JP6768323B2 - Speech recognition devices and methods, as well as computer programs and recording media - Google Patents

Description

The present invention relates to, for example, a voice recognition device and method for recognizing a voice command and switching modes between a plurality of modes, and a technical field of a computer program and a recording medium.

In medical settings, it may be required to be able to operate various devices without touching them. In response to such a request, for example, Patent Document 1 proposes a technique of manipulating a medical image with the line-of-sight position coordinates as a base point when a sound for performing an image manipulation is recognized.

JP-A-2015-93147

However, when the device is operated by recognizing the voice as in Patent Document 1, there is a possibility that an erroneous operation may be executed by the voice that is not intended to operate the device. For example, a word included in a normal conversation may be recognized as a voice command for operating a device, so that an unintended operation may be executed. In such a case, various inconveniences may occur due to improper operation of the device. In particular, in the medical field, safe and prompt treatment is required, and one erroneous operation may cause extremely great damage. The problems to be solved by the present invention include the above. Take as an example. An object of the present invention is to provide a voice recognition device and method capable of realizing accurate device operation by voice, and a computer program and a recording medium.

The voice recognition device for solving the above-mentioned problems is a first switching means for performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to the first voice command. In response to a second voice command different from the first voice command, a second switching means for switching the mode from the second mode to the first mode, and depending on the first mode or the second mode. It is provided with a display control unit for displaying the image on the display unit.

The second voice recognition device for solving the above problems has a first mode capable of responding to the first voice command and a second voice command different from the first voice command for switching to the first mode. It includes a second mode capable of responding only to the second mode, and a second switching means for switching the mode from the second mode to the first mode in response to the second voice command.

The voice recognition method for solving the above problems includes a first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to the first voice command. In response to a second voice command different from the first voice command, a second switching step of switching the mode from the second mode to the first mode and depending on the first mode or the second mode. It is provided with a display control step of displaying the image on the display unit.

A computer program for solving the above problems includes a first switching step of switching a mode between a plurality of first modes and switching a mode from the first mode to a second mode in response to a first voice command. A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command, and the first mode or the second mode are supported. A computer is made to execute a display control step of displaying an image on a display unit.

The computer program described above is recorded as a recording medium for solving the above problems.

It is a block diagram which shows the structure of the voice recognition apparatus which concerns on Example. It is a mode transition diagram which shows each mode which can be switched by the voice recognition apparatus which concerns on embodiment. It is a flowchart which shows the operation flow of the voice recognition apparatus which concerns on embodiment. It is a conceptual diagram which shows the mode switching method from a normal mode. It is a conceptual diagram which shows the mode switching method from a special mode. It is a conceptual diagram which shows the method of switching from a special mode to an arbitrary normal mode. It is a conceptual diagram which shows the partial display example of the normal mode in a special mode. It is a conceptual diagram which shows the method of switching from a normal mode to an arbitrary special mode.

<1>
The voice recognition device according to the present embodiment includes a first switching means for performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to the first voice command, and the above-mentioned. A second switching means for switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command, and an image corresponding to the first mode or the second mode. Is provided with a display control unit for displaying the image on the display unit.

According to the voice recognition device according to the present embodiment, during its operation, the first switching means switches between the plurality of first modes and switches the mode from the first mode to the second mode. The first switching means switches modes in response to the first voice command. The first voice command is preset for each mode as a voice command for switching to each mode.

Further, in the present embodiment, the mode switching from the second mode to the first mode is performed by the second switching means. The second switching means switches from the second mode to the first mode in response to the second voice command. The second voice command is preset as a voice command different from the first voice command.

The display control unit causes the display unit to display an image corresponding to the first mode or the second mode. Therefore, when the mode is switched by the first switching means and the second switching means, the image displayed on the display unit is also switched.

In this embodiment, in particular, in the first mode, it is possible to switch to each of the other modes by the first voice command. That is, from the first mode, it is possible to switch to another first mode by the first voice command, or to switch to the second mode by the first voice command. On the other hand, in the second mode, it is possible to switch to another mode only by the second voice command. That is, even if the first voice command is recognized in the second mode, the mode is not switched to another mode.

With this configuration, the method of switching from the second mode to another mode is limited. Therefore, if the switching from the second mode to the first mode is not intended, the mode is mistakenly switched to the first mode. It is possible to prevent switching from being performed. Specifically, it is possible to prevent an unintentionally emitted voice for mode switching from being recognized as a voice command for switching modes, resulting in inappropriate mode switching.

As described above, according to the voice recognition device according to the present embodiment, it is possible to realize suitable mode switching between the plurality of first modes and the second mode.

<2>
In one aspect of the voice recognition device according to the present embodiment, the display control unit displays a darkened image in the second mode.

According to this aspect, it is possible to prevent the darkened image displayed in the second mode from being unintentionally switched to the image corresponding to the first mode. By doing so, when the surroundings are dark (that is, the darkened image is displayed) and the work to be performed is performed, the surroundings are bright (the image corresponding to the first mode is displayed). It can be prevented from being lost.

A specific example of a situation in which a darkened image is displayed includes darkroom treatment (for example, fluorescence diagnosis) in a medical field.

<3>
In another aspect of the voice recognition device according to the present embodiment, in the second mode, the display control unit adds at least a part of the image corresponding to the first mode to a part of the image corresponding to the second mode. Is displayed.

According to this aspect, at least a part of the image corresponding to the first mode can be visually recognized even in the second mode. That is, even in the second mode, the information displayed in the other modes can be confirmed. Therefore, for example, even when a blackout image is produced in the second mode, the information shown in the first mode can be confirmed while keeping the surroundings in a relatively dark state.

<4>
In another aspect of the voice recognition device according to the present embodiment, the second switching means responds to the second voice command and performs mode switching to the first mode immediately before switching to the second mode.

According to this aspect, when switching from the second mode to the first mode is performed, the mode is switched to the first mode immediately before the switching to the second mode. In this way, the mode can be easily switched with respect to the plurality of first modes.

<5>
In another aspect of the voice recognition device according to this embodiment, the second voice command is a word or onomatopoeia that is unlikely to be issued in an environment in which the voice recognition device can be used.

According to this aspect, it is possible to prevent the second voice command from being unintentionally issued. Therefore, it is possible to effectively limit the switching from the second mode to the first mode. For "words that are unlikely to be uttered in an environment where a voice recognition device can be used", check the words that are uttered in an environment where a voice recognition device can be used in advance, and exclude words that are uttered frequently. And set it. Alternatively, words that have no meaning at all (words that are not normally used) may be used. The "onomatopoeia" is a sound other than a voice that can be emitted by a person, and an example is a sound such as a tongue tapping.

<6>
In another aspect of the voice recognition device according to the present embodiment, the display control unit displays an image to be visually observed at the time of surgery.

According to this aspect, a doctor or the like during surgery can suitably switch modes by using voice. Further, if the darkened image is displayed in the second mode, the darkroom treatment can be preferably performed.

<7>
In another aspect of the voice recognition device according to the present embodiment, the second switching means responds to a voice command in which the second voice command is combined with a third voice command corresponding to each of the first modes. The mode is switched from the second mode to the first mode corresponding to the third voice command.

According to this aspect, by combining the second voice command with the third voice command, it is possible to switch from the second mode to an arbitrary first mode. The third voice command is preset for each mode as a voice command for switching to each of the plurality of first modes. The third voice command may be the same as the first voice command.

<8>
In another aspect of the voice recognition device according to the present embodiment, the second voice command is a combination of a predetermined voice and a movement of the line of sight or a gesture.

According to this aspect, in order to recognize the second voice command, it is required not only to emit a predetermined voice but also to perform a movement of the line of sight, a gesture, and the like. Therefore, it is possible to preferably avoid that the voice emitted unintentionally for mode switching is recognized as the second voice command.

<9>
In another aspect of the voice recognition device according to the present embodiment, the second switching means responds only to a second voice command different from the first voice command for switching to the first mode, and the second mode To switch the mode to the first mode.

According to this aspect, when the mode is switched from the second mode to the first mode, the second switching means responds only to the second voice command. Therefore, it is possible to prevent the second mode from being accidentally switched to the first mode.

<10>
The second voice recognition device according to the present embodiment responds only to the first mode capable of responding to the first voice command and the second voice command different from the first voice command for switching to the first mode. A possible second mode and a second switching means for switching the mode from the second mode to the first mode in response to the second voice command are provided.

According to the second voice recognition device according to the present embodiment, the mode can be switched between the first mode and the second mode. In this embodiment, in particular, the first mode is responsive to the first voice command, while the second mode is responsive only to the second voice command. That is, the mode switching from the second mode to the first mode can be performed only by the second voice command, and the mode cannot be switched by the first voice command or other voice commands.

According to the above-described configuration, it is possible to prevent the second mode from being switched to another mode due to unintended recognition of a voice command while working in the second mode.

<11>
The voice recognition method according to the present embodiment includes a first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to the first voice command, and the above-mentioned. A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command, and an image corresponding to the first mode or the second mode. Is provided with a display control process for displaying the image on the display unit.

According to the voice recognition method according to the present embodiment, suitable mode switching can be realized between the plurality of first modes and the second mode, similarly to the voice recognition device according to the present embodiment described above. ..

In the voice recognition method according to the present embodiment, it is possible to adopt various aspects similar to the various aspects in the voice recognition device according to the above-described embodiment.

<12>
The computer program according to the present embodiment has a first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to the first voice command, and the first switching step. A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command, and an image corresponding to the first mode or the second mode. Have the computer execute the display control process to be displayed on the display unit.

According to the computer program according to the present embodiment, since the computer can execute the same processing as the voice recognition method according to the above-described embodiment, it is suitable between the plurality of first modes and the second mode. Mode switching can be realized.

In the computer program according to the present embodiment, it is possible to adopt various aspects similar to the various aspects in the voice recognition device according to the above-described embodiment.

<13>
The computer program described above is recorded on the recording medium according to the present embodiment.

According to the recording medium according to the present embodiment, suitable mode switching can be realized between the plurality of first modes and the second mode by executing the above-mentioned computer program by a computer.

The voice recognition device and the voice recognition method according to the present embodiment, and the actions and other gains of the computer program and the recording medium will be described in more detail in the following examples.

Hereinafter, examples of the voice recognition device and method, and the computer program and recording medium will be described in detail with reference to the drawings. In the following, a case where the voice recognition device is applied to a display system used in an operating room in a medical field will be described as an example.

<Device configuration>
First, the configuration of the voice recognition device according to this embodiment will be described with reference to FIG. Here, FIG. 1 is a block diagram showing a configuration of a voice recognition device according to an embodiment.

In FIG. 1, the voice recognition device according to the present embodiment includes a voice acquisition unit 110, a voice recognition unit 120, a mode determination unit 130, a voice command determination unit 140, a mode change unit 150, and a screen transition unit 160. It is configured with.

The voice acquisition unit 110 is configured to include, for example, a microphone, and is configured to be able to output a voice signal indicating the acquired voice. The voice signal output from the voice acquisition unit 110 is configured to be output to the voice recognition unit 120.

The voice recognition unit 120 is configured to be able to recognize a word (that is, a word that can be recognized as a voice command for switching a mode) included in the voice indicated by the voice signal. The word recognized by the voice recognition unit 120 is output to the voice command determination unit 140 as a signal indicating the word.

The mode determination unit 130 is configured to be able to acquire information regarding the current mode of the voice recognition device. Each mode in the voice recognition device will be described in detail later. The information about the mode acquired by the mode determination unit 130 is output to the voice command determination unit 140.

The voice command determination unit 140 is configured to be able to determine whether or not the word recognized by the voice recognition unit is a voice command according to the mode. The voice command determination unit 140 includes a mode recognition unit 141, a match rate calculation unit 142, and a match rate determination unit 143 to execute specific processing.

The mode recognition unit 141 determines a voice command to be recognized based on the information regarding the current mode input from the mode determination unit 130. In other words, select the voice command according to the mode.

The match rate calculation unit 142 calculates the match rate between the word recognized by the voice recognition unit 120 and the voice command registered in advance. As for the method of calculating the matching rate, various existing techniques can be adopted, and therefore detailed description thereof will be omitted here.

The match rate determination unit 143 determines whether or not the acquired voice is a voice command to be recognized based on the mode recognized by the mode recognition unit 141 and the match rate calculated by the match rate calculation unit 142. judge.

The voice command determination unit 140 may determine whether or not the command is a voice command by using an index different from the above-mentioned match rate. The determination result in the voice command determination unit 140 is output to the mode change unit 150.

The mode change unit 150 is configured so that the mode can be switched according to a voice command. The mode changing unit 150 is configured to output the result of switching the mode to the screen transition unit 160.

The screen transition unit 160 is configured to be able to switch the display of an external display unit (for example, a liquid crystal display or the like) to one according to the changed mode when the mode is switched by the mode changing unit 150. ing.

<Mode description>
Next, each mode switched by the above-mentioned voice recognition device will be specifically described with reference to FIG. Here, FIG. 2 is a mode transition diagram showing each mode that can be switched by the voice recognition device according to the embodiment.

As shown in FIG. 2, the recognition device according to the present embodiment mutually switches between three normal modes (NAVI mode, GEF mode, and PREOPE mode) and one special mode (darkening mode). It can be carried out.

The NAVI mode is a mode corresponding to a so-called default screen, and is a mode for displaying an image of a patient's facial expression and limbs during surgery, as well as a BIS value and a T1 / T2 image. The BIS value is a value indicating the degree of calmness of the patient in the operation using anesthesia. Further, the T1 / T2 image is an image taken when the substance to be emphasized is changed at the time of taking a picture by MRI (Magnetic Resonance Imaging).

The GEF (Gefrierschnitt) mode is a mode for displaying biopsy results, and can display analysis results and the like for each collected tissue.

The PREOPE (Preoperative: preoperative diagnosis) mode is a mode for displaying a preoperative image. In the example shown in the figure, an image showing information about the brain is displayed.

The darkening mode is a mode for displaying a darkening image (that is, a black screen), and is used when it is desired to block the light of the screen in order to perform a darkroom treatment or the like.

The above mode is an example, and the voice recognition device according to this embodiment can be applied as long as it switches between a plurality of normal modes and at least one special mode. <Process description>
Next, the operation of the voice recognition device according to this embodiment will be described with reference to FIG. Here, FIG. 3 is a flowchart showing an operation flow of the voice recognition device according to the present embodiment.

In FIG. 3, when the voice recognition device according to the present embodiment is operating, the voice acquisition unit 110 first acquires voice (step S101). The acquired voice is recognized by the voice recognition unit 120 (step S102) and output to the voice command determination unit 140. Further, the mode determination unit 130 confirms the current mode in parallel with or in parallel with the acquisition and recognition of the above-mentioned voice (step S103). Information about the current mode is output to the voice command determination unit 140.

The voice command determination unit 140 calculates the matching rate between the words included in the acquired voice and the words registered in advance as voice commands (step S104). The match rate is calculated as a plurality of values corresponding to each of the plurality of words, but only the highest match rate is output as a result.

When the match rate is calculated, it is determined whether or not the current mode is the normal mode (step S105). That is, it is determined whether the current mode is a normal mode (that is, NAVI mode, GEF mode, or PREOPE mode) or a special mode (that is, darkening mode).

When the current mode is the normal mode (step S105: YES), it is determined whether or not the command having the highest match rate is the normal command and the match rate is equal to or higher than a predetermined threshold value (step S106). The normal command is a specific example of the "first voice command", and is determined for each mode as a voice command for mode switching between normal modes and mode switching from normal mode to special mode. ing. Specifically, in mode switching between normal modes, the mode name is a voice command as it is. On the other hand, in the mode switching from the normal mode to the special mode, the word "darkening" is registered as a voice command. The predetermined threshold value is a threshold value set for determining whether or not the recognized voice is a voice command, and an optimum value is set in advance.

When the command with the highest match rate is a normal command and the match rate is equal to or higher than a predetermined threshold value (step S106: YES), the mode change unit 150 switches from the current mode to another mode indicated by the normal command. Switching is performed (step S107). Then, the screen transition unit 160 transitions the screen of the display unit to the one corresponding to the changed mode (step S108). If the command with the highest match rate is not a normal command, or if the match rate is not greater than or equal to a predetermined threshold value (step S106: NO), the voice command determination results in an error, and the mode change unit 150 does not change the mode (step). S109).

On the other hand, when the current mode is the special mode (step S105: NO), it is determined whether or not the command having the highest match rate is the special command and the match rate is equal to or higher than a predetermined threshold value (step S110). ). The special command is a specific example of the "second voice command", and a voice command different from the normal command is set as a voice command for switching the mode from the special mode to the normal mode. In this embodiment, the word "resume" is set as a special command.

When the command with the highest match rate is a special command and the match rate is equal to or higher than a predetermined threshold value (step S110: YES), the mode change unit 150 switches the mode from the special mode to the normal mode (step). S111). Then, the screen transition unit 160 transitions the screen of the display unit to the one corresponding to the changed mode (step S112). If the command with the highest match rate is not a special command, or if the match rate is not greater than or equal to a predetermined threshold value (step S110: NO), the voice command determination results in an error, and the mode change unit 150 does not change the mode (step). S113).

<Specific mode switching operation>
Next, a specific mode switching operation using a voice command will be described with reference to FIGS. 4 to 8. Here, FIG. 4 is a conceptual diagram showing a mode switching method from the normal mode, and FIG. 5 is a conceptual diagram showing a mode switching method from the special mode. Further, FIG. 6 is a conceptual diagram showing a method of switching from the special mode to an arbitrary normal mode, and FIG. 7 is a conceptual diagram showing a partial display example of the normal mode in the special mode. FIG. 8 is a conceptual diagram showing a method of switching from the normal mode to an arbitrary special mode.

As shown in FIG. 4, it is assumed that the current mode is the GEF mode of the normal mode. In this state, when the voice including the word "NAVI mode" is acquired, the normal command "NAVI mode" corresponding to the switching to the NAVI mode is recognized, and the mode is switched from the GEF mode to the NAVI mode. Similarly, when the voice including the word "PREOPE mode" is acquired, the normal command "PREOPE mode" corresponding to the switching to the PREOPE mode is recognized, and the mode is switched from the GEF mode to the PREOPE mode.

Further, when the voice including the word "darkening" is acquired, the normal command "darkening" corresponding to the switching to the darkening mode is recognized, and the mode is switched from the GEF mode to the darkening mode.

In this way, the mode can be switched by a normal command from the GEF mode, which is the normal mode.

As shown in FIG. 5, it is assumed that the current mode is the darkening mode of the special mode. In this state, when the voice including the word "NAVI mode" is acquired, the normal command "NAVI mode" corresponding to the switching to the NAVI mode is recognized, but the mode switching by the normal command is performed in the special mode. Absent. Therefore, the mode is not switched from the dark mode to the NAVI mode.

On the other hand, when the voice including the "restart" word is acquired, the special command "restart" corresponding to the switching from the special mode to the normal mode is recognized, and the dark mode is changed to the GEF mode (normal mode immediately before switching to the dark mode). The mode is switched to.

In this way, the mode cannot be switched by a normal command from the dark mode, which is a special mode. On the other hand, if a special command is used, the mode can be switched from the special mode to the normal mode.

As shown in FIG. 6, consider the case where the current mode is the darkening mode of the special mode again. When the voice including the "resume" word is acquired in this state, the special command "resume" corresponding to the switching from the special mode to the normal mode is recognized as described above, and the dark mode is changed to the GEF mode (dark mode). The mode is switched to (normal mode) immediately before switching to.

On the other hand, when the words "restart" and "NAVI mode" are continuously acquired, the special command "restart" corresponding to the switching from the special mode to the normal mode is recognized, and the NAVI mode is used as the switching destination. The designated designated command "NAVI mode" is recognized, and the mode is switched from the darkening mode to the NAVI mode (mode corresponding to the designated command). The designated command is a specific example of the "third voice command", and is set for each mode as a command for designating the switching destination mode. Specifically, the mode name is the specified command as it is like the normal command.

In this way, by combining the special command and the designated command, it is possible to switch from the special mode to an arbitrary normal mode. That is, it is possible to switch to a normal mode other than the normal mode immediately before switching to the special mode.

As shown in FIG. 7, the darkening mode does not have to show only the darkening image. In this embodiment, when the NAVI mode is switched to the darkening mode, the darkening mode (NAVI) showing only the darkening image is realized. On the other hand, when the GEF mode is switched to the darkening mode, the darkening mode (GEF) that displays a part of the important information of the GEF mode on the darkening image is realized, and the PREOPE mode is switched to the darkening mode. Is realized in a darkening mode (PREOPE) that displays a part of important information of the PREOPE mode on a darkening image.

In this way, the information shown in the normal mode can be confirmed even during the treatment in the dark mode.

As shown in FIG. 8, it is assumed that the current mode is the normal mode NAVI mode. In this state, when the voice including the word "darkening" is acquired, the normal command "darkening" corresponding to the switching to the darkening mode is recognized as described above, and the mode is switched from the NAVI mode to the darkening mode. Is done.

On the other hand, when the words "darkening" and "GEF mode" are continuously acquired, the normal command "darkening" corresponding to the switching to the darkening mode is recognized, and a part of the GEF mode is requested to be displayed. The display command "GEF mode" is recognized, and the mode is switched from the NAVI mode to the darkening mode (GEF) that displays a part of important information of the GEF mode. The display command is set for each mode as a command for designating a normal mode in which a part of the darkened image is displayed. Specifically, the mode name is the specified command as it is like the normal command.

In this way, by combining the normal command and the display command, it is possible to switch from the normal mode to an arbitrary special mode. That is, it is possible to partially display an arbitrary normal mode on the darkened image.

<Effect of Examples>
Finally, the technical effect obtained by the voice recognition device according to the present embodiment will be described in detail.

As described with reference to FIGS. 1 to 5, according to the voice recognition device according to the present embodiment, in the normal mode, switching to each of the other modes can be performed by a normal command. That is, from the normal mode, it is possible to switch to another normal mode by a normal command, or to switch to a special mode by a normal command. On the other hand, in the special mode, it is possible to switch to another mode only with a special command. That is, even if the normal command is recognized in the special mode, the mode is not switched to the normal mode.

Therefore, since the method of switching from the special mode to the normal mode is limited, it is possible to prevent accidentally switching to the normal mode when the switching from the special mode to the normal mode is not intended. ..

Assuming that the mode can be switched by the normal command even in the special mode, the normal command "NAVI mode" is recognized and the NAVI is recognized when the conversation "I saw it in the NAVI mode earlier ..." is performed in the dark mode. Switching to the mode is executed. In this case, if the darkroom treatment is performed in the darkroom mode, the darkroom state is released by switching to the NAVI mode, and appropriate darkroom treatment cannot be performed. In the medical field, such inconvenience may cause great damage.

On the other hand, according to the voice recognition device according to the present embodiment, the voice emitted unintentionally for mode switching is recognized as a voice command for switching modes, and inappropriate mode switching is performed. Can be prevented.

Further, as described with reference to FIGS. 6 to 8, more appropriate mode switching can be performed by combining the designated command and the display command. Therefore, it is possible to display the information to be confirmed extremely preferably.

The present invention is not limited to the above-described embodiment, and can be appropriately modified within the scope of claims and within a range not contrary to the gist or idea of the invention that can be read from the entire specification, and a voice recognition device accompanied by such a modification. And speech recognition methods, as well as computer programs and recording media are also included in the technical scope of the present invention.

110 Voice acquisition unit 120 Voice recognition unit 130 Mode judgment unit 140 Voice command judgment unit 141 Mode recognition unit 142 Match rate calculation unit 143 Match rate judgment unit 150 Mode change unit 160 Screen transition unit

Claims (12)

A first switching means that performs mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching means for switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
It is provided with a display control unit for displaying an image corresponding to the first mode or the second mode on the display unit .
The display control unit is a voice recognition device characterized by displaying a darkened image in the second mode . A first switching means that performs mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching means for switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
With a display control unit that displays an image corresponding to the first mode or the second mode on the display unit.
With
In the second mode, the display control unit causes a part of the image corresponding to the second mode to display at least a part of the image corresponding to the first mode.
A voice recognition device characterized by this. A first switching means that performs mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching means for switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
With a display control unit that displays an image corresponding to the first mode or the second mode on the display unit.
With
The second switching means responds to the second voice command and performs mode switching to the first mode immediately before switching to the second mode.
A voice recognition device characterized by this. The voice recognition device according to any one of claims 1 to 3 , wherein the second voice command is a word or an onomatopoeia that is unlikely to be issued in an environment in which the voice recognition device can be used. The voice recognition device according to any one of claims 1 to 4 , wherein the display control unit displays an image to be visually observed at the time of surgery. The second switching means responds to a voice command in which the second voice command is combined with a third voice command corresponding to each of the first modes, and the second voice command corresponds to the third voice command. The voice recognition device according to any one of claims 1 to 5 , wherein the mode is switched to the first mode. The voice recognition device according to any one of claims 1 to 6 , wherein the second voice command is a combination of a predetermined voice and a movement or gesture of a line of sight. The second switching means responds only to a second voice command different from the first voice command for switching to the first mode, and performs mode switching from the second mode to the first mode. The voice recognition device according to any one of claims 1 to 5 . A first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
A display control step of displaying an image corresponding to the first mode or the second mode on the display unit.
Including
The display control step is a voice recognition method characterized in that a darkened image is displayed in the second mode . A first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
The computer is made to execute the display control step of displaying the image corresponding to the first mode or the second mode on the display unit .
The display control step is a computer program characterized in that a darkened image is displayed in the second mode . A first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
A display control step of displaying an image corresponding to the first mode or the second mode on the display unit.
Let the computer run
In the display control step, at the time of the second mode, at least a part of the image corresponding to the first mode is displayed on a part of the image corresponding to the second mode.
A computer program characterized by that. A first switching step of performing mode switching between a plurality of first modes and mode switching from the first mode to the second mode in response to a first voice command.
A second switching step of switching the mode from the second mode to the first mode in response to a second voice command different from the first voice command.
A display control step of displaying an image corresponding to the first mode or the second mode on the display unit.
Let the computer run
In the second switching step, in response to the second voice command, the mode is switched to the first mode immediately before switching to the second mode.
A computer program characterized by that.