JPH05200052A - Voice controller for microscope used in operation - Google Patents

Abstract

PURPOSE:To enable a voice range to be clearly recognized in an unknown noise condition at the time of undertaking an operation. CONSTITUTION:The directivity axis (d) of an input microphone 17 fitted to a mirror body 8 is directed toward an operator's mouth, and a vibration probe 18 is kept close to the operator's throat. A relay 24 is provided in connection between the microphone signal input section 21 of a voice controller and a speech recognition device 26, and a relay control signal is outputted from a vibration detecting circuit 27, only while a vibration signal is being inputted from the probe 18, thereby energizing the relay 24.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice for an operating microscope, which recognizes a voice produced by an operator or the like and automatically controls the operation of each drive unit of the operating microscope used in the medical field. Regarding the controller.

[0002]

2. Description of the Related Art In recent years, with the development of surgical techniques and surgical tools, so-called microsurgery, which is a surgical operation on a minute affected area, has been frequently performed. As a microsurgery, a surgical microscope for magnifying and observing a surgical site is used, as shown in, for example, neurosurgery and orthopedic / plastic surgery. In microsurgery, the surgeon may use surgical instruments such as bipolar and electric scalpels operated by a foot switch in addition to surgical forceps such as scissors, tweezers, and a scalpel. In such a case, Both hands and feet are often blocked. Furthermore,
Operating inputs such as magnification change, focus adjustment, and body movement of the surgical microscope are usually performed with foot switches, so the number of foot switches increases, and various foot switches can be operated quickly and accurately during surgery. There was a problem that it was difficult to do. Therefore, there is a growing need to use a voice controller that can automatically control each drive unit by voice recognition based on the voice uttered by the operator, etc. Is coming.

Although the voice controller used in the above-mentioned surgical environment is required to have high reliability and safety, the recognition means of the voice recognition device incorporated in the voice controller generally uses a statistical method. Because
It is difficult to obtain a recognition rate of 100%. In particular, in order to maintain a high recognition rate in situations where a high noise level may always occur, such as during surgery, it is a very important factor to accurately detect the voice section from the input sound. Is becoming.

An example of application of a voice recognition device to a surgical microscope is disclosed in Japanese Patent Application Laid-Open No. 62-166312, and in the present invention, the operation unit of each operation unit caused by erroneous recognition of the voice recognition device is disclosed. For the main purpose of preventing malfunctions, only the switching of the operation mode of the multifunction switch by the foot switch or the like is switched by the voice recognition device by using the voice of the operator or the like. Then, the actual driving thereafter is performed by stepping on the foot switch after confirming the switching of the operation mode by the operator or the like, thereby reducing the number of contacts of the foot switch.

Further, as an example in which a voice controller is used for operation input of a surgical microscope, US Pat.
There is one described in No. 53. This invention mainly aims to prevent overrun of the drive unit and to make an emergency stop when the drive unit malfunctions, and while the drive unit of the surgical microscope is being driven,
A technique is disclosed in which, when an audio signal exceeding a certain threshold is input to a voice input microphone of a voice controller, the driving of the audio signal is stopped.

Generally, in a voice recognition device, the detection of a voice section is judged by whether or not the power spectrum of an acoustic signal input by one microphone exceeds a threshold value. Another detection means has been developed as described in the Institute of Information and Communication Engineers (A Vol.J-73-A No.8 PP.1391 to 1398). That is, in this voice recognition device, a plurality of microphones (microphone arrays) are used to suppress ambient noise including sudden noise based on the acoustic signal input to each microphone to detect the voice section of the speaker. It can be effectively performed under noise.

[0007]

However, these conventional devices have various problems when the actual surgical environment is taken into consideration. That is, the technique of inputting an acoustic signal equal to or higher than a threshold value to the microphone to stop the driving of the driving unit in US Pat. No. 4,989,253 stops driving if sudden noise or the like is input during driving of the driving unit. In such a case, the operation may not be performed smoothly. Further, in the voice section detecting means using a single microphone, when a large volume noise generated by a surgical instrument such as a bipolar or electric scalpel or an aspirator is input from the microphone, the level of its power spectrum is a predetermined threshold. When the value exceeds the value, there is a problem in that the voice section may be detected by mistakenly recognizing the voice of the operator, that is, voice recognition may not be performed, and the voice section may not be accurately detected.

Further, the voice section detection method using a microphone array in the paper of the Institute of Electronics, Information and Communication Engineers has a drawback that it has no effect of suppressing noise emitted from a position close to the operator. For example, as shown in FIG. 10, at the time of surgery, in the vicinity of a surgeon 2 who performs surgery while using the microscope body 1 of the surgical microscope, a nurse 3 who hands surgical forceps or the like to the surgeon 2, or a side An assistant 6 or the like who operates the suction device 5 or the like while looking into the endoscope 4 and assists surgery such as suction is working. Therefore, the voices and noises emitted by the nurse 3 and the assistant 6 are emitted from a position relatively close to the operator, so that the voice section of the operator's voice may not be accurately detected.

As described above, in the conventional voice controller for a surgical microscope, in a situation where an unknown noise is generated from an unknown place such as in a surgical environment, the voice section emitted by the operation instructor is always properly detected, It is difficult to obtain a high recognition rate. Therefore, accurate recognition may not be performed, for example, when recognition is not performed, recognition is performed, or conversely, when noise is input and recognition is not required, recognition is performed. Therefore, due to these erroneous recognition, there is a problem that the drive part does not move in the direction intended by the operator during the operation, which may cause the operation to take a long time and input to the voice controller. Due to the malfunction of each drive unit due to the generated noise,
The drive part may start moving in an unintended direction. For example, if a patient needs urgent treatment due to heavy bleeding,
There is a risk that the safety of surgery will be significantly impaired, such as the occurrence of focus shift and field shift resulting in inability to perform appropriate treatment.

To solve such a problem, Japanese Patent Laid-Open No. 62-16
Japanese Patent No. 6312 proposes a method of switching only the mode of a multifunction switch in a voice recognition device in order to improve the safety of operation by voice recognition. However, in this method, the drive unit selected in the voice recognition device is changed. When driving, the foot switch must be operated with the foot, etc., and the operability is significantly reduced despite the use of the voice recognition device, and the cost increases due to the installation of the voice recognition device. is there.

In view of the above problems, an object of the present invention is to provide a voice controller for a surgical microscope capable of obtaining a high voice recognition rate in an environment where unknown noise may occur during surgery. To do.

[0012]

A voice controller for a surgical microscope according to the present invention is provided with at least one acoustic input means for inputting recognition voice to an operating microscope provided with one or more driving means and an input. In a surgical microscope having a voice controller having a voice recognition unit for recognizing the generated voice, the driving unit is driven by the voice, and vibration due to the utterance is detected in order to detect a generation section of the recognition voice. It is characterized by having a vibration detecting means.

[0013]

When the speaker emits an instruction voice for operating the driving means, an acoustic signal is input from the acoustic input means. At the same time, vibration of the vocal cord due to the utterance of the speaker is detected by the vibration detecting means. As a result, the voice section in the acoustic signal is accurately detected, the acoustic signal in this section is transmitted to the voice recognition means as a recognition voice, and the drive means is operated based on the recognition result.

[0014]

Embodiments of the present invention will be described below with reference to the drawings. 1 to 3 show a first embodiment of the present invention, FIG. 1 is a diagram showing a surgical microscope and a surgeon during surgery, and FIG. 2 is an enlarged view of a body portion of FIG. FIG. 3 is a block diagram of the voice controller. In FIG. 1, in a surgical microscope 7, a mirror body 8 is attached to a free end of an arm portion 10 pivotally attached to an upper end portion of a pedestal 9. The arm portion 10 has a first arm 11 that is held rotatably with respect to the gantry 9 about an axis a, and is rotatable with respect to the first arm 11 about an axis b and has an axis b. It comprises a second arm 13 which is rotatable with respect to the member 12 about an axis c (direction perpendicular to the plane of the drawing). Further, the arm portion 10 is configured to be electrically rotatable about each of the axes a, b, and c by an arm driving mechanism (not shown). Thereby, the mirror body 8 can be electrically moved to a desired position in the three-dimensional space. Further, an electric focus adjusting mechanism and an electric zoom mechanism (not shown) are built in the mirror body 8, and each control unit of the arm driving mechanism, the electric focus adjusting mechanism and the electric zoom mechanism is built in the gantry 9. There is.

An input microphone 17, which is a directional microphone, is fixed to the tip of the microphone arm 16 attached to the mirror body 8 (see FIG. 2), and the directional axis d of the input microphone 17 is set in a desired direction. So that the microphone 17 can be fixed at the position facing the microphone arm 1
6 is provided with a ball joint mechanism (not shown). Further, a detachable vibration probe 18 for detecting vibration of the throat (vocal cord) when the operator makes a voice is closely attached to the throat of the operator 2. The input microphone 17 is connected to the microphone signal input unit 21 of the voice controller 20 attached to the gantry 9 via the microphone wire 17a (see FIG. 3), and the acoustic signal collected by the input microphone 17 is transmitted. Further, the vibration probe 18 is connected to the vibration probe signal input section 22 of the voice controller 20 via the vibration probe wire 18a so that the vibration signal detected by the vibration probe 18 is transmitted.

In the voice controller 20 shown in FIG. 3, the microphone signal input section 21 is directly connected to the input side contact of the relay 24, and the output side contact thereof is connected to the voice input section of the voice recognition device 26 via the amplifier 25. Therefore, the voice recognition device 26 performs the recognition process based on the voice signal. The vibration probe signal input unit 22 is connected to the coil side of the relay 24 via the vibration detection circuit 27. The vibration detection circuit 27 outputs a relay control signal from the output section to make the relay 24 conductive only when the input vibration signal exceeds a predetermined threshold value.
Further, the control host CPU 28 of the voice recognition device 26 outputs a control signal of the drive control unit corresponding to the recognition result by the voice recognition device 26, and parallel I / O with the voice recognition device 26. Are connected, and data such as various commands and recognition results are exchanged. The signal output unit of the control host CPU 28 is connected to the control signal output unit 29 provided on the surface of the voice controller 20, and the control signal output from the control host CPU 28 is transmitted via the control signal input unit 30 to the mount 9. It is input to the decoder 31 built in the. On the output side of the decoder 31, each drive control unit, that is, the arm drive mechanism control unit 32, the electric focus adjustment mechanism control unit 33, and the electric zoom mechanism control unit 34.
Are connected to each other by cables, and host CPU for control
Drive control is performed in response to a signal input from 28.

The present embodiment has the above-mentioned structure, and the operation will be described below. First, the surgeon 2 operates the ball joint portion of the microphone arm 16 in advance before the surgery, and the directional axis d of the input microphone 17 is set to the mouth of the surgeon 2 standing at a predetermined surgical position when the surgical microscope 7 is in use. Adjust to face. Further, the vibration probe 18 is attached so as to be in close contact with the throat of the operator 2. During operation, when the surgeon 2 is not uttering voice and noise of a nurse, an assistant, or a surgical instrument such as a suction device is input as an acoustic signal to the input microphone 17, these acoustic signals are input to the microphone signal input unit. 21 is transmitted. However, since the vibration probe 18 does not detect the vibration signal exceeding the threshold value, the vibration detection circuit 27 does not output the relay control signal, and the relay 24 is maintained in the open state, that is, the OFF state. Therefore, the drive control units 32 to 34 do not malfunction.

Next, when the operator 2 utters a voice for operating instructions, for example, "zoom up", this is input as an acoustic signal through the input microphone 17 and transmitted to the microphone signal input section 21. At the same time, the vocal cord vibration of the surgeon 2 at that time is transmitted to the vibration probe 18 and detected as a vibration signal, which is converted into an electric signal and input to the vibration detection circuit 27 via the vibration probe signal input unit 22. It Then, when this electric signal exceeds a predetermined threshold value, a relay control signal is instantaneously output from the vibration detection circuit 27, and the relay 24 is turned ON. This relay control signal is
The electric signal continues to be output until a predetermined time elapses after the electric signal falls below the threshold value within a range not exceeding the predetermined maximum time.

Therefore, during that time, a voltage is applied to the coil side of the relay 24, so that the contact of the relay 24 becomes conductive and is maintained in that state, so that the input microphone 17 recognizes voice through the amplifier 25. It is connected to the device 26. Therefore, the input voice signal “zoom up” is converted into an electric signal by the input microphone 17, amplified by the amplifier 25, input to the voice recognition device 26, and subjected to recognition processing by the voice recognition device 26. Then, the signal of the recognition result corresponding to “zoom up” is output to the control host CPU 28.

Based on the received recognition result, the control host CPU 28 outputs a control signal corresponding to the signal, that is, an up signal to the electric zoom mechanism control section 34 in this example. The output control signal is input to the decoder 31 via the control signal output unit 29 and the control signal input unit 30 in the gantry 9, and the decoder 31 selects the electric zoom mechanism control unit 34 to send out a signal. Do not drive the electric zoom mechanism. In this way, the drive control desired by the operator 2 can be automatically achieved by voice. After the utterance of the operator 2 is completed, the vibration detection circuit 27 is turned off and the relay control signal is cut off after a predetermined time elapses, and the relay 24 is opened, that is, turned off, and the microphone input is disabled.

Also, when the arm drive mechanism control unit 32 and the electric focus adjustment mechanism control unit 33, which are other drive control units, are driven, if the operator 2 similarly indicates by voice, the control is performed in the same procedure. Can be achieved.

As described above, in the present embodiment, when the operator 2 makes a voice, it can be detected immediately, the voice section can be accurately identified and cut out, and the recognition rate of the voice recognition device 26 can be improved. It is possible to improve the operability of the operating microscope 7 and shorten the operating time. Moreover, even if a large noise from a surgical instrument such as an aspirator or a bipolar device, or a voice of a nurse or an assistant is input from the input microphone 17 while the operator 2 does not emit a voice, the voice recognition device 2
It is possible to prevent these signals from reaching up to 6.
Therefore, it is possible to prevent the voice recognition device 26 from erroneously recognizing the voice section by cutting out the voice section using these noises as the instruction voice.
The reliability of voice control and the safety of surgery are greatly improved.
Moreover, the structure of the voice controller 20 is relatively simple, and the manufacturing cost can be reduced.

Next, a second embodiment of the present invention will be described with reference to FIGS.
However, the same parts or members as those in the above-described first embodiment are designated by the same reference numerals, and the description thereof will be omitted. FIG. 4 is a view showing a surgical microscope and a surgeon during surgery, FIG. 5 is an enlarged view of a mirror portion of FIG. 4, and FIG. 6 is a block diagram of a voice controller. In the surgical microscope 36 shown in FIGS. 4 and 5, the arm portion 3 attached to the gantry 9
An XY device 38 for electrically finely moving the mirror body 8 in the XY direction is attached to the free end of the mirror body 7, and the mirror body 8 is fixed below the XY device 38. A means for controlling a drive mechanism (not shown) of the XY device 38 is built in the gantry 9 as the XY device drive control unit 39 together with the electric focus adjustment mechanism control unit 33 and the electric zoom mechanism control unit 34 ( (See FIG. 6).

In addition to the input microphone 17, the noise input microphone 42, which is a directional microphone, is attached to the mirror body 8 via the microphone arm 41, and the microphone arm 41 has a noise input microphone 42.
The microphone 42 is fixed by a ball joint mechanism or the like so that its directional axis e is directed to the operation part E direction. The noise input microphone 42 is connected to the noise signal input unit 44 of the voice controller 43 attached to the gantry 9 by the microphone wire 42a, and the suction device, the electric scalpel, and the like collected by the noise input microphone 42 are operated. The sound signal of the instrument or the like is transmitted to the voice controller 43.

Further, the voice controller 43 shown in FIG.
In the audio signal input section 21 and the noise signal input section 44,
Is connected to a differential amplification circuit 45. In the differential amplification circuit 45, from the acoustic signal including the voice signal of the operator 2 and various noise signals input from the input microphone 17,
An acoustic signal component, which is a noise component uttered in the vicinity of the surgical site E, which is input by the noise input microphone 42, is removed. The output end of the differential amplifier circuit 45 is connected to the input side contact of the relay 24, and the output side contact is the voice recognition device 26.
Connected to the voice input section of. Also, control host CP
A decoder 46 is connected between the U 28 and its control signal output unit 29, and an output signal from the control host CPU 28 is converted into a control signal for each drive control unit 39, 33, 34 by the decoder 46 and output. It is supposed to be done.
The control signal input section 30 in the gantry 9 is connected to the XY device drive control section 39, the electric focus adjustment mechanism control section 33, and the electric zoom mechanism control section 34 by a cable.

Since the present embodiment is constructed as described above, the input microphone 17 is adjusted before the operation so that the directivity axis d is directed toward the operator's mouth, and the noise input microphone 42 is adjusted to the directivity axis. It is adjusted so that e is oriented in the direction of the operation part E where observation and treatment are performed. During the operation, the voice generated by the operator 2 and ambient noise including noise generated by a surgical instrument such as an aspirator or a bipolar device near the surgical site E are input as acoustic signals from the input microphone 17, while
Noise generated mainly near the surgical site E is input to the noise input microphone 42 as an acoustic signal. The acoustic signals input from the microphones 17 and 42 are input to the differential amplifier circuit 45 via the signal input units 21 and 44 of the voice controller 43. Then, from the acoustic signal from the input microphone 17, the acoustic signal from the noise input microphone 42, that is, the noise component uttered near the surgical site is removed and amplified.

The differential acoustic signal processed in this manner is input to the relay 24, but like the first embodiment described above,
When the surgeon 2 is making a voice, the vibration detection circuit 27 controls the relay 24 to be in a conductive state, and the relay 24 is passed through the relay 24 to be input to the voice recognition device 26. Then, recognition processing is performed by the voice recognition device 26, and the control host CPU 28
The recognition result is output to. Further, the decoder 46 converts the control signals of the drive control units 39, 33, and 34, and the operator 2
A desired type of drive control is performed in accordance with the instruction voice.

As described above, in this embodiment, since the noise input microphone 42 is fixed toward the surgical site E, the surgical site E
Since a large level of noise such as the aspirator and bipolar generated in step 2 can be removed before the voice recognition, even when performing voice input while using these surgical instruments,
The noise generated by them can be canceled. for that reason,
Due to the noise generated by these surgical instruments, the voice recognition device 26
Will not be erroneously recognized, and the reliability of voice recognition will be improved. Particularly, in the present embodiment, voice input is possible without interrupting the operation of these surgical instruments, the operation time can be further shortened, and the operability is also improved.

Further, instead of or in addition to the noise input microphone 42, if another noise input microphone is attached to the side endoscope used by the assistant, the voice uttered by the assistant or the like is also input to the input microphone 17 It is possible to remove it from the acoustic signal input to the.

Next, a third embodiment of the present invention will be described with reference to FIGS.
However, the same reference numerals are used for the same parts or members as those in the above-described embodiment, and the description thereof will be omitted. 7 is a diagram showing a surgical microscope and an operator during surgery, FIG. 8 is a block diagram of a transmitter, and FIG. 9 is a block diagram of a voice controller. In the surgical microscope 48 shown in FIG.
A vibration probe 49 having the same function as that of the first embodiment is closely held at the throat of the operator 2, and the vibration probe 49 is transmitted by a transmitter 50 via a vibration probe wire 49a.
It is connected to the. The transmitter 50 is attached to a position such as the waist of the operator 2 that does not interfere with the operation.
In the transmitter 50 shown in FIG. 8, the vibration probe wire 4
9a is connected to the vibration detection circuit 51, and this circuit 5
In No. 1, the vibration detection signal is issued when the electric signal related to the vibration signal exceeds the predetermined threshold value.
Further, the vibration detection circuit 51 is connected to a voicing signal generation unit 52 that outputs a signal while the vibration detection signal is being output, and the voicing signal generation unit 52 is connected to a transmission window 53 for transmitting a wireless signal.

Further, the voice controller 55 shown in FIG.
In, the reception window 56 for receiving the signal from the transmission window 53 is connected to the reception signal processing unit 57. Upon receiving the signal, the reception signal processing unit 57 applies a voltage as a relay control signal to the coil side of the relay 24, and the relay 2
4 is made to conduct. Also, control host C
The PU 28 controls the control signal generation unit 58 that converts the recognition result into foot switch signals corresponding to the drive control units 32 to 34.
The control signal generation unit 58 is connected to the foot switch signal input unit 60 provided on the gantry 9 via the control signal output unit 59. The foot switch signal is a signal for driving the drive control units 32 to 34 emitted from the foot switch in the conventional device using the foot switch.

Since the present embodiment is configured as described above, when the operator utters a voice for instruction, for example, "focus up" at the time of surgery, the acoustic signal is sent to the voice controller 55 via the input microphone 17. Is entered. Moreover, the vocal cord vibration of the surgeon 2 at that time is detected by the vibration probe 49, converted into an electric signal, and input to the vibration detection circuit 51 in the transmitter 50. Then, when this electric signal exceeds the predetermined threshold value, the vibration detection signal instantly rises and is output to the vocalization signal generation unit 52. Moreover, the vibration detection circuit 51 continues to output the vibration detection signal until the predetermined time after the electric signal falls below the threshold value within a range not exceeding the predetermined maximum time. In the utterance signal generation unit 52, while the vibration detection signal is being output, the transmitter 5
A wireless signal is output from the transmission window 53 of 0 to the reception window 56 of the voice controller 55.

The reception signal processing section 57 of the voice controller 55 outputs a relay control signal to the coil side of the relay 24 while the reception window 56 receives the signal. Therefore,
Only when the vibration detection signal is output, the contact of the relay 24 becomes conductive, and the acoustic signal “focus up” input from the input microphone 17 is transmitted to the amplifier 2
5 is input to the voice recognition device 26.
Then, the vibration detection signal output from the vibration detection circuit 51 is turned off after a lapse of a predetermined time after the end of utterance, and the relay 24
Is also turned off.

The voice signal of the operator 2 passing through the relay 24 when the relay 24 is conducting is subjected to recognition processing by the voice recognition device 26, and the recognition result is output to the control signal generator 58 via the control host CPU 28. To be done. Then, the control signal generation unit 58 uses the received recognition result as the drive control unit 3
2 to 34 are converted into foot switch signals, and the drive control units 32 to 34, the electric focus adjustment mechanism control unit 33 in this embodiment, are driven via the generated signal output unit 59 and the foot switch signal input unit 60. Control.

As described above, in this embodiment, the vibration probe 4
By making 9 wireless, surgeon 2 and surgical microscope 4
8 is physically separated. For example, the surgical microscope 48 is temporarily removed and macroscopic treatment such as blood pressure measurement and tomographic imaging at the time of blood vessel suturing is performed, and the surgical microscope 48 is again introduced after the treatment. In such a case, complicated work such as attachment and detachment of the vibration probe 49 becomes unnecessary, and the operation time can be shortened. Furthermore, the vibration probe 4
9. Since there is no risk of the vibration probe wire 49a and the transmitter 50 touching the clean area, they do not need to be sterilized. Further, since the control signal of each drive mechanism supplied to each drive mechanism control section 32 to 34 is made common with the foot switch signal, this embodiment is applied to the surgical microscope in which each drive mechanism is conventionally drive-controlled by the foot switch. When adopting the device according to, there is no need to install a new interface,
It has the advantage of being easy to retrofit and highly versatile.

In each of the above-mentioned embodiments, the mirror body portion 8
It is also possible to apply a sterile drape for sterilization, and there is no problem in maintaining a clean state. Further, the object controlled by the drive control unit is not limited to the mechanism of the above embodiment. The drive control section and the drive mechanism respectively constitute drive means.

[0037]

As described above, the surgical microscope voice controller according to the present invention is provided with the vibration detecting means for detecting the vocalization section of the speaker. It is possible to accurately detect the voice section uttered by a person, improve the recognition rate of the instruction voice, and shorten the operation time. Furthermore,
Therefore, since the malfunction due to noise can be suppressed and the safety of the operation of the voice controller for the surgical microscope can be improved, there is also a practically important advantage that the safety of the surgery can be improved.

[Brief description of drawings]

FIG. 1 is a schematic view showing a surgical microscope and an operator according to a first embodiment of the present invention.

FIG. 2 is an enlarged view of a mirror body portion of FIG.

FIG. 3 is a block diagram of a voice controller.

FIG. 4 is a schematic diagram showing a surgical microscope and an operator according to a second embodiment of the present invention.

5 is an enlarged view of the mirror body portion of FIG. 4. FIG.

FIG. 6 is a block diagram of a voice controller.

FIG. 7 is a schematic diagram showing a surgical microscope and an operator according to a third embodiment of the present invention.

FIG. 8 is a block diagram of a transmitter.

FIG. 9 is a block diagram of a voice controller.

FIG. 10 is a general view showing a state of surgery.

[Explanation of symbols]

 2 Operator 7,36,48 Microscope for operation 14,43,55 Voice controller 17 Input microphone 18,49 Vibration probe 26 Voice recognition device 32 Arm drive mechanism control unit 33 Electric focus adjustment mechanism control unit 34 Electric zoom mechanism control unit 39 XY drive mechanism controller

─────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] March 16, 1992

[Procedure Amendment 1]

[Document name to be amended] Statement

[Correction target item name] 0016

[Correction method] Change

[Correction content]

In the voice controller 20 shown in FIG. 3, the microphone signal input section 21 is directly connected to the input side contact of the relay 24, and the output side contact thereof is connected to the voice input section of the voice recognition device 26 via the amplifier 25. Therefore, the voice recognition device 26 performs the recognition process based on the voice signal. Further, the vibration probe signal input unit 22 is connected to the coil side of the relay 24 via the vibration detection circuit 27. The vibration detection circuit 27 outputs a relay control signal from the output section to make the relay 24 conductive only when the input vibration signal exceeds a predetermined threshold value.
Further, the control host CPU 28 of the voice recognition device 26 outputs a control signal of the drive control unit corresponding to the recognition result by the voice recognition device 26, and parallel I / O with the voice recognition device 26. Are connected, and data such as various commands and recognition results are exchanged. The signal output unit of the control host CPU 28 is connected to the control signal output unit 29 provided in the voice controller 20, and the control signal output from the control host CPU 28 is sent to the gantry 9 via the control signal input unit 30. It is input to the built-in decoder 31. To the output side of the decoder 31, each drive control unit, that is, the arm drive mechanism control unit 32, the electric focus adjustment mechanism control unit 33, and the electric zoom mechanism control unit 34 are connected by a cable, respectively, and input to a signal from the control host CPU 28. Drive control is performed accordingly.

[Procedure Amendment 2]

[Document name to be amended] Statement

[Name of item to be corrected] 0022

[Correction method] Change

[Correction content]

As described above, in the present embodiment, when the operator 2 makes a voice, it can be detected immediately, the voice section can be accurately identified and cut out, and the recognition rate of the voice recognition device 26 can be improved. It is possible to improve the operability of the operating microscope 7 and shorten the operating time. Moreover, even if a large noise from a surgical instrument such as an aspirator or a bipolar device, or a voice of a nurse or an assistant is input from the input microphone 17 while the operator 2 does not emit a voice, the voice recognition device 2
It is possible to prevent these signals from reaching up to 6. Therefore, the voice section is not erroneously recognized by the voice recognition device 26 by cutting out the voice section using these noises as an instruction voice, and the reliability of voice control and the safety of surgery are significantly improved. Moreover, the structure of the voice controller 20 is relatively simple, and the manufacturing cost can be reduced. ─────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] March 16, 1992

[Procedure Amendment 1]

[Document name to be corrected] Drawing

[Name of item to be corrected] Figure 3

[Correction method] Change

[Correction content]

[Figure 3]

[Procedure Amendment 2]

[Document name to be corrected] Drawing

[Name of item to be corrected] Figure 6

[Correction method] Change

[Correction content]

[Figure 6]

Claims (1)

[Claims] 1. A surgical microscope provided with one or more driving means is provided with a voice controller having at least one acoustic input means for inputting a recognition voice and a voice recognition means, and the drive means is driven by a voice. In a surgical microscope which is driven, a voice controller, comprising vibration detection means for detecting vibration due to utterance in order to detect a voice generation section.