JP2020091786A - Speech recognition input device - Google Patents

Abstract

To provide a speech recognition input device capable of reducing the number of utterances required for operation while improving responsiveness to voice input instructions.SOLUTION: A speech recognition input device includes: a data acquisition part that acquires a piece of predetermined data and temporarily stores the data attached with acquisition time of the data in a storage unit; a voice input processing unit that receives a voice input, temporarily stores the voice input time when the voice input is received in the memory, and performs a series of recognition processing of the voice input; and a voice input determination unit configured so as to, when the voice input matches a specific operation instruction, output a command to perform the processing according to the operation instruction on the data at the acquisition time when the voice input is stored in addition to the acquisition time that is the same as the voice input time.SELECTED DRAWING: Figure 1

Description

The present invention relates to a voice recognition input device, and more particularly to a voice recognition input device that is connected to an image capturing device or the like and outputs a command to the image capturing device.

When using the medical X-ray image capturing apparatus in examinations, surgery, etc., it is preferable to use the medical X-ray image capturing apparatus as short as possible in consideration of the health condition of the patient and radiation exposure. For this reason, for example, when finely adjusting the X-ray irradiation range, it is required that the input instruction be smoothly given by the operator.

In addition, for example, even during X-ray fluoroscopy in which continuous X-ray irradiation is performed to observe the inside of the patient as a moving image, various operations are performed by the operator, and therefore it is preferable that the input instruction is smoothly performed. As an operation, for example, when acquiring or saving an image or a moving image for reference, when operating the X-ray diaphragm to adjust the irradiation range of X-rays, an image related to the current examination is selected from past captured images. For example, it is possible to continuously display the images, select an image to be browsed from the images, and display the images again.
Conventionally, an operator physically issues an input instruction as described above by physically operating an input device such as a mouse, a keyboard, a switch and a lever.

However, the operator's hand of the X-ray image pickup apparatus is often blocked during the examination or surgery, and thus an input apparatus that does not require physical operations such as a line of sight and voice is required. As an example of such an input device, Patent Document 1 proposes image display by a voice input instruction using a voice recognition technique. That is, in Patent Document 1, a medical image is stored together with a subject name and a subject ID, and when at least one of the subject name and the subject ID is voice-recognized, the corresponding medical image is searched and displayed from the data file using the recognition result as a key. Let Thereby, even when the operator's hand is blocked, a desired image is displayed without performing a complicated operation of inputting the subject's name or the like.

JP, 2003-339695, A

However, since the voice recognition process usually requires a predetermined time, it takes a certain time from the input instruction to the operation, and the operation instructed by the input may not be executed at the timing desired by the operator. For this reason, it is necessary to repeatedly speak in order to perform a desired operation. In addition, it is necessary to utter many times when performing fine operations such as fine adjustment. That is, the responsiveness to the operator's input instruction is low, the operation takes time, and the operation itself becomes complicated.
Therefore, it is an object of the present invention to provide a voice recognition input device capable of improving responsiveness to a voice input instruction and reducing the number of utterances required for operation.

The present invention has been made in view of the above circumstances, and an object thereof is to improve responsiveness to a voice input instruction and reduce the number of utterances required for operation.

In order to solve the above problems, the present invention provides the following means.
According to one embodiment of the present invention, a data acquisition unit that acquires predetermined data, temporarily stores the acquisition time of the data together with the data, and temporarily stores the data in a storage unit, receives a voice input, and receives the voice input. When the voice input time is temporarily stored in the storage unit and the voice input processing unit performs voice recognition processing on the voice input, and as a result of the voice recognition processing, the voice input matches a specific operation instruction. A voice recognition input device comprising: a voice input determination unit that outputs a command for performing a process in accordance with the operation instruction on the data stored incidentally at the acquisition time that is the same as the voice input time. I will provide a.

According to the present invention, it is possible to improve responsiveness to a voice input instruction and reduce the number of utterances required for operation.

It is a block diagram which shows schematic structure of the speech recognition input device which concerns on the 1st Embodiment of this invention. 6 is a flowchart showing a flow of a voice input process according to a storage instruction of an image captured by the image capturing device by the voice recognition input device of FIG. 1. FIG. 3 is a reference diagram showing an example of image data in the voice recognition input device of FIG. 1 and a data acquisition time associated with this and stored. FIG. 9 is a reference diagram showing an example of display times of image data read out by the voice recognition input device according to the second embodiment of the present invention and image data incidental to the image data. 9 is a flowchart showing a flow of voice input processing for position adjustment of a diaphragm frame of the image pickup device by the voice recognition input device according to the third embodiment of the present invention. FIG. 6 is a reference diagram showing an example of position information of a diaphragm frame in the voice recognition input device of FIG. 5 and position information acquisition times incidental to this and stored.

The voice recognition input device according to the embodiment of the present invention is for giving an input instruction to an external image pickup device or the like connected to the voice recognition input device, and includes a plurality of still images picked up by the image pickup device. Inputting to instruct desired processing such as displaying a desired image from an image, extracting and saving a desired image from a moving image, adjusting an aperture position when capturing an image in an image capturing device, etc. Is.

(First embodiment)
Hereinafter, the voice recognition input device according to the first embodiment of the present invention will be described in more detail with reference to the drawings. FIG. 1 shows a schematic configuration diagram of a voice recognition input device according to the present embodiment.
The voice recognition input device 10 includes a central processing unit (CPU) 11 that controls the entire voice recognition input device 10, a microphone 12 that receives voice input, a memory 13, and a magnetic disk 14. Each of these components is connected via a system bus. Connected to each other.

In addition, the voice recognition input device 10 is communicably connected to the image capturing device 20, issues various input instructions to the image capturing device 20, and acquires image data and the like from the image capturing device 20. The voice recognition input device 10 is connected to the display 30 via the image capturing device 20, and gives an instruction to display an image or the like acquired by the image capturing device 20 on the display 30.
As the image capturing device 20, hardware for acquiring a medical image such as an X-ray device, an MRI device, a CT device, and a PET device can be applied.

As shown in FIG. 1, the CPU 11 has the functions of the voice input processing unit 111, the data acquisition unit 112, and the voice input determination unit 113 in order to give a voice input instruction to the image capturing device or the like by the voice recognition input device 10. To achieve. Note that the functions of the voice input processing unit 111, the data acquisition unit 112, and the voice input determination unit 113 realized by the CPU 11 are realized as software by the CPU 11 reading and executing a program previously stored in a memory such as the magnetic disk 14. Can be realized. Note that part or all of the operations executed by the respective units included in the CPU 11 can be realized by an ASIC (application specific integrated circuit) or an FPGA (field-programmable gate array).

The voice input processing unit 111 temporarily stores the voice input time at which the voice input is received in the memory 13 for the voice input through the microphone 12, and performs a known voice recognition process with the voice input as a recognition target. And outputs the recognition result to the voice input determination unit 113.

The data acquisition unit 112 acquires predetermined data from the image capturing device 20 connected to the voice recognition input device 10, attaches the acquired time together with the acquired data, and temporarily stores the acquired data in the memory 13. In the present embodiment, image data obtained by continuous image capturing such as X-ray fluoroscopy is acquired by the image capturing device 20. Note that the data acquisition unit 112 causes the display 30 to simultaneously display the acquired image data when temporarily storing the image data in the memory 13. As a result, it is possible to support the operator's storage instruction regarding desired image data.

The voice input determination unit 113 determines whether the voice input time stored in the memory 13 is the same as the voice input time when the result of the voice recognition process for the voice input acquired from the voice input processing unit 111 matches a predetermined operation instruction. A command for performing processing according to an operation instruction related to voice input is output for the data stored incidentally to the data acquisition time.

In the present embodiment, for example, when a specific image data is desired to be stored as a still image during a period in which images are continuously captured under fluoroscopy, “save” is set as a predetermined operation instruction. Define it. As a result, when the voice input is stored, the voice input determination unit 113 outputs a command to store the image data stored in the memory 13 at the same time as the voice input time in the magnetic disk 14. To do.

The microphone 12 receives the utterance of the operator as a voice input, converts the voice into an electric signal, and outputs the electric signal to the voice input processing unit 111.
The memory 13 stores programs executed by the CPU 11 and the progress of arithmetic processing, various data such as image data read from the image pickup device 20, the time when the various data are acquired, and voice input instructions. The received input instruction time is temporarily set aside according to an instruction from the CPU.

The magnetic disk 14 stores a program executed by the CPU 11 and data necessary for executing the program. Further, the magnetic disk 14 stores image data read from the image pickup device 20. As the magnetic disk 14, for example, a device capable of exchanging data with a portable recording medium such as a CD/DVD such as a hard disk, a USB memory, or an SD card can be applied.

The flow of the voice input process related to the instruction to save the image captured by the image capturing device 20 by the voice recognition input device 10 configured as described above will be described below with reference to the flowchart of FIG.

As shown in FIG. 2, when the image capturing apparatus 20 starts continuous image capturing by X-ray fluoroscopy or the like, the data acquiring unit 112 starts acquiring image data from the image capturing apparatus 20 in step S101. At this time, the data acquisition unit 12 temporarily stores the image data in the memory 13 together with the image data and the data acquisition time when the image data was acquired, as shown in FIG. At this time, the data acquisition unit 112 causes the display 30 to display the acquired image data simultaneously with the acquisition of the image data. This allows the operator to give an image saving instruction for a desired image while referring to the display 30.

In the next step S102, the voice input processing unit 111 determines whether or not there is voice input through the microphone 12, and when it is determined that there is no input instruction, during the period in which image data acquisition continues. Repeats the process of step S102. When the voice input processing unit 111 determines that there is voice input, the process proceeds to step S103, the voice input time is temporarily stored in the memory 13 as the voice input time, and the voice recognition process is performed (step S104). ..

In the next step S105, the voice input determination unit 113 determines whether or not the voice input is an image saving instruction as a result of the voice recognition processing performed by the voice input processing unit 111. As a result of the determination, when the voice input is the image saving instruction, the process proceeds to step S106, and when the voice input is not the image saving instruction, the process proceeds to step S108.

In step S<b>106, the voice input determination unit 113 outputs a command for saving the image data stored at the data acquisition time coincident with the voice input time on the magnetic disk 14. In the present embodiment, since the voice recognition input device is provided with the magnetic disk 14, the CPU 11 obtains the voice input from the image data acquired from the image capturing device 20 by the data acquisition unit 112 and temporarily stored in the memory 13. The image data stored at the data acquisition time coincident with the time is stored in the magnetic disk 14. Then, the process proceeds to step S107, the voice input time temporarily stored in the memory 13 at step S103 is deleted, and the process proceeds to step S108.

In step S108, it is determined whether the acquisition of the image data is completed, that is, whether the image capturing apparatus 20 has completed the continuous image capturing by X-ray fluoroscopy. The image data temporarily stored in the memory 13 and the data acquisition time stored in association with the image data are erased, and the voice input process ends.

As described above, according to the present embodiment, the voice input time at which the voice input according to the image storage instruction by the operator is performed is stored, and in parallel with this, the data acquisition unit acquires the data when acquiring the image data. The time is stored together with the image data. Therefore, by collating the voice input time and the data acquisition time, it is possible to immediately extract the image data for which the operator has instructed to save the image. Therefore, it is possible to accurately save the image that the operator wants to save, at the designated timing and with a small number of utterances. That is, it is possible to realize a highly responsive voice recognition input device in which the operation desired by the operator can be executed quickly and accurately, and the number of utterances required for the operation is reduced.

(Modification)
In the voice recognition input device 10 described above, an example in which specific image data is saved by a voice input instruction by the operator's utterance has been described, but the present invention is not limited to this. It is also possible to save all the image data during the period from the start of saving to the end of saving by making two instructions.
By doing so, it is possible to accurately save all the image data that the operator wants to save at the instructed timing and with a small number of utterances.

(Second embodiment)
In the present embodiment, the image data is simultaneously displayed on the display 30 while continuously acquiring the image data from the image capturing device 20, or the image data already stored in the memory 13 or the magnetic disk 14 is continuously displayed 30. In the case of displaying on the screen, for example, it is possible to perform an operation desired by the operator by voice input, such as advancing the image, returning the image, and advancing or delaying the time for turning the image.

In this case, when the voice input processing unit 111 stores the voice input time in the memory 13 together with the voice input by the operator, and the data acquisition unit 112 reads (acquires) and displays the image data, it is being displayed. The image data and the display time of are stored temporarily in the memory 13 (see FIG. 4). Thereby, for example, when the display stop instruction is given by the operator, it is possible to cause the display 30 to display the image data corresponding to the display time corresponding to the voice input time according to the display stop instruction.

(Third Embodiment)
In the present embodiment, a voice when the voice input device is connected to the image capturing device 20 having an X-ray diaphragm, and a voice when adjusting the X-ray aperture position when capturing an image in the image capturing device 20. The input process will be described. Since the voice recognition input device 10 according to the present embodiment has the same configuration as the voice recognition input device according to the first embodiment described above, the same components are designated by the same reference numerals, and the description of each component will be omitted. To do.

The position of the X-ray diaphragm frame can be adjusted according to the voice input, and for example, any one side of the X-ray diaphragm frame can be moved, both upper and lower sides, both left and right sides, and all four sides can be simultaneously moved. The moving directions can be arbitrarily adjusted by appropriately combining the moving direction and the narrowing direction of the X-ray diaphragm frame. The operator starts moving the designated side in the designated direction in response to the voice input to start the movement, and the X-ray diaphragm frame is stopped again in response to the voice input to stop the operator.

The flow of voice input processing for adjusting the position of the aperture frame of the image pickup device 20 by the voice recognition input device 10 will be described below with reference to the flowchart of FIG.
When the operator inputs a voice to start moving the diaphragm frame, the designated side starts moving in the designated direction through the voice recognition process, that is, the diaphragm frame adjusting operation starts.

As shown in FIG. 5, when the adjustment operation of the aperture frame of the image capturing apparatus 20 is started, the data acquisition unit 112 causes the display 30 to display the position of the aperture frame of the image capturing apparatus 20 and the aperture frame of the image capturing apparatus 20 in step S201. Start acquisition of location information (data). By displaying the position of the diaphragm frame on the display 30, the position of the diaphragm frame can be adjusted on the display. Then, when acquiring the aperture position information, the data acquisition unit 12 temporarily stores the position information in the memory 13 together with the position information of the aperture frame and the position information acquisition time when the position information was acquired, as shown in FIG.

In the next step S202, the voice input processing unit 111 determines whether or not there is voice input through the microphone 12, and when it is determined that there is no input instruction, during the period during which the acquisition of image data continues. Repeats the process of step S202. When the voice input processing unit 111 determines that there is a voice input, the process proceeds to step S203, the voice input time is temporarily stored in the memory 13 as the voice input time, and the voice recognition process is performed (step S204). ..

In the next step S205, the voice input determination unit 113 determines whether or not the voice input is a diaphragm frame movement stop instruction as a result of the voice recognition processing performed by the voice input processing unit 111. As a result of the determination, if the voice input is the aperture frame movement stop instruction, the process proceeds to step S206. If the voice input is not the aperture frame movement stop instruction, the process proceeds to step S208.

In step S<b>206, the voice input determination unit 113 outputs to the image capturing apparatus 20 the position information that is stored incidentally at the position information acquisition time that matches the voice input time. In the present embodiment, out of the position information temporarily stored in the memory 13 by the data acquisition unit 112, the position information additionally stored at the position information acquisition time that matches the voice input time is output to the image capturing apparatus 20. To do. Then, the process proceeds to step S207, the voice input time temporarily stored in the memory 13 at step S203 is deleted, and the process proceeds to step S208.

In step S208, it is determined whether or not the acquisition of the image data has been completed, that is, whether or not the image capturing apparatus 20 has completed the continuous image capturing by X-ray fluoroscopy. The image data temporarily stored in the memory 13 and the data acquisition time stored in association with the image data are erased, and the voice input process ends.

As described above, according to the present embodiment, the voice input time at which the voice input regarding the position adjustment of the aperture frame is performed by the operator is stored, and in parallel with this, the data acquisition unit acquires the position information of the aperture frame. The position information acquisition time is stored together with the position information when performing. Therefore, by collating the voice input time with the position information acquisition time, the position information when the operator gives the stop frame stop instruction can be immediately extracted. Therefore, the position information of the aperture frame that the operator wants to determine can be accurately output to the image pickup device 20 with a small number of utterances. That is, it is possible to realize a highly responsive voice recognition input device in which the operation desired by the operator can be executed quickly and accurately and the number of utterances required for the operation is reduced.
The voice recognition input device described above not only performs input related to operations such as storage or display of a desired image and adjustment of the position of the aperture frame, but also input related to operations such as movement of a bed provided in the image capturing apparatus. You can also do it.

10... Voice recognition input device, 11... CPU, 12... Microphone, 13... Memory, 14... Magnetic disk, 111... Voice input processing unit, 112... Data acquisition unit , 113... Voice input determination unit, 20... Image pickup device, 30... Display

Claims (4)

A data acquisition unit that acquires predetermined data, attaches the acquisition time of the data together with the data, and temporarily stores the data in a storage unit;
A voice input processing unit that receives voice input, temporarily stores the voice input time when the voice input is received in the storage unit, and performs voice recognition processing for the voice input;
As a result of the voice recognition process, when the voice input matches a specific operation instruction, a process according to the operation instruction is performed on the data stored incidentally at the acquisition time at the same time as the voice input time. A voice recognition input device, comprising: a voice input determination unit that outputs a command for execution. The data is image data continuously acquired by an external image pickup device,
The data acquisition unit accompanies the acquisition time of the image data together with the image data and temporarily stores it in the storage unit,
The voice input determination unit stores the image data stored in association with the acquisition time at the same time as the input instruction time when the operation instruction related to the voice input is an image storage instruction. The voice recognition input device according to claim 1, which outputs a command. The data is image data continuously acquired by an external image pickup device,
While the data acquisition unit displays the image data on the display device while acquiring the image data, the acquisition time of the image data is additionally stored and temporarily stored in the storage unit,
When the operation instruction related to the voice input is an image display, the voice input determination unit displays on the display device the image data stored in association with the acquisition time at the same time as the voice input time. The voice recognition input device according to claim 1, which outputs a command for causing the input. The data is position information of an aperture frame in an external image pickup device,
The data acquisition unit continuously acquires the position information, and temporarily stores the position information in the storage unit with the acquisition time of the position information.
When the operation instruction related to the voice input is a movement stop instruction of a diaphragm frame, the voice input determination unit stores the position information additionally stored at the acquisition time that is the same time as the voice input time. The voice recognition input device according to claim 1, wherein the voice recognition input device outputs the image recognition device.

Images