JP2019101367A - Voice manipulation system - Google Patents

Abstract

To provide a voice operation system capable of accurately and safely operating a plurality of devices included in a stage mechanism, a studio mechanism, or a game mechanism.SOLUTION: A voice type operation device 10 receives an operation instruction by voice from an operator. A voice recognition device 40 converts an operation instruction by voice from the voice type operation device 10 into command data. A stage mechanism control device 50 receives command data converted by the voice recognition device 40 and status information indicating the state of the plurality of devices, and generates character information representing command data and status information. An audio output device 20 outputs a sound based on the character information generated by the stage mechanism control device 50. A mechanical operation device 30 receives a manual operation instruction from the operator. The stage mechanism control device 50 controls the plurality of devices in accordance with the manual operation instruction input to the mechanical operation device 30 and the command data.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a voice operation system for operating a plurality of devices included in a stage mechanism, a studio mechanism or a play mechanism by voice.

  An operating device for operating a plurality of stage devices included in a stage mechanism is disclosed, for example, in Japanese Patent Laid-Open No. 2016-118814 (Patent Document 1). The operation device described in Patent Document 1 is configured by connecting a touch screen and a console, and is usually provided in an operation room or the like apart from the site near the stage where the stage device is present.

  An operator who operates the above-mentioned operation device receives an instruction for operating each stage device from the conductor by performing voice communication with a conductor who instructs the stage mechanism on the site. The operator operates the stage device designated by the conductor by performing an input operation on the operation device based on the instruction.

JP, 2016-118814, A

  However, in the operation procedure described above, there may be a case where the operator of the operating device operates the operating instruction incorrectly due to the surrounding environment or the like. In this case, the stage device to be operated performs an operation different from the operation instruction.

  Alternatively, even if there is an error in the conductor's operation instruction itself, there may be a case where the stage device is operated without the operator being aware of the error. In any case, if the stage device to be operated performs an undesirable operation, it may cause interference with other stage devices. As a result, the safety of the stage mechanism may be impaired.

  In addition, in order for the conductor to confirm that the operation instruction is correctly transmitted to the operator, it is necessary to rely on the voice exchange with the operator, so the confirmation operation takes time and operation efficiently. Problem of not being able to

  The present invention has been made to solve such problems, and its object is to accurately and safely operate a plurality of devices included in a stage mechanism, a studio mechanism or a play mechanism. It is providing a voice operation system.

  According to one aspect of the present invention, a voice operation system for operating a plurality of devices included in a stage mechanism, a studio mechanism or a play mechanism by voice includes a first operation device, a voice recognition device, and a control device. , An audio output device, and a second operating device. The first operation device is configured to receive an operation instruction by voice from the operator. The voice recognition device is configured to convert an operation instruction by voice input to the first operation device into command data. The control device is configured to receive command data converted by the voice recognition device and status information indicating states of a plurality of devices, and generate character data representing the command data and the status information. The audio output device is configured to output an audio based on the character information generated by the control device.

  According to the voice operation system, when the voice instruction registered in the voice recognition device is converted into command data and transmitted to the control device, the control device reversely converts it into character information, and the voice based on the character information is It is output from the audio output device. The voice instruction given by the operator is fed back to the operator as a voice based on the character information, so that the operator can correctly register the voice instruction issued by him / her based on the feedback voice. You can check if it is Further, since the voice based on the character information includes the status information, the operator can confirm by the voice whether or not the device to be operated can safely be operated according to the voice instruction.

  Preferably, the voice operation system further includes a second operation device configured to receive a manual operation instruction from the operator. The control device is configured to control each of the plurality of devices in accordance with a manual operation instruction and command data input to the second operation device.

  With this configuration, the operation of the device to be operated is triggered by the manual instruction by the operator, so the voice instruction is correctly registered, and the safe operation of the stage device to be operated is guaranteed. In the above state, the device to be operated can be operated. Thereby, safe and accurate operation of the device to be operated can be realized.

  Preferably, the second operating device includes a mechanical operating unit, and is configured to receive a manual operation instruction to the operating unit.

  According to this configuration, the manual operation by the operator can be used as a trigger of the operation of the device to be operated. Therefore, it is possible to operate the device to be operated in a state where the voice instruction is correctly registered and the safe operation of the stage device to be operated is guaranteed.

  Preferably, when the command data is a stop instruction, the control device stops the plurality of devices according to the command data without waiting for a manual operation instruction. With this configuration, it is possible to quickly stop all the plurality of devices in a situation where an abnormality such as failure of any of the plurality of devices has occurred.

  Preferably, the first operation device is further configured to receive an execution instruction by voice from the operator. The voice recognition device is further configured to convert an execution command input to the first operating device into a command for the control device. The control device is configured to control each of the plurality of devices according to the command data when receiving the command representing the execution command.

  According to this configuration, the operation of the device to be operated is executed using the execution instruction of the operator's voice as a trigger, so the voice instruction is correctly registered and the safe operation of the stage device to be operated The device to be operated can be operated in a state in which Thereby, safe and accurate operation of the device to be operated can be realized.

  Preferably, when the command data is a stop instruction, the control device stops the plurality of devices according to the command data without waiting for input of a command representing the execution instruction. With this configuration, it is possible to quickly stop all the plurality of devices in a situation where an abnormality such as failure of any of the plurality of devices has occurred.

  Preferably, the operation instruction by voice includes identification information for identifying a device to be operated, and operation information indicating an operation content of the device to be operated. The speech recognition device is configured to convert the identification information and the operation information into command data represented by a command code executable by the control device.

  According to this configuration, the control device can control the device to be operated based on the identification information and the operation information by receiving the command data. Further, the control device can generate character information representing identification information and operation information based on the command data.

  Preferably, the character information includes identification information for identifying a device to be operated, operation information indicating an operation content of the device to be operated, and status information of the device to be operated.

  With this configuration, the operator safely operates the device to be operated in accordance with the voice instruction as to whether or not the voice instruction issued by the operator is correctly registered based on the voice based on the character information. You can check if you can.

  Preferably, at least one of the first operating device, the audio output device, and the second operating device is configured to be portable or attachable to an operator. With this configuration, the convenience of the operator can be improved.

  Preferably, a plurality of first operating devices are provided corresponding to a plurality of operators. The voice operation system further comprises a voice transmission device. The voice transmission device is configured to receive an operation instruction by voice input to each of the plurality of first operation devices and transmit the operation instruction to the voice recognition device.

  With such a configuration, since it is possible to use an existing voice transmission device used for voice communication between a plurality of operators, it becomes possible to share one voice recognition device with a plurality of voice type operation devices. . Therefore, the voice operation system can be built at low cost.

  Preferably, a plurality of second operating devices are provided corresponding to a plurality of operators. Each of the plurality of second operating devices is configured to enable input operation of an operation instruction by voice to the first operating device.

  With such a configuration, it is possible to easily separate voice communication and voice instruction in a configuration that uses an existing voice transmission device used for voice communication between a plurality of operators. Thereby, high recognition accuracy can be maintained in the speech recognition apparatus.

  According to the present invention, it is possible to provide a voice operation system capable of accurately and safely operating a plurality of devices included in a stage mechanism or a play mechanism.

FIG. 1 is a schematic configuration diagram of a voice operation system according to an embodiment of the present invention. It is a figure which shows an example of the audio | voice-operated operating device shown in FIG. It is a figure for demonstrating the flow of the data between an operator, an audio operation system, and a stage mechanism. It is a figure explaining one mode of code conversion in a speech recognition device. It is a figure explaining the example of code conversion in a speech recognition device. It is a figure for demonstrating the flow of the data between an operator, an audio operation system, and a stage mechanism. It is a flowchart for demonstrating the operation | movement of the voice operating system according to this Embodiment. It is a figure explaining the 1st example of composition of speech recognition which can be applied to a speech operation system. It is a figure explaining the 2nd example of composition of speech recognition which can be applied to a speech operation system. It is a figure explaining the 3rd example of composition of speech recognition which can be applied to a speech operation system.

  Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings have the same reference characters allotted and description thereof will not be repeated.

[Configuration of voice operation system]
FIG. 1 is a schematic block diagram of a voice operation system according to an embodiment of the present invention. Voice operation system 100 according to the present embodiment can typically be applied to an operation system for operating a plurality of stage devices 60_1 to 60 — n (n is an integer of 2 or more) included in the stage mechanism. Voice operation system 100 according to the present embodiment is also applicable to an operation system for operating a plurality of devices included in the studio mechanism and a plurality of play devices included in the game mechanism.

  Referring to FIG. 1, stage devices 60_1 to 60 — n are devices installed on the stage of large-scale facilities such as studios, theaters, halls, and banquet halls. The stage device includes a hanging mechanism that raises and lowers large tools, lighting fixtures, screen equipment, screens and acoustic reflectors, etc. suspended from the upper part of the stage for presentation effects and storage, and unloading and presentation of large tools The floor mechanism that moves the stage floor to get the above effect is included. The voice operation system 100 is used to produce a stage by centrally controlling the plurality of stage devices 60_1 to 60 — n.

  The voice operation system 100 is a system for operating each of the plurality of stage devices 60_1 to 60 — n with voice. The voice operation system 100 includes a voice operation device 10, a voice output device 20, a mechanical operation device 30, a voice recognition device 40, and a stage mechanism control device 50.

  The voice operation device 10, the voice output device 20, and the mechanical operation device 30 are installed at the site near the stage where the stage device is present. The voice recognition device 40 and the stage mechanism control device 50 are installed in a site near the stage or in an operation room away from the site. At least the voice operation device 10, the voice output device 20 and the mechanical operation device 30 are provided so that they can be used by an operator who operates the stage mechanism on the site.

  The stage mechanism control device 50 transmits and receives data to and from each of the voice recognition device 40, the voice output device 20 and the mechanical operation device 30. The communication method may be, for example, wireless communication by Bluetooth (registered trademark), wireless LAN (Local Area Network), or the like, or wired communication using a USB (Universal Serial Bus) bus or the like.

  An operating device 70 can be further connected to the stage mechanism control device 50. As shown in FIG. 1, the operating device 70 includes an operating unit operable by the operator, and can be configured, for example, by a general-purpose operating device generally referred to as a console. The operating device 70 is installed in a field or an operating room away from the field, and can be operated by an operator different from the operator who uses the voice operating system 100. The stage mechanism control device 50 controls the plurality of stage devices 60_1 to 60 — n by voice input to the voice operation system 100 or input operation to the operation device 70 as described later.

  The voice operation device 10 is used to register an operation instruction by voice from the operator (hereinafter also referred to as “voice instruction”) in the voice recognition device 40. Specifically, the voice operation device 10 includes a microphone as a voice input device, and converts voice acquired by the microphone into voice data. The voice instruction converted into voice data is transmitted to the voice recognition device 40.

  The voice output device 20 is configured to output a voice based on character information. The voice output device 20 outputs voice based on the character information based on an instruction from the stage mechanism control device 50.

  The mechanical operation device 30 is configured to receive a manual operation instruction from the operator (hereinafter also referred to as “manual instruction”). Specifically, the mechanical operating device 30 includes an operating unit that can be operated by the operator. The operation unit is configured by a mechanical operation button. As the mechanical operation button, for example, a push button type switch which can be pressed by the operator OP, a lever switch, a stick controller, a jog dial, a rotary encoder or the like can be used. The mechanical operation buttons include an operation button corresponding to an operation command for the stage device to be operated to operate, and an operation button corresponding to the stop command for stopping the operation of the stage device to be operated. At least including.

  In the present embodiment, the voice-type operating device 10 corresponds to an example of the “first operating device”, and the mechanical operating device 30 corresponds to an example of the “second operating device”. 70 corresponds to an example of the “third operating device”.

  FIG. 2 is a view showing an example of the voice operation device 10, the voice output device 20 and the mechanical control device 30. As shown in FIG. Referring to FIG. 2, each of voice operating device 10, voice output device 20 and mechanical operating device 30 is configured to be carried or worn by operator OP.

  The audio operating device 10 and the audio output device 20 are, for example, a headset (headphone with a microphone). Specifically, the microphone portion of the headset constitutes the audio control device 10, and the headphone portion of the headset constitutes the audio output device 20.

  The audio output device 20 may be an earphone, a bone conduction acoustic device, or a speaker. In the example of FIG. 2, the voice type operation device 10 and the voice output device 20 are integrated so that the operator OP can be worn, but the voice type operation device 10 and the voice output device 20 are separately provided. May be attached to the operator OP. Alternatively, each of the voice operation device 10 and the voice output device 20 may be a terminal that can be carried by the operator OP, or may be fixed at the site.

  The mechanical operating device 30 may be a terminal that can be carried by the operator OP as shown in FIG. 2 or may be fixed at the site. In addition, at least two of the audio operating device 10, the audio output device 20, and the mechanical operating device 30 may be integrated.

  Returning to FIG. 1, the voice recognition device 40 stores (registers) voice data input from the voice operation device 10 as a voice instruction in a memory in the device. The voice recognition device 40 is configured to convert the registered voice instruction into command data. The generated command data includes a command code that can be executed by the stage mechanism control device 50. The detailed configuration of the command data will be described later.

  The stage mechanism control device 50 is configured to be able to communicate with the plurality of stage devices 60_1 to 60 — n. The communication method can be wired or wireless communication. In the present embodiment, although the case where the stage mechanism control device 50 directly communicates with each stage device will be described, it may be a method of communicating with each stage device via a network.

  The stage mechanism control device 50 is mainly configured by a microcomputer including, as an example, a central processing unit (CPU) and a memory such as a read only memory (ROM) and a random access memory (RAM). The stage mechanism control device 50 centrally controls the plurality of stage devices 60_1 to 60 — n by the CPU executing a program stored in the memory.

  Specifically, the stage mechanism control device 50 receives command data from the speech recognition device 40. As described above, the command data represents the voice instruction registered in the voice recognition device 40. In addition, the stage mechanism control device 50 receives a manual instruction from the mechanical operation device 30.

  The stage mechanism control device 50 is a control command for controlling the operation of each of the plurality of stage devices 60_1 to 60 — n based on the voice instruction registered in the voice recognition device 40 and the manual instruction from the mechanical operation device 30. Generate The stage mechanism control device 50 transmits the generated control command to the corresponding stage device. Each of the stage devices 60_1 to 60 — n includes a control unit (not shown). When receiving the control command from the stage mechanism control device 50, the control unit of each stage device controls the operation of each part of the stage device according to the control command.

  Each of the stage devices 60_1 to 60 — n periodically transmits information indicating the state of the own device (hereinafter, also referred to as “status information”) to the stage mechanism control device 50. The status information is the operation state of the own device, for example, information indicating whether the device is currently operating or stopped, information indicating the current position of the device itself, whether the device is normal or has an error occurred Contains information indicating Each stage device may transmit status information to the stage mechanism control device 50 together with identification information (device name or device number) for identifying the own device.

[Operation of voice operation system]
Next, the operation of voice operation system 100 according to the present embodiment will be described.

  FIG. 3 is a diagram for explaining the flow of data among the operator, the voice operation system 100 and the stage mechanism.

  Referring to FIG. 3, first, the operator inputs a voice instruction to voice-type operation device 10 (OP1 in the figure). When the voice operation device 10 receives a voice instruction from the operator, the voice operation device 10 transmits voice data indicating the voice instruction to the voice recognition device 40.

  When the voice recognition device 40 receives a voice instruction (voice data) from the voice operation device 10, the voice recognition device 40 registers the received voice instruction. The voice recognition device 40 converts voice instructions, which are voice data, into command data. Specifically, the voice instruction from the operator includes identification information of the stage device in order to specify the stage device to be operated. The voice instruction further includes operation information indicating the operation content of the stage device to be operated. The voice recognition device 40 converts the identification information and the operation information into a command code that can be executed by the stage mechanism control device 50.

FIG. 4 is a view for explaining one mode of code conversion in the speech recognition device 40. As shown in FIG.
Referring to FIG. 4, speech recognition device 40 stores a plurality of command codes. Each of the plurality of command codes is associated with identification information or operation information.

  In the example of FIG. 4, the plurality of command codes are a code (for example, code 001 to 100) associated with the apparatus name of the stage apparatus and a code (for example, code 101 to 200) associated with the operation amount of the stage apparatus And a code (e.g., codes 201 to 300) associated with the motion direction of the stage apparatus.

  The device name of the stage device includes, for example, names of large tools, lighting fixtures, screen equipment, names of a screen and acoustic reflector, or hanging mechanisms for raising and lowering them, names of floor mechanisms, and the like. A command code can be assigned to each of the stage devices. Alternatively, when a plurality of stage devices are grouped into one group, two or more stage devices for which collective operation is required can be assigned a command code for each group.

  The amount of movement of the stage apparatus includes, for example, the movement distance and rotation angle of the stage apparatus. For example, for each of the movement distance and the rotation angle, the tolerance range can be subdivided, and a code can be assigned to each subdivided range. Further, the amount of movement of the stage apparatus includes, for example, the height position from the floor of the stage and the target position of the stage apparatus. A code can be assigned to each target position.

  The operation direction of the stage apparatus includes, for example, the vertical direction, the longitudinal direction, the horizontal direction, the rotation direction, and the like. A code can be assigned to each of these directions.

  The voice recognition device 40 stores a table as shown in FIG. 4 that indicates the correspondence between identification information and operation information and a plurality of command codes. When the voice recognition device 40 receives a voice command from the voice operation device 10, the voice recognition device 40 converts the voice command into a code with reference to the table.

  Here, for example, as shown in FIG. 5, it is assumed that the voice instruction from the operator is “rise to 22 m above the floor”. This voice instruction includes “緞” (device name), which is identification information of the operation target, “22 m on the floor” (target position), which is the movement amount of the operation target, and “rise” which is the operation direction of the operation target. It consists of three words. In this case, the speech recognition device 40 converts each of the three words into a command code with reference to the table. Then, the speech recognition device 40 generates command data by combining the converted command codes.

  In the example of FIG. 5, the word "緞" is converted to the command code "001", the word "on the floor 22m" is converted to the command code "122", and the word "rising" is converted to the command code "210". Be done. Therefore, the voice instruction "to raise the grid to 22 m above the floor" is converted into command data including the command code "001, 122, 210".

  In order to ensure the accuracy of the code conversion process in the speech recognition device 40, the syntax (word order) of the speech instruction can be determined in advance. For example, as shown in FIG. 5, the identification information, the operation information (operation amount), and the operation information (operation direction) can be ordered.

  Alternatively, at the beginning of the audio instruction, an instruction to start code conversion can be included. For example, when the speech recognition device 40 receives a speech instruction "instruction", it may start code conversion processing, and convert the speech instruction input following the "instruction" into a command code.

  Returning to FIG. 3, when receiving the command data from the speech recognition device 40, the stage mechanism control device 50 generates character information representing the received command data. Specifically, the stage mechanism control device 50 inversely converts the received command data into character information by referring to the table of FIG. 4. For example, when the command data (code "001, 122, 210") shown in FIG. 5 is received, the stage mechanism control device 50 determines from the command data the three words "緞", "on floor 22m" and "rise". Is extracted and character information including the extracted three words is generated.

  Further, when the stage mechanism control device 50 acquires status information from each of the plurality of stage devices 60_1 to 60 — n, the status information of the stage device to be operated is extracted from the acquired status information. At this time, status information of the stage device linked to the stage device to be operated can be extracted together. The stage device linked to the stage device to be operated is, for example, a stage device or the like in which movable ranges overlap with the stage device to be operated.

  The stage mechanism control device 50 converts the extracted status information into character information. The stage mechanism control device 50 transmits the generated character information to the voice output device 20.

  The voice output device 20 outputs voice based on the character information generated by the stage mechanism control device 50. Since the voice based on the character information is issued in response to the voice instruction, in the following description, the voice based on the character information is also referred to as "response voice". The response voice includes, for example, a total of seven items of “device name”, “attribute name”, “speed”, “target position”, “current position”, “operation direction” and “status”.

  The “apparatus name” includes the name of the stage apparatus to be operated. It may be an apparatus number assigned to the stage apparatus. The “attribute name” includes information specifying a group to which the stage device to be operated belongs.

  The "speed" includes a target speed at which the stage device to be operated should operate. The “target position” includes the target position of the stage device to be operated. The “current position” includes the current position of the stage device to be operated.

  The "status" includes status information of the stage device to be operated. For example, information indicating whether the stage device to be operated is currently operating or stopped, information indicating whether the stage device is normal, or whether an abnormality has occurred, are included. The “status” may also include status information of the stage device linked to the stage device to be operated.

  Thus, from the voice output device 20, the content of the voice instruction registered based on the voice input OP1 of the operator and the status information of the stage device to be operated specified by the voice instruction become the response voice. Output. By listening to the response voice, the operator confirms whether or not his / her voice input OP1 matches the registered voice instruction, that is, whether or not his / her voice instruction is correctly registered. Can be done (OP2 in FIG. 3).

  In addition, the operator can grasp the current state of the stage device to be operated by listening to the response voice, and thus, confirms whether or not the stage device can be operated according to the voice instruction. Can be done (OP2 in FIG. 3).

  For example, when the operator misunderstands the current position of the stage device to be operated, if the stage device is operated according to the voice instruction, the stage device moves to a position different from the operator's intention, and the operation is not performed. May affect the stage equipment of the Alternatively, when the stage device to be operated is operating according to a voice instruction from another operator, there is a possibility that another operator's voice instruction and his own voice instruction may be batted. The operator can foresee the possibility of these problems occurring by grasping the current state of the stage device to be operated from the response voice.

  Returning to FIG. 3, when it is confirmed that the voice instruction is correctly registered and that the stage device to be operated can be operated according to the voice instruction (OP2 in the figure), the operator operates the mechanical type An input operation is performed on the operation unit of the operation device 30 (OP3 in the figure). The operator performs an input operation to the operation button corresponding to the operation command for performing operation of the stage device to be operated among the plurality of mechanical operation buttons included in the operation unit.

  When an input operation is performed on the operation button, the mechanical operation device 30 generates an operation command and outputs the operation command to the stage mechanism control device 50. The stage mechanism control device 50 generates a control command (electric signal) for controlling the stage device to be operated based on the operation command from the mechanical operation device 30. The stage mechanism control device 50 outputs the generated control command to the stage device to be operated. As a result, the stage device to be operated operates in accordance with the voice instruction.

  In addition, when it is desired to stop the stage device against the voice instruction during operation of the stage device to be operated, the operator performs an input operation on the operation button corresponding to the stop command by the mechanical operation device 30. Can do.

  On the other hand, if it is confirmed that the voice instruction is incorrectly registered, such as an error or omission in the registered content, or the voice instruction is correctly registered, but the operation target is the same as the voice instruction. When it is confirmed that the stage device can not be operated, the operator can input the voice instruction to the voice operation device 10 again (OP1 in the figure). Then, as to the newly input voice instruction, whether the voice instruction is correctly registered based on the response voice output from the voice output device 20, and according to the voice instruction of the stage device to be operated Can be confirmed again (OP2 in the figure).

  As described above, in the voice operation system 100 according to the present embodiment, the voice instruction registered in the voice recognition device 40 is converted into command data and transmitted to the stage mechanism control device 50. Thereafter, the command data is converted back into character information by the stage mechanism control device 50, and a response sound based on the character information is output from the sound output device 20. That is, the voice instruction given by the operator is fed back to the operator as a response voice based on the character information. Thereby, the operator can confirm whether the voice instruction issued by the user is correctly registered in the voice operation system 100 based on the response voice.

  In addition to the voice instruction, the status information of the stage device to be operated is output as a voice from the voice output device 20, so that the operator can safely follow the voice operation to the stage device to be operated It can be checked whether it can be operated.

  Furthermore, when it is confirmed that the voice instruction is correctly registered and that the stage device to be operated can be safely operated, the operator operates the mechanical operation device 30 to operate the operation target. Stage equipment can be operated. That is, the operation of the stage apparatus to be operated is not triggered by a voice instruction from the operator but is triggered by a manual instruction by the operator. By doing this, since the voice instruction is correctly registered, and the safe operation of the stage device to be operated can be guaranteed, the stage device to be operated can be operated. Can realize safe and accurate operation of the stage device.

  Further, in the conventional operation device, the operator usually operates in accordance with the instruction from the on-site conductor in the operation room or the like remote from the site, so the state of the stage device to be operated is indicated by voice instruction from the conductor. There was a situation that could only be known. On the other hand, according to voice operation system 100 according to the present embodiment, since the conductor himself acts as the operator to operate the stage apparatus, the operator can visually recognize the state of the stage apparatus to be operated it can. Furthermore, since the operator does not require complicated manual operation in the mechanical operating device 30, the operator can concentrate his / her gaze on the stage device to be operated. As a result, the operator can operate the stage apparatus accurately and safely while grasping the latest state of the stage apparatus to be operated.

  However, in the voice operation system 100 according to the present embodiment, when any abnormality occurs in the voice operation system 100, such as failure of any of the plurality of stage devices 60_1 to 60_n, the entire plurality of stage devices 60_1 to 60_n are Emergency stop is required. In such a case, the operator who has detected an abnormality can input a voice instruction such as “Emergency stop” to the voice operation device 10, for example. When the voice command of the emergency stop is converted into command data by the voice recognition device 40 and given to the stage mechanism control device 50, the stage mechanism control device 50 can quickly without waiting for a manual command from the mechanical operation device 30. The entire stage device 60_1 to 60 — n can be stopped.

[Modification of operation of voice operation system]
Next, a variation of the operation of voice operation system 100 according to the present embodiment will be described.

  FIG. 6 is a diagram for explaining the flow of data among the operator, the voice operation system 100, and the stage mechanism. Compared with the flow of data shown in FIG. 3, in the flow of data shown in FIG. 6, the button operation (OP3 in FIG. 3) by the operator is replaced with the voice input (OP4 in FIG. 6) by the operator. The difference is that The other parts are the same as in FIG. 3, and thus the detailed description will not be repeated.

  6, the content of the voice instruction registered based on the operator's voice input OP1 from the voice output device 20 and the status information of the stage device to be operated specified by the voice command are response voices. When it is output, the operator listens to the response voice to determine whether or not the voice input OP1 of the operator matches the registered voice instruction, that is, the voice instruction of the user is correctly registered. It can be confirmed whether or not it is (OP2 in the figure).

  In addition, the operator can grasp the current state of the stage device to be operated by listening to the response voice, and thus, confirms whether or not the stage device can be operated according to the voice instruction. Can be done (OP2 in the figure).

  When it is confirmed that the voice instruction is correctly registered and that the operation-targeted stage apparatus can be operated as the voice instruction (OP2 in the figure), the operator instructs the voice-type operation device 10 to operate. Input a voice instruction (OP4 in the figure). In this voice input OP4, the operator can input an execution command for executing the voice command registered based on the above-described voice input OP1. For example, the operator can input an audio instruction “execution” to the audio operation device 10 as an execution instruction. When the voice operation device 10 receives an execution command (voice data) from the operator, the voice operation device 10 transmits voice data indicating the execution command to the voice recognition device 40.

  The voice recognition device 40 converts an execution command (voice data) from the voice operation device 10 into a command for the stage mechanism control device 50. Specifically, the voice recognition device 40 converts an execution command, which is voice data, into a command code associated with the execution command. The command code is a code assigned to the execution command, and can be included in the table shown in FIG. Thereby, the speech recognition apparatus 40 can convert an execution command (for example, "execution") from the operator into a command code by referring to the table.

  As in the case of the voice input OP1, in the voice input OP4, by including an instruction (for example, "instruction") for starting code conversion at the beginning of the voice instruction, the code conversion process in the speech recognition device 40 can be accurately performed. Can be enhanced.

  When the stage mechanism control device 50 receives the command code representing the execution command from the voice recognition device 40, the control for controlling the stage device to be operated in accordance with the voice instruction registered based on the voice input OP1 of the operator. Generate a command (electrical signal). For example, when command data (codes "001, 22, 210") shown in FIG. 5 is received from the speech recognition device 40 in response to the voice input OP1, the stage mechanism control device 50 is a command representing an execution command. When the code is received, a control command for “raising the grid to 22 m above the floor” is generated.

  The stage mechanism control device 50 outputs the generated control command to the stage device to be operated. As a result, the stage device to be operated operates in accordance with the voice instruction.

  As described above, in the present modification, when it is confirmed that the voice instruction is correctly registered and that the stage apparatus to be operated can be operated safely, the operator can voice the execution command. By inputting at, the stage device to be operated can be operated according to the registered voice instruction. That is, in the present modification, the operation of the stage device to be operated is executed using an execution command uttered by the operator as a trigger. By doing this, since the voice instruction is correctly registered, and the safe operation of the stage device to be operated can be guaranteed, the stage device to be operated can be operated. Can realize safe and accurate operation of the stage device.

  However, when an abnormality occurs in the voice operation system 100, such as failure of any of the plurality of stage devices 60_1 to 60 — n, the operator who has detected the abnormality may, for example, The voice instruction "stop" can be input. In this case, when the voice command of the emergency stop is converted into command data by the voice recognition device 40 and given to the stage mechanism control device 50, the stage mechanism control device 50 inputs a command representing an execution command from the voice recognition device 40. The entire stage device 60_1 to 60 — n can be quickly stopped without waiting for

  The operations of the voice operation system 100 shown in FIG. 3 and the modified examples of the operation of the voice operation system 100 shown in FIG. 6 can be implemented by combining them as appropriate. FIG. 7 is a flowchart for explaining the operation of voice operation system 100 according to the present embodiment.

  Referring to FIG. 7, first, in step S01, the stage mechanism control device 50 determines whether or not an input operation on the operating device 70 has been performed. When the input operation is performed on operation device 70 (when YES in S01), stage mechanism control device 50 controls the stage device to be operated based on the operation command from operation device 70 in step S12. To generate a control command (electrical signal). The stage mechanism control device 50 outputs the generated control command to the stage device to be operated. As a result, the stage device to be operated operates according to the input operation.

  On the other hand, if the input operation to the operation device 70 is not performed (NO in S01), the process proceeds to step S02, and it is determined whether the voice input to the voice operation device 10 (OP1 in FIGS. 3 and 6) is performed. Is determined. If the voice input OP1 is not performed (NO in S02), the process ends.

  On the other hand, if the voice input OP1 is performed (YES in S02), the process proceeds to step S03, and the voice recognition device 40 converts the voice instruction, which is voice data, into command data (command code) .

  Next, in step S04, the stage mechanism control device 50 converts the command data generated by the speech recognition device 40 and the status information of the stage device to be operated into character information. In step S05, a voice (response voice) based on the character information generated by the stage mechanism control device 50 is output from the voice output device 20.

  Next, at step 06, it is judged if the button operation (OP3 in FIG. 3) on the mechanical operation device 30 has been performed. When the button operation on the mechanical operation device 30 is performed (YES in S06), the mechanical operation device 30 generates an operation command and outputs the operation command to the stage mechanism control device 50. The stage mechanism control device 50 generates a control command (electric signal) for controlling the stage device to be operated based on the operation command from the mechanical operation device 30. The stage mechanism control device 50 outputs the generated control command to the stage device to be operated. As a result, the stage device to be operated operates in accordance with the voice instruction.

  On the other hand, when the button operation on mechanical operating device 30 is not performed in step S06 (when NO in S06), the process proceeds to step S08, and voice input (OP4 in FIG. 6) to voice operating device 10 is performed. It is determined whether or not it is. If the voice input OP4 is performed (YES in S08), the voice recognition device 40 converts an execution command, which is voice data, into a command code in step S09. When a command code representing an execution command is given to the stage mechanism control device 50 in step S10, the stage mechanism control device 50 proceeds to step S11 and operates according to the voice instruction registered based on the voice input OP1 in step S02. A control command (electric signal) for controlling the target stage device is generated. The stage mechanism control device 50 outputs the generated control command to the stage device to be operated. As a result, the stage device to be operated operates in accordance with the voice instruction.

[Voice recognition in voice operation system]
Hereinafter, with reference to FIGS. 8 to 10, a configuration example for speech recognition in speech operation system 100 according to the present embodiment will be described. Each of FIGS. 8 to 10 exemplifies a case where two operators OPA and OPB issue voice instructions independently of each other. The operator may be three or more.

  FIG. 8 is a view for explaining a first configuration example of voice recognition that can be applied to the voice operation system 100. As shown in FIG. Referring to FIG. 8, operator OPA can issue a voice instruction and a manual instruction, respectively, using voice operation device 10A and mechanical operation device 30A. The operator OPB can issue an audio instruction and a manual instruction, respectively, using the audio operating device 10B and the mechanical operating device 30B.

  In FIG. 8, voice recognition devices 40A and 40B are provided corresponding to the voice operation devices 10A and 10B, respectively. That is, the voice operation device 10 and the voice recognition device 40 correspond one to one.

  FIG. 9 is a view for explaining a second configuration example of voice recognition that can be applied to the voice operation system 100. As shown in FIG. Also in FIG. 9, as in FIG. 8, the operator OPA can issue a voice instruction and a manual instruction using the voice operation device 10A and the mechanical operation device 30A, respectively. The operator OPB can issue an audio instruction and a manual instruction, respectively, using the audio operating device 10B and the mechanical operating device 30B.

  In FIG. 9, one voice recognition device 40 is provided for the plurality of voice-type controller devices 10A and 10B. Furthermore, between each voice-type operating device 10 and the voice recognition device 40, a voice transmission device 15 is provided.

  In the second configuration example, the voice instruction input to each voice-type operating device 10 is transmitted to the voice recognition device 40 via the voice transmission device 15. In the stage mechanism and the play mechanism, usually, a plurality of operators each possess an intercom, and voice communication is performed between the operators via a voice transmission device. In the second configuration example, the intercom possessed by each operator can be used as the voice operation device 10. That is, each operator can communicate with other operators using the intercom and can issue an audio instruction. According to the second configuration example, the voice operation system 100 can be realized at low cost by utilizing the existing device.

  FIG. 10 is a view for explaining a third configuration example of voice recognition that can be applied to the voice operation system 100. As shown in FIG. Also in FIG. 10, similarly to FIGS. 8 and 9, the operator OPA can issue a voice instruction and a manual instruction, respectively, using the voice operation device 10A and the mechanical operation device 30A. The operator OPB can issue an audio instruction and a manual instruction, respectively, using the audio operating device 10B and the mechanical operating device 30B. Further, as in FIG. 9, a voice transmission device 15 is provided between each voice-type operating device 10 and the voice recognition device 40.

  In FIG. 10, voice buttons 35A and 35B are provided on the mechanical operation devices 30A and 30B, respectively. The voice buttons 35A and 35B are operation buttons for effectively setting the input operation of the voice instruction to the voice operation device 10.

  Here, it is assumed that the audio operation devices 10A and 10B are intercoms, and the operators OPA and OPB can communicate via the audio transmission device 15. In this situation, when the operator OPB performs an input operation on the voice button 35B, the voice recognition device 40 enters a standby state for receiving a voice input to the voice operation device 10B. When the operator OPB inputs a voice instruction to his / her voice type operation device 10, the voice instruction is transmitted to the voice recognition device 40 via the voice transmission device 15.

  According to the third configuration example, in the configuration in which the intercom possessed by each operator is used as the voice operation device 10, it is easy to separate communication between the operators and the voice instruction.

  It should be understood that the embodiments disclosed herein are illustrative and non-restrictive in every respect. The scope of the present invention is indicated not by the above description but by the claims, and is intended to include all the modifications within the meaning and scope equivalent to the claims.

  10, 10A, 10B voice operation device, 15 voice transmission device, 20 voice output device, 30, 30A, 30B mechanical control device, 35A, 35B voice button, 40 voice recognition device, 50 stage mechanism control device, 60_1-60_n Stage device, 70 operation device, 100 voice operation system, OP, OPA, OPB operator.

Claims (11)

A voice operation system for operating a plurality of devices included in a stage mechanism, a studio mechanism or a play mechanism by voice,
A first operation device configured to receive an operation instruction by voice from an operator;
A voice recognition device configured to convert, into command data, the operation instruction by the voice input to the first operation device;
A control device configured to generate character information representing the command data and the status information in response to the command data converted by the voice recognition device and status information indicating a state of the plurality of devices;
A voice operation system comprising: a voice output device configured to output a voice based on the character information generated by the control device. And a second operation device configured to receive a manual operation instruction from the operator.
The voice operation system according to claim 1, wherein the control device is configured to control each of the plurality of devices in accordance with the manual operation instruction input to the second operation device and the command data. .   The voice operation system according to claim 2, wherein the second operation device includes a mechanical operation unit, and is configured to receive the manual operation instruction to the operation unit.   4. The voice operation system according to claim 2, wherein, when the command data is a stop instruction, the control device stops the plurality of devices according to the command data without waiting for the manual operation instruction. . The first operation device is further configured to receive an execution instruction by voice from the operator;
The voice recognition device is further configured to convert the execution command input to the first operation device into a command for the control device.
The voice operation system according to claim 1, wherein the control device is configured to control each of the plurality of devices according to the command data when receiving a command representing the execution command.   6. The voice operation according to claim 5, wherein, when the command data is a stop instruction, the control device stops the plurality of devices according to the command data without waiting for input of a command representing the execution command. system. The operation instruction by voice includes identification information for identifying a device to be operated, and operation information indicating operation content for the device to be operated,
The voice recognition device is configured to convert the identification information and the operation information into the command data represented by a command code that can be executed by the control device. Voice control system described in.   The character information includes identification information for identifying a device to be operated, operation information indicating an operation content for the device to be operated, and the status information of the device to be operated. The voice operation system according to any one of 7. The third control device configured to receive a manual operation instruction from an operator different from the operator is connected to the control device;
The control device is a case where the instruction by the voice is not input to the first operation device, and the operation instruction from the different operator is input to the third operation device. The voice operation system according to any one of claims 1 to 8, configured to control each of the plurality of devices in accordance with operation instructions from different operators. A plurality of first operation devices are provided corresponding to a plurality of operators, respectively.
The voice transmission device according to any one of claims 1 to 9, further comprising: an audio transmission device configured to receive an operation instruction by the voice input to each of the plurality of first operation devices and transmit the operation instruction to the voice recognition device. The voice operation system described in the section. A plurality of first operation devices are provided corresponding to a plurality of operators, respectively.
It further comprises an audio transmission device configured to receive an operation instruction by the voice input to each of the plurality of first operation devices and transmit the operation instruction to the speech recognition device;
A plurality of second operation devices are provided corresponding to the plurality of operators, respectively.
The method according to any one of claims 2 to 4, wherein each of the plurality of second operation devices is configured to effectively set the input operation of the operation instruction by the voice to the first operation device. Voice operation system.

Images