehicle device of the present invention has a predetermined operation command for each seat position, and is collected via a plurality of microphones when the operation command is input by voice. The voice generation position corresponding to the voice signal is identified from the voice signal, and when the input operation command is an operation command permitted at the generation position, processing corresponding to the operation command is executed.

  For example, the first aspect of the present invention is an in-vehicle device that is mounted on a vehicle and executes processing in response to an operation command input by voice, in association with information indicating a seat area in the vehicle, The permission command storage means for storing the operation command permitted for the person sitting in the seat, the voice recognition start receiving means for receiving an instruction to start the input of the operation command from the user, and the voice recognition start receiving means for inputting the operation command After receiving the start instruction from the user, the sound generation position corresponding to the sound signal is identified from the sound signals collected via each of the plurality of microphones, and the identified position is generated from the position. Sound source position specifying means output together with a sound signal corresponding to the sound, and sound for recognizing an operation command from the sound signal output from the sound source position specifying means And the operation command permitted at the sound generation position corresponding to the sound signal output from the sound source position specifying means is extracted from the permission command storage means, and the operation command recognized by the voice recognition means is extracted. And a command processing unit that executes a process corresponding to the operation command recognized by the voice recognition unit when the operation command is the same as any one of the operation commands.

  The second aspect of the present invention is a speech recognition method in an in-vehicle device that is mounted on a vehicle and executes processing in accordance with an operation command input by voice, wherein the in-vehicle device is a seat area in the vehicle. In correspondence with the information indicating the permission command storage step for storing the operation command permitted for the person sitting on the seat in the permission command storage means, and the instruction for starting the input of the operation command is received from the user. After receiving an operation command input start instruction from the user in the step and the voice recognition start reception step, the voice generation position corresponding to the voice signal is specified from the voice signals collected through each of the plurality of microphones. The sound source position specifying step for outputting the specified generation position together with the audio signal corresponding to the sound generated from the generation position. A voice recognition step for recognizing an operation command from the voice signal output in the sound source position specifying step, and a permission command storage means for the operation command permitted in the sound generation position corresponding to the voice signal output in the sound source position specifying step. A command processing step for executing a process corresponding to the operation command recognized in the voice recognition step when the operation command extracted from the voice recognition step is the same as one of the extracted operation commands. A speech recognition method is provided.

  According to the vehicle-mounted device of the present invention, in the vehicle-mounted device that performs processing according to an operation command input by voice, permission is given to a passenger sitting at the position according to the position in the vehicle where the passenger is sitting. Operation commands to be set can be set.

  First, a first embodiment of the present invention will be described with reference to the drawings.

  FIG. 1 is a system configuration diagram showing the configuration of an in-vehicle system 10 according to the first embodiment of the present invention. The in-vehicle system 10 includes a plurality of microphones 11, a voice recognition start button 12, a display device 13, a sensor 14, and an in-vehicle device 20. The in-vehicle device 20 includes a sound source position specifying unit 21, a start instruction receiving unit 22, a voice recognition unit 23, a command processing unit 24, and a permission command storage unit 25.

  The start instruction receiving unit 22 instructs the sound source position specifying unit 21 to specify the sound generation position corresponding to the sound signal when the voice recognition start button 12 is pressed by the user. When the sound source position specifying unit 21 is instructed to specify the generation position of the audio signal from the start instruction receiving unit 22, the delay amount of the audio signal collected through each of the plurality of microphones 11 provided in the vehicle. Based on the difference in amplitude and the like, the generation position of the sound corresponding to the sound signal is specified. Then, the sound source position specifying unit 21 outputs the specified generation position to the voice recognition unit 23 together with a voice signal corresponding to the voice generated from the generation position.

  In addition, when the signals collected via each of the plurality of microphones 11 include sound signals corresponding to a plurality of sounds generated from different positions, the sound source position specifying unit 21 performs the corresponding process for each occurrence position. A voice signal corresponding to the voice generated from the generation position is output to the voice recognition unit 23 together with information indicating the corresponding generation position. For example, as shown in FIG. 2, the data 40 output from the sound source position specifying unit 21 to the voice recognition unit 23 is associated with the sound source position 41 indicating the sound generation position in the vehicle, from the sound source position 41. An audio signal 42 corresponding to the generated audio is stored.

  In the present embodiment, the sound source position 41 stores coordinates on the xy plane when the horizontal plane at a predetermined height in the vehicle is the xy plane. As another example, the sound source position 41 may store three-dimensional coordinates indicating a position in the vehicle.

  The voice recognition unit 23 recognizes an operation command from each voice signal output from the sound source position specifying unit 21 using a known voice recognition technology, and the recognized operation command is used as the voice that is the basis of the operation command. It outputs to the command processing part 24 with the information which shows the generation | occurrence | production position of the audio | voice corresponding to a signal.

  In the permission command storage unit 25, for example, as shown in FIG. 3, a seat attribute 251 indicated by the seat area 250 in association with a seat area 250 indicating a seat area in the vehicle, a person sitting in the seat A running permission command 252 indicating a plurality of operation commands permitted when the vehicle is traveling, and a stopping permission command 253 indicating a plurality of operation commands permitted to the person sitting in the seat while the vehicle is stopped Stored.

  In the seat area 250, for example, as shown in FIG. 4, the coordinates of the vertices facing each other in the rectangular area surrounding each seat position on the xy plane when the horizontal plane at a predetermined height in the vehicle is the xy plane. Stored. FIG. 4 schematically shows the interior of the vehicle as viewed from above. An area 30 near the handle 15 indicates a driver seat, an area 31 indicates a passenger seat, and an area 32 indicates a rear seat. ing. In the example shown in FIG. 4, the plurality of microphones 11 and the display device 13 are provided near the dashboard.

  When all the operation commands are permitted in the travel permission command 252 or the stop permission command 253, “ALL” indicating that all the operation commands are permitted is stored.

  When the command processing unit 24 receives a voice signal and information indicating the voice generation position corresponding to the voice signal from the voice recognition unit 23, the command processing unit 24 refers to the permission command storage unit 25 and includes the generation position. Identify the seating area. The command processing unit 24 determines whether or not the vehicle is traveling based on a measurement signal received from a sensor 14 such as a GPS (Global Positioning System) receiver, a direction sensor, or a distance sensor.

  When the vehicle is traveling, the command processing unit 24 extracts a plurality of operation commands that are associated with the specified seat area and stored in the traveling permission command 252. On the other hand, when the vehicle is stopped, the command processing unit 24 extracts a plurality of operation commands that are associated with the specified seat area and stored in the stop permission command 253.

  Then, when the operation command received from the voice recognition unit 23 corresponds to one of a plurality of operation commands extracted from the permission command storage unit 25, the command processing unit 24 generates a voice signal that is the source of the operation command. For example, as shown in FIG. 5, the seat area including the voice generation position corresponding to is displayed on the display device 13, and processing corresponding to the operation command received from the voice recognition unit 23 is executed.

  In the example shown in FIG. 5, the command processing unit 24 displays an icon 50 indicating the generation position of the audio signal in the screen of the display device 13. The icon 50 includes an area 51 indicating a passenger seat, an area 52 indicating a driver seat, and an area 53 indicating a rear seat. In the example shown in FIG. 5, it is displayed that processing corresponding to an operation command by voice generated from the driver's seat has been executed.

  As another example, as shown in FIG. 6, an area 55 indicating that a process corresponding to an operation command by voice generated from the passenger seat has been executed along the edge of the screen is generated from the driver's seat. An area 56 for displaying that the process corresponding to the voice operation command has been executed and an area 57 for displaying that the process corresponding to the voice operation command generated from the rear seat has been executed may be displayed. Good.

  When receiving information indicating a plurality of voice signals and voice generation positions corresponding to the respective voice signals from the voice recognition unit 23, the command processing unit 24 is based on the voice generation positions corresponding to the respective voice signals. The permission command storage unit 25 is referred to, and the operation command based on the audio signal corresponding to the audio generated from the driver's seat area is preferentially processed. When there is no operation command by an audio signal corresponding to the voice generated from the driver's seat, the command processing unit 24 executes the operation command with priority in the order of the passenger seat and the rear seat, for example.

  FIG. 7 is a flowchart illustrating an example of the operation of the in-vehicle device 20. For example, the vehicle-mounted device 20 starts the operation shown in this flowchart at a predetermined timing such as when the vehicle engine is started.

  First, the start instruction receiving unit 22 determines whether or not the voice recognition start button 12 is desired to be pressed (S100). When the voice recognition start button 12 is not pressed (S100: No), the start instruction receiving unit 22 repeats the process shown in step S100 until the voice recognition start button 12 is pressed.

  When the voice recognition start button 12 is pressed (S100: Yes), the start instruction receiving unit 22 instructs the sound source position specifying unit 21 to specify the sound generation position corresponding to the sound signal. The sound source position specifying unit 21 determines the sound generation position corresponding to the sound signal based on the delay amount or difference in amplitude of the sound signal collected via each of the plurality of microphones 11 provided in the vehicle. The specified generation position is output to the voice recognition unit 23 together with a voice signal corresponding to the voice generated from the generation position.

  Next, the voice recognition unit 23 recognizes an operation command from each voice signal output from the sound source position specifying unit 21 using a known voice recognition technique (S102), and the recognized operation command is converted into the operation command. Are output to the command processing unit 24 together with information indicating the sound generation position corresponding to the sound signal that is the source of the above.

  Next, the command processing unit 24 refers to the operation command output from the voice recognition unit 23 and determines whether or not a plurality of operation commands have been recognized (S103). When a plurality of operation commands are recognized (S103: Yes), the command processing unit 24 refers to the permission command storage unit 25 based on the voice generation position output from the voice recognition unit 23 together with the operation command, and the driver's seat An operation command based on an audio signal corresponding to the audio generated from the area is preferentially processed (S104).

  Next, the command processing unit 24 displays the seat position including the sound generation position corresponding to the processed operation command on the display device 13 (S105), and the start instruction receiving unit 22 performs the process shown in step S100. Execute.

  When a single operation command is recognized in step S103 (S103: No), the command processing unit 24 executes a process corresponding to the recognized operation command (S106), and performs the process shown in step S105. Execute.

  The first embodiment of the present invention has been described above.

  As is clear from the above description, according to the in-vehicle system 10 of the present embodiment, in the in-vehicle device 20 that performs processing according to the operation command input by voice, according to the position in the vehicle where the occupant is sitting, It is possible to set an operation command to be permitted for a passenger sitting at the position.

  Next, a second embodiment of the present invention will be described.

  FIG. 8 is a system configuration diagram showing the configuration of the in-vehicle system 10 according to the second embodiment of the present invention. The in-vehicle system 10 includes a plurality of microphones 11, a voice recognition start button 12, a plurality of display devices 13, a sensor 14, and an in-vehicle device 20. The in-vehicle device 20 includes a sound source position specifying unit 21, a start instruction receiving unit 22, a voice recognition unit 23, a command processing unit 24, and a permission command storage unit 25. Except for the points described below, in FIG. 8, the components denoted by the same reference numerals as those in FIG. 1 have the same or similar functions as those in FIG.

  Each display device 13 is provided at a different position in the vehicle, for example, as shown in FIG. The display device 13-1 is provided in front of the driver's seat, for example, and displays a screen to be shown to a person sitting in the driver's seat. The display device 13-2 is provided in front of the passenger seat, for example, and displays a screen to be shown to a person sitting in the passenger seat. The display device 13-3 is, for example, a roof monitor provided in front of the rear seat, and displays a screen to be shown to a person sitting on the rear seat.

  In the permission command storage unit 25, for example, as shown in FIG. 10, it is generated from the seat indicated by the attribute 251, the permission command 252 during travel, the permission command 253 during stop, and the seat region 250 in association with the seat region 250. The display device ID 254 for identifying the display device 13 that reflects the processing result of the operation command corresponding to the sound signal of the sound is stored in advance.

  When the command processing unit 24 receives a voice signal and information indicating the voice generation position corresponding to the voice signal from the voice recognition unit 23, the command processing unit 24 refers to the permission command storage unit 25 and includes the generation position. Identify the seating area. Then, the command processing unit 24 determines whether or not the vehicle is traveling based on the measurement signal received from the microphone 11.

  When the vehicle is traveling, the command processing unit 24 extracts a plurality of operation commands that are associated with the specified seat area and stored in the traveling permission command 252. On the other hand, when the vehicle is stopped, the command processing unit 24 extracts a plurality of operation commands that are associated with the specified seat area and stored in the stop permission command 253.

  Then, when the operation command received from the voice recognition unit 23 corresponds to one of a plurality of operation commands extracted from the permission command storage unit 25, the command processing unit 24 executes processing corresponding to the operation command. . Then, the command processing unit 24 refers to the permission command storage unit 25 and displays the display device ID associated with the seat region 250 including the sound generation position corresponding to the sound signal that is the source of the operation command. Is identified. Then, the command processing unit 24 reflects the execution result on the display device 13 corresponding to the specified display device ID.

  The second embodiment of the present invention has been described above.

  Also in the in-vehicle system 10 of the present embodiment, in the in-vehicle device 20 that performs processing in accordance with an operation command input by voice, depending on the position in the vehicle where the occupant is sitting, the occupant sitting at the position Operation commands allowed. Furthermore, the processing based on the operation command can be reflected on the display device 13 viewed by the person sitting at the position where the sound that is the source of the operation command is emitted.

  The in-vehicle device 20 in the first or second embodiment is realized by a computer 60 configured as shown in FIG. 11, for example. FIG. 11 is a hardware configuration diagram illustrating an example of a hardware configuration of the computer 60 that realizes the functions of the in-vehicle device 20. The computer 60 includes a CPU (Central Processing Unit) 61, a RAM (Random Access Memory) 62, a ROM (Read Only Memory) 63, an HDD (Hard Disk Drive) 64, an input interface (I / F) 65, an output interface (I / F). F) 66 and a media interface (I / F) 67.

  The CPU 61 operates based on a program stored in the ROM 63 or the HDD 64 and controls each unit. The ROM 63 stores a boot program executed by the CPU 61 when the computer 60 is started up, a program depending on the hardware of the computer 60, and the like. The HDD 64 stores a program executed by the CPU 61.

  The input interface 65 receives a signal from the microphone 11, the voice recognition start button 12, or the sensor 14 and sends it to the CPU 61. The CPU 61 controls the microphone 11, the voice recognition start button 12, and the sensor 14 through the input interface 65, and acquires a signal from the microphone 11, the voice recognition start button 12, or the sensor 14 through the input interface 65. . The output interface 66 sends the data acquired from the CPU 61 to the display device 13. The CPU 61 controls the display device 13 via the output interface 66 and outputs the generated data to the display device 13 via the output interface 66.

  The media interface 67 reads a program or data stored in the recording medium 68 and provides it to the RAM 62. A program provided to the CPU 61 via the RAM 62 is stored in the recording medium 68. The program is read from the recording medium 68, installed in the computer 60 via the RAM 62, and executed by the CPU 61. The recording medium 68 is, for example, an optical recording medium such as a DVD (Digital Versatile Disk) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  A program installed and executed on the computer 60 causes the computer 60 to function as the sound source position specifying unit 21, the start instruction receiving unit 22, the voice recognition unit 23, the command processing unit 24, and the permission command storage unit 25. The computer 60 reads these programs from the recording medium 68 and executes them. However, as another example, the computer 60 may be provided with a communication function to acquire these programs via a communication line.

  The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the gist.

  For example, in the second embodiment described above, the in-vehicle system 10 includes a plurality of display devices 13 corresponding to the plurality of seats, but as another form, the in-vehicle system 10 corresponds to each of the plurality of seats. One display device 13 that displays a screen to be displayed may be provided. In this case, the command processing unit 24 reflects the execution result of the process corresponding to the operation command on the screen for the seat area 250 including the generation position of the audio signal corresponding to the operation command.

  As the display device 13 for displaying the corresponding screen of each of the plurality of seats, for example, a slit is provided on the front surface of the panel, and images for the driver's seat and passenger's side are alternately arranged in the horizontal direction, A dual display which is a liquid crystal display capable of displaying different images on the driver's seat side and the passenger's seat side by separating the light of the backlight left and right with the slit is preferable.

It is a system configuration figure showing the composition of in-vehicle system 10 concerning a first embodiment of the present invention. It is a figure which shows an example of the structure of the data 40 output from the sound source position specific | specification part. It is a figure which shows an example of the structure of the data stored in the permission command storage part 25 in 1st embodiment. It is a conceptual diagram for demonstrating a seat area | region. 4 is a conceptual diagram illustrating an example of a screen displayed on the display device 13. FIG. 12 is a conceptual diagram illustrating another example of a screen displayed on the display device 13. FIG. 4 is a flowchart showing an example of the operation of the in-vehicle device 20. It is a system configuration figure showing the composition of in-vehicle system 10 concerning a second embodiment of the present invention. It is a conceptual diagram for demonstrating arrangement | positioning of the display apparatus 13 in 2nd embodiment. It is a figure which shows an example of the structure of the data stored in the permission command storage part 25 in 2nd embodiment. It is a hardware block diagram which shows an example of a structure of the computer 50 which implement | achieves the function of the vehicle equipment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... In-vehicle system, 11 ... Microphone, 12 ... Voice recognition start button, 13 ... Display device, 14 ... Sensor, 15 ... Handle, 20 ... In-vehicle device, 21. .. Sound source position specifying unit, 22... Start instruction receiving unit, 23... Voice recognition unit, 24... Command processing unit, 25.・ Area 32 ... Area 40 ... Data 41 ... Sound source position 42 ... Audio signal 50 ... Icon 51 ... Area 52 ... Area 53 ... -Area, 55 ... Area, 56 ... Area, 57 ... Area, 60 ... Computer, 61 ... CPU, 62 ... RAM, 63 ... ROM, 64 ... HDD 65 ... Input interface 66 ... Output interface , 67 ... media interface, 68 ... recording medium

Claims (7)

An in-vehicle device that is mounted on a vehicle and executes processing according to an operation command input by voice,
A permission command storage means for storing an operation command to be permitted for a person sitting on the seat in association with information indicating a seat area in the vehicle;
Voice recognition start accepting means for accepting an operation command input start instruction from the user;
After the voice recognition start accepting means accepts an instruction to start inputting an operation command from the user, the voice generation position corresponding to the voice signal is identified from the voice signals collected through each of the plurality of microphones, and identified. Sound source position specifying means for outputting the generated position together with an audio signal corresponding to the sound generated from the generated position;
Voice recognition means for recognizing an operation command from the voice signal output from the sound source position specifying means;
The operation command permitted at the sound generation position corresponding to the sound signal output from the sound source position specifying means is extracted from the permission command storage means, and the operation command recognized by the sound recognition means is extracted. An in-vehicle device comprising: a command processing unit that executes a process corresponding to the operation command recognized by the voice recognition unit when the operation command is the same as one of the operation commands. The in-vehicle device according to claim 1,
In the permission command storage means,
Information indicating the area of the driver's seat is included as information indicating the area of the seat in the vehicle. The information indicating the area of the driver's seat includes an operation command that is permitted while the vehicle is traveling, and the vehicle is stopped. Are associated with permitted operation commands,
The command processing means includes
If the sound generation position corresponding to the sound signal output from the sound source position specifying means is included in the area of the driver's seat, if the vehicle is running, the operation commands permitted while the vehicle is running are An on-vehicle apparatus characterized in that if the vehicle is stopped and extracted from the permission command storage means, an operation command permitted while the vehicle is stopped is extracted from the permission command storage means. The in-vehicle device according to claim 1 or 2,
The command processing means includes
An in-vehicle device characterized in that information indicating a sound generation position corresponding to an operation command to be processed is displayed on a display device. The in-vehicle device according to any one of claims 1 to 3,
The sound source position specifying means includes
After the voice recognition start receiving means receives an instruction to start inputting an operation command from the user, the voice corresponding to each voice signal is obtained from the mixed signal including a plurality of voice signals collected through each of the plurality of microphones. For each occurrence position, the sound signal of the sound generated from the position is separated, and the separated sound signal is output together with information indicating the sound generation position corresponding to the sound signal,
The voice recognition means
When a plurality of audio signals are output from the sound source position specifying means, an operation command is recognized for each audio signal, and the recognized operation command is combined with information indicating the generation position of the sound that is the basis of the operation command. Output,
The command processing means includes
An in-vehicle apparatus that preferentially processes an operation command by voice generated from a driver's seat area when a plurality of operation commands are recognized by the voice recognition means. The in-vehicle device according to any one of claims 1 to 3,
The sound source position specifying means includes
After the voice recognition start receiving means receives an instruction to start inputting an operation command from the user, the voice corresponding to each voice signal is obtained from the mixed signal including a plurality of voice signals collected through each of the plurality of microphones. For each occurrence position, the sound signal of the sound generated from the position is separated, and the separated sound signal is output together with information indicating the sound generation position corresponding to the sound signal,
The voice recognition means
When a plurality of audio signals are output from the sound source position specifying means, an operation command is recognized for each audio signal, and the recognized operation command is combined with information indicating the generation position of the sound that is the basis of the operation command. Output,
The command processing means includes
When a plurality of operation commands are recognized by the voice recognition unit, for each operation command, an operation command that is permitted at a voice generation position that is a source of the operation command is extracted from the permission command storage unit, If the operation command by voice generated from the generation position and recognized by the voice recognition means is the same as any one of the extracted operation commands, the processing result corresponding to the operation command is An on-vehicle device characterized by displaying on a display device corresponding to an area of a seat including a sound generation position corresponding to the operation command among display devices provided for each. The in-vehicle device according to any one of claims 1 to 3,
The sound source position specifying means includes
After the voice recognition start receiving means receives an instruction to start inputting an operation command from the user, the voice corresponding to each voice signal is obtained from the mixed signal including a plurality of voice signals collected through each of the plurality of microphones. For each occurrence position, the sound signal of the sound generated from the position is separated, and the separated sound signal is output together with information indicating the position where the sound signal is generated,
The voice recognition means
When a plurality of audio signals are output from the sound source position specifying means, an operation command is recognized for each audio signal, and the recognized operation command is combined with information indicating the generation position of the sound that is the basis of the operation command. Output,
The command processing means includes
When a plurality of operation commands are recognized by the voice recognition unit, for each operation command, an operation command that is permitted at a voice generation position that is a source of the operation command is extracted from the permission command storage unit, If the operation command by voice generated from the generation position and recognized by the voice recognition means is the same as any one of the extracted operation commands, the processing result corresponding to the operation command is An in-vehicle device, wherein a display device capable of different display is reflected in a display corresponding to a seat area including a sound generation position corresponding to the operation command. A voice recognition method in an in-vehicle device that is mounted on a vehicle and executes processing according to an operation command input by voice,
The in-vehicle device is
A permission command storage step of storing, in the permission command storage means, an operation command to be permitted to a person sitting on the seat in association with information indicating a seat area in the vehicle;
A voice recognition start acceptance step for accepting an operation command input start instruction from a user;
After receiving an instruction to start inputting an operation command from the user in the voice recognition start receiving step, the voice generation position corresponding to the voice signal is specified from the voice signals collected through each of the plurality of microphones, and specified. A sound source position specifying step for outputting the generated position together with an audio signal corresponding to the sound generated from the generated position;
A voice recognition step of recognizing an operation command from the voice signal output in the sound source position specifying step;
The operation command permitted at the sound generation position corresponding to the sound signal output in the sound source position specifying step is extracted from the permission command storage means, and the operation command recognized in the sound recognition step is the extracted operation command. And a command processing step of executing a process corresponding to the operation command recognized in the voice recognition step.

Images