JP7124572B2 - IMAGE FORMING APPARATUS AND IMAGE FORMING APPARATUS CONTROL PROGRAM - Google Patents

Description

The present invention relates to an image forming apparatus and a control program for the image forming apparatus. More particularly, the present invention relates to an image forming apparatus and a control program for an image forming apparatus capable of improving voice recognition accuracy.

Electrophotographic image forming apparatuses include MFPs (Multi Function Peripherals), facsimile machines, copiers, printers, etc., which have scanner functions, facsimile functions, copying functions, functions as printers, data communication functions, and server functions. be.

In recent years, a technique has been proposed in which a device recognizes a voice uttered by a user or an operator of the device and performs an operation according to the recognized voice. Japanese Unexamined Patent Application Publication No. 2002-200002 discloses a conference device that can switch the directivity of a microphone without a user's intentional operation. This conference device has a microphone and a camera attached to an arm. When the arm is upright and the camera can shoot, the microphone has forward directivity. The microphone is omnidirectional when the arm is tilted and the camera cannot take a picture.

Japanese Unexamined Patent Application Publication No. 2002-200002 discloses an image forming apparatus having a voice recognition function. This image forming apparatus includes an audio data generation unit that receives audio and generates audio data, a noise data generation unit that generates noise data by simulating the operation of a movable part that operates during job execution, and a a noise removal unit for removing noise data from the audio data generated by the audio data generation unit; and a speech recognition unit for performing speech recognition based on the audio data from which the noise data has been removed by the noise removal unit.

JP 2015-188042 A JP 2016-168707 A

In the conventional technology in which an image forming apparatus recognizes a voice uttered by a user or an operator and performs an operation according to the recognized voice, the directivity of a microphone that receives voice input (direction dependence of voice that receives input) is fixed. was

For example, in order to recognize voices from a wide range around the image forming apparatus, an omni-directional microphone (a mic that accepts voice input from a wide range of directions) is used as a microphone for receiving voice input. In such a case, in a situation where a plurality of image forming apparatuses are installed close to each other, there is a risk that other image forming apparatuses may mistakenly recognize the voice emitted to operate the image forming apparatuses. rice field. In addition, in situations where the image forming apparatus is installed in a crowded place such as the center of an office, there is a risk that the image forming apparatus may mistakenly recognize voices unrelated to the operation of the image forming apparatus, such as conversation. was there.

For example, as a microphone that accepts voice input, a microphone with unidirectionality (a directivity that accepts voice input from a specific input direction) is used in order to recognize the voice of the user using the image forming device. However, if this microphone is set to accept voice input from the front of the image forming apparatus, there is a risk that the voice emitted by the worker cannot be recognized when a jam occurs. . That is, when a jam occurs, a worker who is confused about the procedure for clearing the jam should move to a position other than the front (such as a door on the side of the image forming apparatus or the position of the paper discharge section) and clear the jam from such a position. A voice may be emitted asking for instructions on how to In this case, if the directivity of the microphone is directed toward the front of the image forming apparatus, there is a possibility that the voice uttered by the operator cannot be recognized.

A conventional technique for operating an image forming apparatus by voice has a problem of low voice recognition accuracy due to misrecognition of voice or failure to recognize voice depending on the situation of the image forming apparatus.

SUMMARY OF THE INVENTION An object of the present invention is to provide an image forming apparatus and a control program for the image forming apparatus that can improve speech recognition accuracy.

An image forming apparatus according to an aspect of the present invention includes voice input means for receiving input of voice, voice recognition means for recognizing the voice received by the voice input means, and processing based on recognition results by the voice recognition means. and the directivity of the voice input means, which is the direction dependency of the voice that accepts the input, in the direction determined according to the type of state when the image forming apparatus is in a state that requires some work . and switching means for switching between.

An image forming apparatus according to another aspect of the present invention includes voice input means for receiving an input of voice, voice recognition means for recognizing the voice received by the voice input means, and processing based on the result of recognition by the voice recognition means. and switching means for switching, based on the state of the image forming apparatus, the directivity of the audio input means, which is the direction dependency of the audio that receives the input, wherein the switching means comprises at least unidirectional and Switching the directivity of the audio input means from options including omnidirectional, unidirectional is a directivity that accepts voice input from a specific input direction, and omnidirectional is wider than the input direction It is the directivity that accepts voice input from the direction of the range.

In the image forming apparatus described above, preferably, the switching means switches the directivity of the audio input means from options including a plurality of unidirectional directions having a plurality of input directions different from each other.

In the above image forming apparatus, preferably, when the state of the image forming apparatus is not in a specific state, the switching means switches the directivity of the voice input means to unidirectional with the front of the image forming apparatus as the input direction.

In the above image forming apparatus, the specific state preferably includes a state in which a jam occurs in the image forming apparatus, and when the jam occurs in the image forming apparatus, the switching means changes the directivity of the voice input means to omnidirectional. switch to

In the above image forming apparatus, preferably, when the jam that has occurred in the image forming apparatus is cleared, the switching means switches the directivity of the sound input means to unidirectional with the front of the image forming apparatus as the input direction.

The image forming apparatus preferably further includes a housing and a door provided in the housing that can be opened and closed, wherein the specific state includes an open state of the door, and when the door is in the open state, the switching means switches the directivity of the voice input means to unidirectional with the direction of the door as the input direction, and after switching the directivity of the voice input means to unidirectional with the direction of the door as the input direction, the image The switching means switches the directivity of the voice input means to omnidirectional when the non-operation time in which no operation is performed on the forming apparatus has passed the first time.

Preferably, in the above image forming apparatus, there are a plurality of doors, and when one of the plurality of doors is in an open state, the switching means is unidirectional with the direction of the opened door as an input direction. The directivity of the voice input means is switched according to the nature.

Preferably, the above image forming apparatus further includes storage means that is provided in the housing and stores the sheets and that can be pulled out from the housing, and the specific state includes a state in which the storage means is pulled out. , when the accommodation means is pulled out from the housing, the switching means switches the directivity of the voice input means to unidirectional with the direction of the accommodation means as the input direction, and makes the direction of the accommodation means the input direction. After switching the directivity of the audio input means to unidirectional, the switching means switches the directivity of the audio input means when the non-operation time during which no operation is performed on the image forming apparatus elapses for a second period of time. Switch to omnidirectional.

In the above image forming apparatus, preferably, the specific state includes a state in which an operation mode of the image forming apparatus has transitioned to a work mode for a worker to perform work on the image forming apparatus, and the operation mode of the image forming apparatus is changed to the work mode. transition, the switching means switches the directivity of the audio input means to omnidirectional.

In the above image forming apparatus, preferably, the specific state includes a state in which a trouble occurs in which image formation cannot be performed in the image forming apparatus. Switch the directivity of the input means to omnidirectional.

A control program for an image forming apparatus according to still another aspect of the present invention includes voice input means for receiving input of voice, voice recognition means for recognizing the voice received by the voice input means, and a result of recognition by the voice recognition means. A control program for an image forming apparatus, comprising a control means for executing processing based on the following: This is for causing the computer to execute a switching step of switching the directivity of the audio input means, which is the direction dependency of the audio that receives the input.
A control program for an image forming apparatus according to still another aspect of the present invention includes voice input means for receiving input of voice, voice recognition means for recognizing the voice received by the voice input means, and a result of recognition by the voice recognition means. A control program for an image forming apparatus comprising a control means for executing processing based on the state of the image forming apparatus, wherein the directivity of the voice input means, which is the direction dependency of voice for receiving input, is switched based on the state of the image forming apparatus. for causing the computer to perform a switching step, in which the directivity of the audio input means is switched from options including at least unidirectional and omnidirectional; It is a directivity that accepts voice input from all directions, and omni-directivity is a directivity that accepts voice input from a wider range of directions than the input direction.

According to the present invention, it is possible to provide an image forming apparatus and a control program for the image forming apparatus that can improve speech recognition accuracy.

1 is a block diagram showing the configuration of an image forming apparatus 100 according to an embodiment of the invention; FIG. 1 is a front view schematically showing the configuration of an image forming apparatus 100 according to an embodiment of the invention; FIG. FIG. 7 is a diagram showing an example of options for switching the directivity of the microphone 29; 4 is the first part of the flow chart showing the directivity switching operation of the microphone 29 in one embodiment of the present invention. FIG. 10 is the second part of the flow chart showing the directivity switching operation of the microphone 29 in one embodiment of the present invention. FIG. FIG. 10 is the third part of the flow chart showing the directivity switching operation of the microphone 29 in one embodiment of the present invention. FIG. FIG. 10 is the fourth part of the flow chart showing the directivity switching operation of the microphone 29 in one embodiment of the present invention. FIG. FIG. 10 is the fifth part of the flowchart showing the directivity switching operation of the microphone 29 according to the embodiment of the present invention; FIG. FIG. 10 is the sixth part of the flow chart showing the directivity switching operation of the microphone 29 in one embodiment of the present invention. FIG.

An embodiment of the present invention will be described below with reference to the drawings.

In this embodiment, a case where the image forming apparatus is an MFP will be described. The image forming apparatus may be an MFP, a printer, a facsimile machine, a copier, or the like.

FIG. 1 is a block diagram showing the configuration of an image forming apparatus 100 according to one embodiment of the invention.

Referring to FIG. 1, image forming apparatus 100 (an example of image forming apparatus) in the present embodiment includes a CPU (Central Processing Unit) 21 (an example of voice recognition means, control means, and switching means), bus 22 , ROM (Read Only Memory) 23, RAM (Random Access Memory) 24, non-volatile memory 25, hard disk device 26, display unit 27, operation unit 28, microphone 29 (an example of voice input means), and , voice input unit 30 (an example of voice input means), authentication unit 31, scanner unit 32, image processing unit 33, printer unit 34, facsimile communication unit 35, network communication unit 36, post-processing unit 37 , a paper feed tray sensor 38 , a paper sensor 39 , a door sensor 40 , a paper feed tray 41 (an example of storage means), and an operation panel 42 .

CPU 21 controls the overall operation of image forming apparatus 100 based on programs stored in ROM 23 . In particular, the CPU 21 uses a dictionary for speech recognition processing to recognize speech data generated by the speech input unit 30, and executes various processes based on the recognition result.

For example, when recognizing voice data for setting job execution conditions such as the number of prints, density, paper size, etc., the CPU 21 reflects the settings in the job execution conditions. When recognizing voice data instructing execution of a job, the CPU 21 executes the job. When recognizing voice data inquiring about various operation methods of the image forming apparatus 100 , the CPU 21 responds to the inquiry through the display unit 27 .

The bus 22 includes a CPU 21, a ROM 23, a RAM 24, a non-volatile memory 25, a hard disk device 26, a display unit 27, an operation unit 28, a microphone 29, a voice input unit 30, an authentication unit 31, a scanner unit 32, an image processing unit 33, and a printer unit. 34, facsimile communication unit 35, network communication unit 36, post-processing unit 37, paper feed tray sensor 38, paper sensor 39, door sensor 40, paper feed tray 41, and operation panel 42 are connected.

ROM 23 is, for example, a flash ROM. Various programs executed by the CPU 21 and various fixed data are stored in the ROM 23 . The ROM 23 may be non-rewritable.

A RAM 24 is a main memory of the CPU 21 . The RAM 23 is used for temporarily storing necessary data when the CPU 21 executes various programs. The RAM 24 is also used as an image memory for temporarily storing image data.

The nonvolatile memory 25 is a memory that retains data even when the power is turned off. The non-volatile memory 25 stores device-specific information, various setting information, authentication information for verification, display data for various screens to be displayed on the display unit 27, a dictionary for voice recognition processing, and the like.

Various types of data are stored in the hard disk device 26 . The hard disk device 26 also stores image data obtained by scanning and copying documents, print data (image data) included in print jobs requested from external devices, and received facsimile data. , image data attached to e-mail, and image data input by connecting an external storage device. Note that the voice recognition processing dictionary may be stored in the hard disk device 26 instead of the non-volatile memory 25 .

The display unit 27 is composed of a liquid crystal display or the like. The display unit 27 displays various screens such as an operation screen, a setting screen, a confirmation screen, and a notification screen.

The operation unit 28 includes various buttons such as a mode selection key for selecting an operation mode (job type) of a job to be set, a start key, a stop key, a cancel key, and a numeric keypad. It is composed of a touch panel or the like that detects the coordinate position that is displayed. The operation unit 28 receives various operations performed on the image forming apparatus 100 . The display unit 27 and the operation unit 28 are provided on the operation panel 42 .

The microphone 29 and the voice input section 30 constitute voice input means. A microphone 29 is for voice operation and is provided on the operation panel 42 . The voice input unit 30 receives voice input through the microphone 29 and generates voice data.

The authentication unit 31 identifies (specifies) and authenticates the user by, for example, comparing authentication information input by the user with authentication information for verification stored in the nonvolatile memory 25 .

The scanner unit 32 optically reads a document to acquire image data. The scanner unit 32 includes, for example, a light source that irradiates the document with light, a line image sensor that receives the reflected light and reads the document for one line in the width direction, and a line-by-line reading position that sequentially moves in the length direction of the document. an optical path consisting of lenses and mirrors that guide the reflected light from the original to the line image sensor to form an image; a converter that converts the analog image signal output from the line image sensor into digital image data, etc. contains.

The image processing unit 33 performs rasterization processing on print data (print data in vector format) received from an external device, and performs various operations such as image correction, rotation, enlargement/reduction, or compression/expansion on image data. image processing.

The printer unit 34 forms an image based on the image data on paper by an electrophotographic process and outputs the image. The printer unit 34 is a so-called laser printer. It includes a scanning unit that scans the photoreceptor drum with laser light, a developing device, a transfer/separating device, a cleaning device, and a fixing device. Note that the printer unit 34 may be a printer of another type, such as an LED printer that irradiates a photosensitive drum with an LED (Light Emitting Diode).

A facsimile communication unit 35 transmits and receives image data to and from an external device having a facsimile function through a public line.

The network communication unit 36 communicates with an external device through a network such as a LAN (Local Area Network).

The post-processing section 37 performs post-processing such as folding processing, punching processing, stapling processing, binding processing, or cutting processing on sheets on which images have been formed.

The paper feed tray 41 accommodates paper for image formation. The paper feed tray 41 may be singular or plural.

FIG. 2 is a front view schematically showing the configuration of image forming apparatus 100 according to one embodiment of the present invention. In FIG. 2, the width direction of the image forming apparatus 100 is the x-axis, the front is the y-axis direction, and the height direction is the z-axis. The x-, y-, and z-axes are orthogonal to each other. Both the x-axis and the y-axis lie in the horizontal plane.

1 and 2, image forming apparatus 100 further includes housing 100a (an example of a housing) and doors 61 to 64 (an example of doors). The housing 100 a accommodates each member constituting the image forming apparatus 100 . A scanner section 32 is provided at the top of the housing 100a. The scanner unit 32 includes an ADF (Auto Document Feeder) 32a that feeds a document to a reading position. A printer section 34 is provided below the scanner section 32 at the center of the housing 100a. Here, a plurality of paper feed trays 41 are provided below the printer unit 34 and inside the housing 100a. Each of the plurality of paper feed trays 41 can be pulled out forward (positive direction of the y-axis) from inside the housing 100a. When the paper feed tray 41 is pulled out forward, the paper feed tray 41 is in an open state in which the inside is exposed. An operation panel 42 is provided on the upper front surface of the housing 100a. A user stands near the front of image forming apparatus 100 and performs operations such as setting a document to prepare for a job, operating operation panel 42 , and the like.

Each of the doors 61-64 is provided in the housing 100a. Each of the doors 61 to 64 can be opened and closed, and exposes the interior of the housing 100a to the outside when opened. Doors 61 and 62 are doors that are opened when a jam that has occurred in the printer section 34 is cleared. The door 61 is provided on the front surface of the housing 100a, and the door 62 is provided on the left side surface of the housing 100a. The door 63 is a door that is opened when clearing a jam that has occurred in the post-processing section 37 . The door 63 is provided on the front surface of the housing 100a. A door 64 is a door that is opened when clearing a jam that has occurred in the ADF 30a. The door 64 is provided on the upper surface of the housing 100a. The door may be singular or plural.

The paper feed tray sensor 38 detects the open/closed state of each of the plurality of paper feed trays 41 .

A paper sensor 39 detects a jam that has occurred in the printer section 34 .

The door sensor 40 detects the open/closed state of each of the doors 61-64.

Note that the image forming apparatus 100 has a normal mode and a service mode as operation modes. The service mode is a work mode for a worker (such as a service engineer) to work on the image forming apparatus 100 . The operation mode of image forming apparatus 100 transitions between a normal mode and a service mode when a predetermined operation is received through operation panel 42 .

The CPU 21 switches the directivity of the voice input means (specifically, the microphone 29) based on the state of the image forming apparatus 100. FIG. The directivity of the microphone 29 is the directional dependence of the sound that the microphone 29 receives as input.

FIG. 3 is a diagram showing an example of options for switching the directivity of the microphone 29. As shown in FIG. In FIG. 3, the position of the microphone 29 is set as the origin, and the area for receiving voice input is hatched.

2 and 3, the directivity of microphone 29 can be switched from options including unidirectional and omnidirectional under the control of CPU 21. FIG. Unidirectionality is a directivity that accepts voice input from a specific input direction. The omnidirectionality is a directivity that accepts voice input from a wider range of directions than the above-described input directions (directions in which the microphone 29 having unidirectionality accepts voice input). Furthermore, when the microphone 29 has unidirectionality, the directivity of the microphone 29 may be switchable among options including a plurality of unidirectionalities having a plurality of mutually different input directions.

FIG. 3A shows unidirectionality with the front of the image forming apparatus 100 as the input direction. The paper feed tray 41 and the door 61 in the open state are located in front of the microphone 29 (specifically, in the positive direction of the y-axis as seen from the microphone 29). Therefore, when the directivity of the microphone 29 is switched to the state shown in FIG. Voice input from the operator can be received with high sensitivity.

FIG. 3B shows unidirectionality with the left side of the image forming apparatus 100 as the input direction. The door 62 exists on the left side of the housing 100a when it is in the open state, and exists to the left (in the positive direction of the x-axis) as viewed from the microphone 29 . Therefore, when the directivity of the microphone 29 is switched to the state shown in FIG. 3B, the voice input unit 30 can receive the voice input from the worker working near the door 62 with high sensitivity. .

FIG. 3C shows unidirectionality with the right side of the image forming apparatus 100 as the input direction. The door 63 exists on the right side (negative direction of the x-axis) when viewed from the microphone 29 . Therefore, when the directivity of the microphone 29 is switched to the state shown in FIG. 3C, the voice input unit 30 can receive voice input from the worker working near the door 63 with high sensitivity. .

FIG. 3D shows unidirectionality with the right rear of the image forming apparatus 100 as the input direction. The door 64 exists on the right rear side (between the negative direction of the x-axis and the negative direction of the y-axis) when viewed from the microphone 29 . Therefore, when the directivity of the microphone 29 is switched to the state shown in FIG. 3D, the voice input unit 30 can receive the voice input from the worker working near the door 64 with high sensitivity. .

FIG. 3(e) shows omnidirectionality. By switching the directivity of the microphone 29 to the state shown in FIG. 3(e) when the position of the person emitting the voice cannot be predicted, the voice input unit 30 can receive voice input from a wide range with good sensitivity. can.

Although FIG. 3 shows the case where the microphone 29 has directivity only in the x-axis and y-axis directions, the microphone 29 may also have directivity in the z-axis direction.

Next, the operation of switching the directivity of the microphone 29 in this embodiment will be described.

4 to 9 are flow charts showing the directivity switching operation of the microphone 29 according to one embodiment of the present invention.

Referring to FIG. 4, at an arbitrary timing, CPU 21 determines whether or not image forming apparatus 100 is in a specific state (S100). The specific state is preferably a state that requires some work on image forming apparatus 100 . Here, the specific states are a state in which a jam has occurred, an open state of any one of the doors 61 to 64, an open state (pulled out state) of any of the plurality of paper feed trays 41, and an image forming state. A state in which the operation mode of the apparatus 100 has transitioned to the service mode and a state in which the image forming apparatus 100 is in trouble are included.

If it is determined in step S100 that image forming apparatus 100 is not in the specific state (NO in S100), image forming apparatus 100 is in a state of being able to operate normally. In this case, the CPU 21 switches the directivity of the microphone 29 to unidirectional with the front of the image forming apparatus 100 as the input direction (S101), and ends the process.

When a user who operates image forming apparatus 100 executes various jobs such as a copy job, a scan job, or a print job in image forming apparatus 100, the user normally faces image forming apparatus 100 (on the positive side of the y-axis). stand on the screen) and emit voices to perform operations related to job execution. In this case, the voice generated by the user includes voice for setting job execution conditions such as the number of prints or density, paper size, etc., and voice for instructing execution of the job. As in the process of step S101, when the image forming apparatus 100 is in a state of being able to operate normally, the front of the image forming apparatus 100 is set as the input direction of the microphone 29, so that the user performs an operation related to job execution. can be efficiently picked up by the microphone 29.

When it is determined in step S100 that the image forming apparatus 100 is in the specific state (NO in S100), the CPU 21 determines whether or not the paper sensor 39 has detected a jam (S200).

If it is determined in step S200 that the jam has occurred (YES in S200), the CPU 21 proceeds to the process of step S201 in FIG.

If it is determined in step S200 that no jam has been detected (NO in S200), the CPU 21 determines whether or not the door sensor 40 has detected the open state of any one of the doors 61 to 64 (S300). ).

If it is determined in step S300 that any one of the doors 61 to 64 is open (YES in S300), the CPU 21 proceeds to step S301 of FIG.

If it is determined in step S300 that none of the doors 61 to 64 are open (NO in S300), the CPU 21 causes the paper feed tray sensor 38 to detect the open state of any one of the plurality of paper feed trays 41. It is determined whether or not it has been detected (S400).

When it is determined in step S400 that any one of the plurality of paper feed trays 41 is detected to be open (YES in S400), the CPU 21 proceeds to the process of step S401 in FIG.

When it is determined in step S400 that none of the plurality of paper feed trays 41 is in the open state (NO in S400), CPU 21 detects that the operation mode of image forming apparatus 100 has changed to the service mode. It is determined whether or not (S500).

If it is determined in step S500 that the operation mode of image forming apparatus 100 has changed to the service mode (YES in S500), the CPU 21 proceeds to the process of step S501 in FIG.

If it is determined in step S500 that the operation mode of image forming apparatus 100 has not changed to the service mode (NO in S500), CPU 21 determines that trouble has occurred in image forming apparatus 100 (S600), The process proceeds to step S601 in FIG.

Referring to FIG. 5, when determining that the occurrence of a jam has been detected, the CPU 21 switches the directivity of the microphone 29 to omnidirectional (S201).

Jams can occur at various locations in image forming apparatus 100 . The position of the worker who performs the work for clearing the jam also changes according to the location where the jam occurs. For this reason, as in the processing of step S201, when a jam occurs, switching the directivity of the microphone 29 to omnidirectional enables the worker's voice emitted from a wide range ) can be efficiently picked up.

Next, the CPU 21 determines whether or not the open state of any one of the doors 61 to 64 has been detected (S202). The CPU 21 repeats the process of step S202 until it determines that any one of the doors 61 to 64 is open.

If it is determined in step S202 that one of the doors 61 to 64 is open (YES in S202), the CPU 21 directs the microphone 29 unidirectionally with the direction of the opened door as the input direction. switch gender (S203).

If a door is opened during jam clearing, it is highly likely that the worker will use the door to clear the jam, and more specific procedures for clearing the jam (e.g. lever information) are required. ) is likely to be emitted. Therefore, as in the process of step S203, when the door is opened, the directivity of the microphone 29 is switched to unidirectional with the direction of the door as the input direction, so that the operator's voice can be efficiently transmitted. can be picked up.

Subsequently, the CPU 21 determines whether or not the non-operation time (the time during which no voice or manual operation is performed on the image forming apparatus 100) has elapsed while the door is open (S204).

In step S204, when it is determined that the predetermined time has elapsed with the door open (YES in S204), the CPU 21 switches the directivity of the microphone 29 to omnidirectional (S206).

In step S204, when it is determined that the predetermined time has not elapsed while the door remains open (NO in S204), the CPU 21 detects that the open door has been closed by the door sensor 40. It is determined whether or not (S205).

When it is determined in step S205 that the closed door that was in the open state is not detected (NO in S205), the CPU 21 proceeds to the process of step S204.

If it is determined in step S205 that the closed door has been detected (YES in S205), the CPU 21 proceeds to step S206.

If the predetermined time has passed without any operation while the door is open, the operator may perform work to clear the jam at another location. Even if the open door is closed, the operator may have to clear the jam at another location. For this reason, as in the process of step S206, when a predetermined time has passed without any operation while the door is open, or when the open door is closed, the microphone 29 is directed omnidirectionally. By switching the nature, the worker's voice emitted from a wide range can be efficiently picked up.

Following the processing of step S206, the CPU 21 determines whether or not the paper sensor 39 has detected that the paper jam has been resolved (S207). The CPU 21 repeats the process of step S207 until it determines that the jam has been cleared.

If it is determined in step S207 that the jam has been cleared (YES in S207), the CPU 21 switches the directivity of the microphone 29 to unidirectional with the front as the input direction (S208), and ends the process.

Referring to FIG. 6, when it is determined that any of the doors 61 to 64 is open, the CPU 21 sets the directivity of the microphone 29 to unidirectional with the direction of the open door as the input direction. (S301).

If the door is opened without a jam, it is presumed that the operator has an intention other than clearing the jam, such as replenishing toner or staples. It is presumed that the operation to Therefore, as in the process of step S301, when the door is opened, the directivity of the microphone 29 is switched to unidirectional with the direction of the door as the input direction, so that the operator's voice can be efficiently transmitted. can be picked up.

Next, the CPU 21 determines whether or not the non-operation time (an example of the first time) has passed a predetermined time while the door is open (S302).

In step S302, when it is determined that the predetermined time has passed without the door being operated (YES in S302), the CPU 21 switches the directivity of the microphone 29 to omnidirectional (S304).

If the door remains open for a predetermined period of time without operation, the operator may replace consumables such as a toner bottle through the door. In this case, the operator asks which of the spare consumables prepared around the image forming apparatus 100 is required (for example, what color toner bottle is required). , may be emitted from the periphery of the image forming apparatus 100 . For this reason, as in the process of step S304, when the door is open and the non-operating time has passed for a predetermined time, by switching the directivity of the microphone 29 to omnidirectional, The worker's voice uttered can be efficiently picked up.

In step S302, when it is determined that the predetermined time has not elapsed while the door remains open (NO in S302), the CPU 21 detects that the open door has been closed by the door sensor 40. It is determined whether or not (S303).

If it is determined in step S303 that the closed door has not been detected (NO in S303), the CPU 21 proceeds to the process of step S302.

If it is determined in step S303 that the closed door has been detected (YES in S303), the CPU 21 proceeds to the process of step S306.

Following the process of step S304, the CPU 21 determines whether or not the door sensor 40 has detected that the open door has been closed (S305). The CPU 21 repeats the process of step S305 until it determines that the closed door that was in the open state is detected.

In step S305, when it is determined that the door that was in the open state has been closed (YES in S305), the CPU 21 switches the directivity of the microphone 29 to unidirectional with the front as the input direction (S306). ) and terminate the process.

Referring to FIG. 7, when it is determined that the open state of one of the plurality of paper feed trays 41 is detected, the CPU 21 sets the direction of the paper feed tray 41 in the open state as the input direction. The directivity of the microphone 29 is switched (S401).

When the paper feed tray 41 is opened, there is a high possibility that the operator will make a sound asking what size paper should be replenished in the paper feed tray 41 . Therefore, as in the process of step S401, by switching the directivity of the microphone 29 to unidirectional with the direction of the paper feed tray 41 as the input direction when the paper feed tray 41 is opened, It is possible to efficiently pick up the worker's voice emitted from the vicinity of the paper feed tray 41. - 特許庁

Next, the CPU 21 determines whether or not a predetermined time (an example of a second time) has passed without operation while the paper feed tray 41 is open (S402).

In step S402, when it is determined that the predetermined time has elapsed with the paper feed tray 41 open (YES in S402), the CPU 21 switches the directivity of the microphone 29 to omnidirectional (S404).

When the predetermined time has passed without any operation while the paper feed tray 41 is open, the operator asks which size paper is required from the spare paper prepared around the image forming apparatus 100 . The inquiring voice may be emitted from the vicinity of the image forming apparatus 100 . For this reason, as in the process of step S404, when a predetermined time has passed without any operation while the paper feed tray 41 is in the open state, the directivity of the microphone 29 is switched to omnidirectional, so that the image forming apparatus 100 can It is possible to efficiently pick up the worker's voice emitted from the surroundings.

In step S402, if it is determined that the predetermined time has not elapsed while the door remains open (NO in S402), the CPU 21 causes the paper feed tray sensor 38 to close the open paper feed tray 41. It is determined whether or not it has been detected (S403).

When it is determined in step S403 that the closed sheet feeding tray 41, which was in the open state, is not detected (NO in S403), the CPU 21 proceeds to the process of step S402.

If it is determined in step S403 that the paper feed tray 41 that was in the open state has been closed (YES in S403), the CPU 21 proceeds to the process of step S406.

Following the process of step S404, the CPU 21 determines whether or not the paper feed tray sensor 38 has detected that the open paper feed tray 41 has been closed (S405). The CPU 21 repeats the process of step S405 until it is determined that the paper feed tray 41 that has been in the open state is closed.

If it is determined in step S405 that the paper feed tray 41, which was in the open state, has been closed (YES in S405), the CPU 21 changes the directivity of the microphone 29 to unidirectional with the front as the input direction. Switch (S406) and terminate the process.

Referring to FIG. 8, when CPU 21 determines that it has detected that the operation mode of image forming apparatus 100 has changed to the service mode, CPU 21 switches the directivity of microphone 29 to omnidirectional (S501).

In the service mode, the service engineer checks the operation of various motors of the image forming apparatus 100 while outputting a test print, touches various sensors of the image forming apparatus 100, and checks the on/off state of the touched sensors. It is assumed that various tasks will be performed. Therefore, it is not possible to predict the position where the service engineer performs the voice operation. Therefore, as in the process of step S501, when the operation mode of image forming apparatus 100 transitions to the service mode, by switching the directivity of microphone 29 to omnidirectional, the sound emitted from the periphery of image forming apparatus 100 is The voice of the service engineer can be picked up efficiently.

Subsequently, the CPU 21 determines whether or not the cancellation of the service mode (that is, the transition to the normal mode) has been detected (S502). The CPU 21 repeats the process of step S502 until it determines that the service mode has been released.

If it is determined in step S502 that the service mode has been canceled (YES in S502), the CPU 21 switches the directivity of the microphone 29 to unidirectional with the front as the input direction (S503), and ends the process.

Referring to FIG. 9, when determining that image forming apparatus 100 has a problem, CPU 21 switches the directivity of microphone 29 to omnidirectional (S601).

Here, trouble means a state in which image formation cannot be performed, and a state in which work by a service engineer is required. Specifically, failure of parts such as fans and motors. It is assumed that a service engineer will be called when a trouble occurs in the image forming apparatus 100 . Since the service engineer performs various tasks to investigate and solve troubles, it is impossible to predict the position where the service engineer performs the voice operation. Therefore, as in the processing of step S601, when the operation mode of the image forming apparatus 100 is changed to the service mode, by switching the directivity of the microphone 29 to omnidirectional, the sound emitted from the periphery of the image forming apparatus 100 is It is possible to efficiently pick up the voice of the service engineer.

Subsequently, the CPU 21 determines whether or not it has detected that the trouble has been resolved (S602). The resolution of the trouble may be detected by a predetermined operation performed by the service engineer through the operation panel, or may be detected by various sensors. The CPU 21 repeats the processing of step S602 until it is determined that the problem has been resolved.

If it is determined in step S602 that the trouble has been resolved (YES in S602), the CPU 21 switches the directivity of the microphone 29 to unidirectional with the front as the input direction (S603), and ends the process. .

[Effects of Embodiment]

According to the present embodiment, since the directivity of microphone 29 is switched based on the state of image forming apparatus 100, more appropriate directivity can be adopted based on the usage status of the user or worker. As a result, the voice uttered by the user or worker can be efficiently picked up, and the voice recognition accuracy can be improved.

[others]

The CPU 21 switches the directivity of the voice input means based on at least one of the presence/absence of a jam, the open/closed state of the door, the open/closed state of the storage unit, the operation mode of the image forming apparatus, and the presence/absence of trouble. may

The processing in the above-described embodiments may be performed by software or by using hardware circuits. It is also possible to provide a program for executing the processes in the above-described embodiments, or record the program on a recording medium such as a CD-ROM, flexible disk, hard disk, ROM, RAM, memory card, etc. and provide it to the user. You may decide to A program is executed by a computer such as a CPU. Alternatively, the program may be downloaded to the device via a communication line such as the Internet.

The above-described embodiments should be considered illustrative in all respects and not restrictive. The scope of the present invention is indicated by the scope of the claims rather than the above description, and is intended to include all modifications within the scope and meaning equivalent to the scope of the claims.

21 CPU (Central Processing Unit) (an example of speech recognition means, control means, and switching means)
22 Bus 23 ROM (Read Only Memory)
24 RAM (Random Access Memory)
25 non-volatile memory 26 hard disk device 27 display unit 28 operation unit 29 microphone (an example of voice input means)
30 voice input unit (an example of voice input means)
31 authentication unit 32 scanner unit 32a ADF (Auto Document Feeder)
33 Image processing unit 34 Printer unit 35 Facsimile communication unit 36 Network communication unit 37 Post-processing unit 38 Paper feed tray sensor 39 Paper sensor 40 Door sensor 41 Paper feed tray (an example of storage means)
42 Operation panel 61-64 Door (an example of a door)
100 image forming apparatus (an example of an image forming apparatus)
100a housing (an example of a housing)

Claims (13)

An image forming apparatus,
voice input means for receiving voice input;
voice recognition means for recognizing voice input by the voice input means;
a control means for executing processing based on a recognition result by the speech recognition means;
Switching means for switching the directivity of the voice input means, which is the direction dependency of the voice for receiving input , to the direction determined according to the type of the state when the image forming apparatus is in a state requiring some kind of work. and an image forming apparatus. An image forming apparatus,
voice input means for receiving voice input;
voice recognition means for recognizing voice input by the voice input means;
a control means for executing processing based on a recognition result by the speech recognition means;
switching means for switching, based on the state of the image forming apparatus, the directivity of the audio input means, which is the direction dependency of audio for receiving input;
the switching means switches the directivity of the audio input means from options including at least unidirectional and omnidirectional;
The unidirectionality is a directivity that accepts voice input from a specific input direction,
The image forming apparatus, wherein the omnidirectionality is a directivity that accepts voice input from directions in a wider range than the input direction. 3. The image forming apparatus according to claim 2, wherein said switching means switches the directivity of said voice input means from options including a plurality of said unidirectivity having a plurality of said input directions different from each other. 3. When the state of said image forming apparatus is not in a specific state, said switching means switches the directivity of said voice input means to said unidirectional directivity in which said input direction is in front of said image forming apparatus. 4. The image forming apparatus according to 2 or 3. the specific state includes a state in which a jam has occurred in the image forming apparatus;
5. The image forming apparatus according to claim 4, wherein when a jam occurs in said image forming apparatus, said switching means switches the directivity of said voice input means to said omni-directivity. 2. When a jam that has occurred in said image forming apparatus is resolved, said switching means switches the directivity of said voice input means to said unidirectional directivity in which said input direction is in front of said image forming apparatus. 5. The image forming apparatus according to 5. a housing;
A door that is provided in the housing and can be opened and closed,
The specific state includes an open state of the door,
when the door is open, the switching means switches the directivity of the voice input means to the unidirectional direction in which the direction of the door is the input direction;
After the directionality of the voice input means is switched to the unidirectional direction in which the direction of the door is the input direction, a non-operation time period during which no operation is performed on the image forming apparatus elapses. 7. The image forming apparatus according to claim 4, wherein said switching means switches directivity of said voice input means to said omni-directivity. said door is plural,
When one of the plurality of doors is open, the switching means directs the voice input means to the unidirectional direction in which the input direction is the direction of the open door. 8. The image forming apparatus according to claim 7, wherein the gender is switched. Further comprising storage means that is provided in a housing and stores paper and that can be pulled out from the housing,
The specific state includes a state in which the accommodation means is pulled out,
when the accommodation means is pulled out from the housing, the switching means switches the directivity of the voice input means to the unidirectional direction in which the direction of the accommodation means is the input direction;
After switching the directivity of the voice input means to the unidirectional direction in which the direction of the accommodating means is the input direction, a second time period of non-operation during which no operation is performed on the image forming apparatus has elapsed. 9. The image forming apparatus according to claim 4, wherein said switching means switches the directivity of said voice input means to said omni-directivity when said voice input means is omnidirectional. The specific state includes a state in which an operation mode of the image forming apparatus has transitioned to a work mode for a worker to perform work on the image forming apparatus,
10. The image forming apparatus according to claim 4, wherein when an operation mode of said image forming apparatus transitions to said work mode, said switching means switches the directivity of said voice input means to said omni-directivity. Device. The specific state includes a state in which a trouble occurs in which the image forming apparatus cannot form an image,
11. The image forming apparatus according to claim 4, wherein when said trouble occurs in said image forming apparatus, said switching means switches the directivity of said voice input means to said omni-directivity. An image comprising voice input means for receiving voice input, voice recognition means for recognizing the voice received by said voice input means, and control means for executing processing based on the recognition result of said voice recognition means. A control program for a forming device,
A switching step of switching the directivity of the voice input means, which is the direction dependency of the voice for receiving input , to the direction determined according to the type of the state when the image forming apparatus is in a state requiring some kind of work. A control program for an image forming apparatus that causes a computer to execute An image comprising voice input means for receiving voice input, voice recognition means for recognizing the voice received by said voice input means, and control means for executing processing based on the recognition result of said voice recognition means. A control program for a forming device,
for causing a computer to execute a switching step of switching the directivity of the audio input means, which is the direction dependency of audio for receiving input, based on the state of the image forming apparatus;
in the switching step, switching the directivity of the voice input means from options including at least unidirectional and omnidirectional;
The unidirectionality is a directivity that accepts voice input from a specific input direction,
The control program for an image forming apparatus, wherein the omnidirectionality is a directivity that accepts voice input from directions in a wider range than the input direction.

Images