JP2010128237A - Speech interactive system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that, when a speech interactive system is incorporated in an interactive object, the interactive object is too large to carry, and it may suffer big damage, when it is fallen or sunk in water. <P>SOLUTION: The interactive object 11 and a server 13 which is connected with the interactive object 11 with or without wires are provided. A speech recognition board 55 and an interactive processing section 71 are arranged in the server 13. When a predetermined device such as a game machine is operated, or a predetermined operation body is operated, a moving section is separately provided from the interactive object 11, and the device is operated with or without wires. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a voice interaction system, and is effective when applied to, for example, a mobile phone, a personal computer, a camera, and a game machine.

  In recent years, spoken dialogue devices have been developed and commercialized through industry, government and academia.

  However, conventional voice interaction devices, such as a voice interaction robot, are often integrated with the person to be interacted with, and it is always pointed out that there is a possibility of failure due to a fall accident or submergence accident when carrying this. The Further, the above-mentioned voice interactive apparatus is very expensive, and there is a problem that a large amount of cost is required for repair if the above accident occurs and breaks down.

  In addition, although the conventional voice interaction device has been reduced in size, there has been a problem that it becomes practically inconvenient because it becomes a very large mobile phone when incorporated in a mobile phone, for example. For this reason, although a voice interaction device has been developed, there are cases where it is not actually incorporated into the interactee. In addition, it is difficult to reduce the size of a robot incorporating a voice interaction device.

  In addition, the conventional voice dialogue apparatus is merely positioned as a dialogue target for performing voice dialogue only by being combined with the dialogue target, and can provide a higher-value and higher-functional voice dialogue system. There wasn't. Furthermore, the conventional voice interaction apparatus has a problem that a more advanced user interface cannot be realized only by combining with the object to be interacted.

  In view of the above points, the first object of the present invention is to provide a spoken dialogue system that reduces damage when an accident occurs.

  In addition, in view of the above points, the second object of the present invention is to provide a spoken dialogue system that can be made compact.

  In addition, in view of the above points, the third object of the present invention is to provide a high-value voice dialogue system with high added value.

  In addition, in view of the above points, a fourth object of the present invention is to provide an object to be spoken or a voice dialogue system capable of voice dialogue capable of realizing an advanced user interface.

In order to achieve the above object, according to the present invention, in the first aspect of the present invention, there is provided speech conversion means for converting a human voice into a voice signal and a sound generation means for generating a sound by changing a predetermined pronunciation signal into vibration. The interactee,
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
With
The server computer processes the voice signal converted by the voice conversion means to recognize the voice of the person, determines the voice corresponding to the voice recognized by the voice recognition means, and outputs a predetermined pronunciation signal And a dialogue control means.

  According to this configuration, the object to be interacted with the voice conversion means and the sound generation means and the server computer that is configured separately from the object to be interacted with the voice recognition means and the dialog control means are wired and wirelessly connected. A person can perform a voice conversation with a person to be interacted with.

  Since the voice recognition means and the dialogue control means are provided in the server computer, the expensive voice recognition means and the dialogue control means do not break down even when the object to be interacted is dropped or submerged in a puddle. Furthermore, when the interactee is connected wirelessly to the server computer, the interactee can be moved without being restricted by the length of the wire as in the case of being connected by wire. Can do.

In the invention according to claim 2, to-be-interacted body provided with sounding means for sounding by changing a predetermined sounding signal into vibration,
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
A voice conversion unit that is provided separately from the interactee and the server computer, and is connected to either the talkee and the server computer either by wire or wirelessly and converts a human voice into an audio signal;
With
The server computer processes the voice signal converted by the voice conversion means to recognize the voice of the person, determines the voice corresponding to the voice recognized by the voice recognition means, and outputs a predetermined pronunciation signal And a dialogue control means.

  According to this, since the voice conversion means is provided separately from the object to be interacted with and the server computer, it is possible to input the sound to the sound conversion means even if a person does not approach the object to be interacted with. Further, since the voice conversion device is not carried around, the voice conversion means does not break down even when the interactee is dropped or submerged in a puddle.

In the invention according to claim 3, there is provided a voice conversion means for converting a human voice into a voice signal, and a to-be-interactive body provided with a sound generation means for changing a predetermined sound generation signal into vibration,
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
With
Both speech recognition means for processing a speech signal converted by the speech conversion means and a dialogue recognition means for determining a word corresponding to the word recognized by the word recognition means and outputting a predetermined pronunciation signal One of the means is provided in the object to be interacted with, and the other is provided in the server computer.

  According to this, the person to be interacted with the person to be interacted is connected by a wired or wireless connection between the object to be interacted with the voice recognition means and the server computer on which the dialog control means is installed. It can be performed.

  Since the dialog control means is provided in the server computer, the expensive dialog control means does not break down when the object to be interacted is dropped or submerged in a puddle. Further, when the interactee and the server computer are connected wirelessly, the interactee can be moved without being restricted by the length of the wire as in the case of being connected by wire. it can. As described above, even when one of the voice recognition unit and the dialogue control unit is mounted on the interactee and the other is mounted on the server computer, the above-described effects can be obtained.

In the invention according to claim 4, to-be-interacted body provided with sounding means for sounding by changing a predetermined sounding signal into vibration,
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
A voice conversion unit that is provided separately from the interactee and the server computer, and is connected to either the talkee and the server computer either by wire or wirelessly and converts a human voice into an audio signal;
With
Both voice recognition means for processing a voice signal converted by the voice conversion means to recognize a human voice, and a dialog control means for determining a voice corresponding to the voice recognized by the voice recognition means and outputting a predetermined pronunciation signal One of the means is provided in the object to be interacted with, and the other is provided in the server computer.

  According to this, since the voice conversion means is provided separately from the object to be interacted with and the server computer, it is possible to input the sound to the sound conversion means even if a person does not approach the object to be interacted with. Further, since the voice conversion device is not carried around, the voice conversion means does not break down even when the interactee is dropped or submerged in a puddle.

  According to any one of claims 1 to 4, compared to the case where all of the voice conversion means, the sound generation means, the voice recognition means, and the dialogue control means are mounted on the dialogue target, Can be made small and light, and the object can be easily carried.

According to a fifth aspect of the present invention, in the spoken dialogue system according to any one of the first to fourth aspects, a pronunciation information storage unit capable of storing predetermined pronunciation information further includes a computer to be interacted with and a server computer. Is mounted on either
Predetermined pronunciation information is stored in the pronunciation information storage unit,
When a person requests predetermined pronunciation information via the voice conversion means, when a person permits the predetermined pronunciation information via the voice conversion means, or when the person to be spoken pronounces himself using the predetermined pronunciation information One of the features is that predetermined sounding information is read from the sounding information storage unit and sounded by the sounding means.

  According to this, not only a person has a voice conversation with a person to be interacted but also a person requests a predetermined pronunciation information, a person permits a predetermined pronunciation information through the voice conversion means, a predetermined pronunciation It is possible to provide a highly functional voice dialogue system capable of obtaining predetermined pronunciation information in any case where the person to be spoken by himself / herself uses information. In addition, when a person requests predetermined pronunciation information, an advanced user interface can be provided that reads out the predetermined pronunciation information and produces sound from the sound generation means when the person to be spoken uses the predetermined pronunciation information. . Further, when the pronunciation information storage unit is mounted on the server computer, the pronunciation information stored in the pronunciation information storage unit is damaged even if the interactee is dropped or submerged in a puddle. There is nothing.

In the invention described in claim 6, in claim 5, the pronunciation information storage unit is configured to be freely connected to the Internet.
The pronunciation information can be downloaded from a predetermined storage location on the Internet.

  According to this, it is possible to provide a highly functional voice dialogue system that can download predetermined pronunciation information from the Internet. Further, since the predetermined pronunciation information can be downloaded from the Internet, even if the predetermined pronunciation information stored in the pronunciation information storage unit is damaged, the predetermined pronunciation information can be restored immediately.

As in the invention described in claim 7, in any one of claims 1 to 6, the interactee is one or more movable parts;
A motor for moving each of the one or more movable parts;
A drive unit for driving each motor;
A controller that outputs a command signal to command the operation of the movable part to the drive part;
May be provided.

  According to this, it is possible to move the movable part by outputting the command signal for commanding the operation of the movable part from the controller to the drive part and driving the motor based on the command signal. As described above, the spoken dialogue system may include a movable unit, a motor, a drive unit, and a controller in the object to be interacted.

According to an eighth aspect of the present invention, in any one of the first to sixth aspects, the interactee is one or more movable parts;
A motor for moving each of the one or more movable parts;
A drive unit for driving each motor;
With
The server computer includes a controller that outputs an operation command signal to the drive unit.

  According to this, the command signal for commanding the operation of the movable part is output from the controller provided for the server computer to the drive part provided for the interactee, and the motor is driven based on the command signal. Thus, the movable part can be moved.

  As described above, since the controller is provided in the server computer, the expensive controller does not fail even when the interactee is dropped or submerged in a puddle.

In the invention according to claim 9, in any one of claims 1 to 6, the interactee is one or more movable parts;
A motor for moving each of the one or more movable parts;
With
The server computer includes a drive unit that drives each motor, and a controller that outputs an operation command signal to the drive unit.

  According to this, the command signal for commanding the operation of the movable part is output from the controller provided in the server computer to the drive unit, and the motor provided in the interactee is driven based on the command signal. Thus, the movable part can be moved.

  Since the drive unit and the controller are provided in the server computer, the expensive drive unit and controller do not break down even when the object to be interacted is dropped or submerged in a puddle.

According to a tenth aspect of the present invention, in any one of the first to sixth aspects, the at least one of the interactee and the server computer is provided separately from the interactee and the server computer. It is equipped with a movable unit that can be connected and moved by either wired or wireless,
The movable unit includes one or more movable parts;
A motor for moving each of the one or more movable parts;
A drive unit for driving each motor;
A controller that outputs a command signal to command the operation of the movable part to the drive part;
It is characterized by having.

  According to this, the movable unit is provided separately from the interactee and the server computer, and can be moved by being connected to the interactee either by wire or wirelessly.

  As described above, since the movable part, motor, drive unit, and controller are provided separately from the interactee, even if the interactee is dropped or submerged in a puddle, the expensive movable part The motor, drive unit and controller will not break down.

According to an eleventh aspect of the present invention, in any one of the first to sixth aspects, at least one of the interactee and the server computer is provided separately from the interactee and the server computer. It has a movable unit connected by either wired or wireless,
The movable unit includes one or more movable parts;
Motors each driving one or more movable parts;
A drive unit for driving each motor;
With
One of the object to be interacted with and the server computer includes a controller that outputs an operation command signal to the drive unit.

  According to this, a command signal for commanding the operation of the movable part is output from the controller provided in either the interactee or the server computer to the drive unit, and the movable unit is provided based on this command signal. By driving the motor, the movable part can be moved.

  Since the movable part, motor, and drive part are provided separately from the interactee, the expensive movable part, motor, and drive part will fail even if the interactee is dropped or submerged in a puddle. There is nothing to do.

According to a twelfth aspect of the present invention, in any one of the first to sixth aspects, a wired and wireless connection is provided to at least one of the interactee and the server computer. It has a movable unit connected by either
The movable unit includes one or more movable parts;
A motor for moving each of the one or more movable parts;
With
A drive unit for driving each motor is provided in either the interactee or the server computer,
A controller that outputs an operation command signal to the drive unit is provided in either the interactee or the server computer.

  According to this, since at least the movable part and the motor are provided in the movable unit, the expensive movable part and the motor do not break down even when the interactee is dropped or submerged in a puddle. .

  According to any one of claims 8 to 12, the interactee can be made smaller and lighter than when the movable part, the motor, the drive unit, and the controller are all provided in the interactee. Therefore, it is possible to easily carry the interactee.

  As in a thirteenth aspect of the present invention, in any one of the tenth to twelfth aspects, the interactee and the movable unit may be configured to be freely attachable.

  According to this, since the movable unit can be attached to the interacting body, there are two cases where the interacted body is configured separately from the movable unit and when the interacted body is configured integrally with the movable unit. You can use different configurations.

According to a fourteenth aspect of the present invention, in the voice interaction system according to any one of the first to ninth aspects, the image display means for displaying a predetermined image is either integrated with or separated from the object to be interacted. It is established in
An image information storage unit in which predetermined image information is stored in advance is mounted on either the interactee or the server computer,
When a person requests predetermined image information through the voice conversion unit, or when a person permits the predetermined image information through the voice conversion unit, the interactee uses the predetermined image information to display the predetermined image information. In any case of displaying, predetermined image information is read from the image information storage unit and displayed on the image display means.

  According to this, when the image display means is provided separately from the interactee, the image display means can be damaged even if the interactee is dropped or submerged in a puddle. Absent. Further, when the image information storage unit is mounted on the server computer, the image information in the image information storage unit is not damaged even if the interactee is dropped or submerged in a puddle. . Note that the image information storage unit may be mounted on the interactee, and the image display means may be provided integrally with the interactee.

According to a fifteenth aspect of the present invention, in the voice interaction system according to any one of the tenth to thirteenth aspects, the image display means for displaying a predetermined image is either the object to be interacted or the movable unit. Provided, connected to at least one of the interactee, the server computer, and the movable unit by either wired or wireless,
An image information storage unit in which predetermined image information is stored in advance is mounted on any of the interactee, the server computer, and the movable unit,
When a person requests predetermined image information through the voice conversion unit, or when a person permits the predetermined image information through the voice conversion unit, the interactee uses the predetermined image information to display the predetermined image information. In any case of displaying, predetermined image information is read from the image information storage unit and displayed on the image display means.

According to this, when the image display means is mounted on either the server computer or the movable unit, the expensive image display means can be used even when the interactee is dropped or submerged in a puddle. Will not damage. Further, when the image information storage unit is mounted on either the server computer or the movable unit, the image information stored in the image information storage unit can be obtained even when the object to be interacted is dropped or submerged in a puddle. Will not damage. Note that the image display means may be provided in the interactee, and the image information storage unit may be provided in the interactee.

According to a sixteenth aspect of the present invention, in the voice interaction system according to any one of the tenth to thirteenth aspects, the image display means for displaying a predetermined image is separate from both the object to be interacted and the movable unit. Is connected to at least one of the interactee, the server computer, and the movable unit by either wired or wireless,
An image information storage unit in which predetermined image information is stored in advance is mounted on any of the interactee, the server computer, and the movable unit,
When a person requests predetermined image information through the voice conversion unit, or when a person permits the predetermined image information through the voice conversion unit, the interactee uses the predetermined image information to display the predetermined image information. In any case of displaying, predetermined image information is read from the image information storage unit and displayed on the image display means.

  According to this, since the image display means for displaying a predetermined image is provided separately from both the interactee and the movable unit, even when the interactee is dropped or submerged in a puddle The image information in the image information storage unit is not damaged.

  According to any one of claims 14, 15, and 16, when a person requests predetermined image information via the voice conversion unit, the person receives a predetermined image via the voice conversion unit. When the information is permitted, it is possible to provide a high-performance voice dialogue system that can obtain the predetermined image information in any case where the interactee displays the predetermined image using the predetermined image information. In addition, when a person requests predetermined image information through the voice conversion unit, or when a person permits the predetermined image information through the voice conversion unit, the person to be interacted with the predetermined image information uses the predetermined image information. In any case of displaying an image, it is possible to realize an advanced user interface that obtains predetermined image information from the image information storage unit and displays it on the image display means.

According to a seventeenth aspect of the present invention, in any one of the fourteenth to sixteenth aspects, the image information storage unit is configured to be connectable to the Internet.
The image information can be downloaded from a predetermined storage location on the Internet.

  According to this, it is possible to provide a high-performance voice interaction system that can download predetermined image information from the Internet. Further, since the predetermined image information can be downloaded from the Internet, even if the predetermined image information stored in the image information storage unit is damaged, the predetermined image information can be restored immediately.

As in the eighteenth aspect of the present invention, in any one of the first to ninth aspects and the fourteenth aspect, the imaging means capable of imaging a predetermined object including a person is integrated with and separated from the interactee. Composed of one of the bodies,
Image recognition means for recognizing a predetermined object from image data captured by the image pickup means may be mounted on either the interactee or the server computer.

  According to this, it is possible to recognize a predetermined object from the imaging data imaged by the imaging means. As described above, the imaging means may be configured either as an integral body or a separate body. In addition, it is possible to provide a high-functional voice interaction system including an imaging unit.

According to a nineteenth aspect of the present invention, in any one of the tenth to thirteenth, fifteenth, and sixteenth aspects, the imaging means capable of imaging a predetermined object including a person is an interactive body and a movable body. It is provided in any of the units and is connected to at least one of the interactee, the server computer, and the movable unit by either wired or wireless,
Image recognition means for recognizing a predetermined object from image data captured by the imaging means is mounted on at least one of the interactee, the server computer, and the movable unit.

  According to this, it is possible to recognize a predetermined object including a person from the imaging data captured by the imaging unit. When the imaging unit is provided in the movable unit, the expensive imaging unit is not damaged even when the interactee is dropped or submerged in a puddle. Further, when the image recognition means is mounted on the server computer or the movable unit, the expensive image recognition means is not damaged. Note that the imaging means may be provided on the interactee, and the image recognition means may be mounted on the interactee.

According to a twentieth aspect of the present invention, in any one of the tenth to thirteenth, fifteenth, and sixteenth aspects, the imaging means capable of imaging a predetermined object including a person is an interactive body and a movable body. It is provided separately from any of the units, and is connected to at least one of the interactee, the server computer, and the movable unit by either wired or wireless,
Image recognition means for recognizing a predetermined object from image data captured by the imaging means is mounted on at least one of the interactee, the server computer, and the movable unit.

  According to this, it is possible to recognize a predetermined object including a person from the imaging data captured by the imaging unit. As described above, the imaging means may be configured either as an integral body or a separate body. In addition, it is possible to provide a high-functional voice interaction system including an imaging unit.

  According to a twenty-first aspect of the present invention, in any one of the seventh to twentieth aspects, the movable portion performs a predetermined communication operation in at least one of a case where a dialogue is performed with a person and a predetermined explanation is given. As described above, the controller outputs a command signal to the drive unit.

  Accordingly, it is possible to provide an advanced voice dialogue system that performs a communication operation and produces a realistic sensation as compared to a voice dialogue system in which no movable part is provided. In addition, it is possible to realize an advanced user interface that performs a communication operation and produces a realistic sensation as compared to a voice dialogue system that does not include a moving part.

According to a twenty-second aspect of the present invention, in any one of the tenth to thirteenth and thirteenth and fifteenth aspects, the movable portion is disposed at a position for operating a predetermined device.
When a human voice is an instruction to operate a predetermined device, when a human voice is permission to operate a predetermined device, when operating a predetermined device by a predetermined operation input means, operate the predetermined device When the automatic execution program is executed, the controller outputs a command signal to the drive unit so as to operate a predetermined device.

  According to this, it is possible to provide an advanced spoken dialogue system in which the controller outputs a command signal to the drive unit and the movable unit operates a predetermined device.

  According to a twenty-third aspect of the present invention, in any one of the eighteenth to twentieth aspects, the imaging unit images a predetermined object including a person, and the image recognition unit recognizes the predetermined object. Based on the above, the controller outputs a command signal to the drive unit so as to perform a predetermined communication operation with a person.

  According to this, an advanced voice dialogue system that captures images of a predetermined object including a person, communicates based on the result of the image recognition means recognizing the predetermined object, and pronounces with a sense of reality is provided. it can. Further, it is possible to realize an advanced user interface that captures an image of a predetermined object including a person, performs a communication operation based on a result of the image recognition unit recognizing the predetermined object, and pronounces with a sense of presence. .

  According to a twenty-fourth aspect of the present invention, in any one of the eighteenth to twentieth aspects, the imaging unit images a predetermined object including a person, and the image recognition unit recognizes the predetermined object. Based on the above, at least one of a plurality of pronunciation data is selected and pronounced with respect to a person via a pronunciation means.

  According to this, it is possible to provide an advanced speech dialogue system that recognizes a predetermined object including a person by the imaging means and the image recognition means and performs a voice dialogue with the person. In addition, it is possible to realize a high-level user interface for recognizing a predetermined object including a person by the image recognizing means and having a voice conversation with the person.

According to a twenty-fifth aspect of the present invention, in any one of the eighteenth to twentieth aspects, the imaging unit images an operation unit of a predetermined device,
When a human voice is an instruction to operate a predetermined device, when a human voice is permission to operate a predetermined device, when operating a predetermined device by a predetermined operation input means, operate the predetermined device When the automatic execution program is executed, based on the result of the image recognizing means recognizing the position of the operating means, the movable part and the object to be interacted move to the operating position of the means and operate a predetermined device. The controller outputs a command signal to the drive unit.

  According to this, it is possible to provide an advanced voice dialogue system in which the movable part and the object to be interacted move to the operation position of the means and operate a predetermined device. Further, when the human voice is an instruction to operate the predetermined device, the human voice is permitted to operate the predetermined device, or the predetermined device is operated by the predetermined operation input means, the movable portion and It is possible to realize an advanced user interface in which the interactee moves to the operation position of the means and operates a predetermined device.

According to a twenty-sixth aspect of the present invention, in any one of the eighteenth to twentieth aspects, the imaging unit images the progress of the table game, and the image recognition unit recognizes the progress of the table game. Is configured as
An operation determining means for determining the next operation of the movable part from the progress status recognized by the image recognition means;
The controller outputs a command signal to the drive unit so that the movable unit executes the next operation determined by the operation determination unit.

  According to this, the progress state of the table game is imaged and recognized by the imaging means and the image recognition means, the next action of the movable part is determined by the action determining means, and the next moving part determined by the action determining means is determined. It is possible to provide an advanced spoken dialogue system that executes the operations of

  According to a twenty-seventh aspect of the present invention, in any one of the eighteenth to twentieth aspects, the controller outputs a command signal to the driving unit to move the movable unit to search for a predetermined object including a person. It is characterized by.

  According to this, it is possible to provide an advanced voice interaction system that searches for a predetermined object.

According to a twenty-eighth aspect of the present invention, in any one of the eighteenth to twentieth aspects, the tracking program in which the imaging unit tracks a predetermined object recognized by the image recognition unit is an interactive object and a server computer. Is mounted on either
A command signal is output from the controller to the drive unit so that the imaging unit tracks a predetermined object including a person, and the movable unit is moved.

  According to this, since the movable unit can be moved so that the imaging unit tracks a predetermined object including a person, even if the predetermined object including the person moves, the predetermined object including the person is tracked. It is possible to provide an advanced spoken dialogue system that recognizes

According to a twenty-ninth aspect of the present invention, in the voice interaction system according to any one of the first to twenty-eighth aspects, an operation for outputting an operation signal to an operation means of an operating body further including an operation means operated by an operation signal A signal output means is mounted on at least one of the interactee and the server computer;
The actuating means and the actuating signal output means are connected by one of wireless and wired.

  According to this, it is possible to provide an advanced speech dialogue system that directly operates the operating means of the operating body by the operating signal output from the operating signal output means without using the movable unit.

  According to a thirty-third aspect of the present invention, in any one of the first to thirty-first aspects, the interactee is configured by a mobile phone.

  According to this, it is possible to provide an advanced voice interaction system in which a person and a mobile phone have a voice conversation. In addition, it is possible to obtain the operation and effect obtained by replacing the “subject to be interacted” of the operation and effect described after any one of the above-described means of claims 1 to 30 with “mobile phone”.

  According to a thirty-first aspect of the present invention, in any one of the first to thirty-first aspects, the interactee is constituted by a computer.

  According to this, it is possible to provide an advanced voice dialogue system in which a person and a computer perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted object” of the operation and effect described after any one of the above-described means by the “computer”.

  According to a thirty-second aspect of the present invention, in any one of the first to thirtieth aspects, the interactee is configured by a game machine.

  According to this, it is possible to provide an advanced voice dialogue system in which a person and a game machine perform voice dialogue. In addition, it is possible to obtain an operation and an effect obtained by replacing the “interacted object” of the operation and effect described after any one of the above-described means by a “game machine”.

  According to a thirty-third aspect of the present invention, in any one of the first to thirty-third aspects, the object to be interacted is configured by a camera.

  According to this, it is possible to provide an advanced voice interaction system in which a person and a camera have a voice conversation. In addition, it is possible to obtain an operation and an effect obtained by replacing the “interactive body” of the operation and effect described after any one of the above-described means of claims 1 to 30 with a “camera”.

  According to a thirty-fourth aspect of the present invention, in any one of the first to thirty-first aspects, the interactee is configured by a robot body.

  According to this, it is possible to provide an advanced voice dialogue system in which a person and a robot body perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted body” of the operation and effect described after any one of the above-described means by the “robot body”.

  According to a thirty-fifth aspect of the present invention, in any one of the first to thirty-third aspects, the object to be interacted is formed of any one of a doll, a stuffed toy, and a toy.

  According to this, it is possible to provide an advanced voice dialogue system in which a person and any one of a doll, a stuffed animal, and a toy perform voice dialogue. Further, an effect obtained by replacing the “interactive body” of the action and effect described after any one of the means of claims 1 to 30 with any of “doll”, “stuffed animal”, and “toy”. Obtainable. In addition, since the object to be interacted with is composed of any one of a doll, a stuffed animal, and a toy, it is easy to get familiar.

(First embodiment)
First, terms used in the following description will be described. A person's voice is a sound emitted by a person. Pronunciation is a sound emitted from a spoken dialogue system to a person.

  This will be specifically described below. FIG. 1 is an external view of the voice dialogue system, FIG. 2 is a block diagram of the voice dialogue system, and FIG. 3 is a front sectional view of the movable unit. As shown in FIG. 1, the voice interaction system 100 according to the first embodiment includes an object to be interacted 11, a server 13, and a movable unit 15. The server 13 constitutes the server computer of the present invention.

  The person to be interacted 11 is assumed to be a conversation partner when viewed from a person, and as shown in FIG. 2, the drive unit 17, the upper arm motor 19, the lower arm motor 21, the hand motor 23, and the traveling motor 25. , Turning motor 27, upper arm portion 29, lower arm portion 31, hand 33, traveling portion 35, turning portion 37, microphone 39, sound output board 41, speaker 43, CCD camera 45, command signal receiving demodulation means 47, sound signal A modulation transmission unit 49, a sound signal reception / demodulation unit 51, an imaging signal modulation transmission unit 53, a small control device (not shown), and a power supply (not shown) are provided.

  Based on a command signal from the controller 59, which will be described later, the drive unit 17 controls the upper arm motor 19, the lower arm motor 21, the hand motor 23, the traveling motor 25, and the turning motor 27 in accordance with the command signal from the controller 59. To drive.

  Upper arm motor 19, lower arm motor 21, hand motor 23, traveling motor 25, and turning motor 27 move upper arm portion 29, lower arm portion 31, hand 33, traveling portion 35, and turning portion 37, respectively. To do.

  The upper arm portion 29, the lower arm portion 31, the hand 33, the traveling portion 35, and the turning portion 37 are respectively shown as an upper arm motor 19, a lower arm motor 21, a hand motor 23, a traveling motor 25, and a turning motor 27. It is attached to the drive shaft that is not, and can be moved by driving the drive shaft. The upper arm part 29, the lower arm part 31, the hand 33, the traveling part 35, and the turning part 37 have a predetermined communication operation (gesture, hand gesture) in at least one of cases where a predetermined explanation is given when a conversation is performed with a person. Can do. The communication operation is performed when the controller 59 outputs a command signal for performing a predetermined communication operation to the drive unit 17. The predetermined communication operation is determined by an operation determination unit 73 described later. The upper arm part 29, the lower arm part 31, the hand 33, the traveling part 35, and the turning part 37 are collectively referred to as a movable part. The upper arm part 29, the lower arm part 31, the hand 33, the traveling part 35, and the turning part 37 constitute a movable part of the present invention.

  Moreover, the upper arm part 29, the lower arm part 31, the hand 33, the traveling part 35, and the turning part 37 can operate the predetermined device 200 in cooperation. The operation of the predetermined device is performed by the controller 59 outputting a command signal for operating the predetermined device 200 to the drive unit 17. At that time, a CCD camera 45 (to be described later) images the operation means 200a of the predetermined apparatus 200, performs image recognition by the image recognition means, and further, the controller 59 operates the drive unit 17 based on a program for operating the predetermined apparatus 200. In addition, a command signal for operating the predetermined apparatus 200 is output. If the operation can be performed without using the CCD camera 45 and the image recognition means, the CCD camera 45 and the image recognition means may not be used.

  The microphone 39 converts a human voice into a voice signal and outputs the voice signal. The microphone constitutes the sound conversion means of the present invention.

  The sound output board 41 converts the sound signal received and demodulated by the sound signal reception demodulating means 51 into a predetermined voltage and outputs it.

  The speaker 43 converts the voltage output from the audio output board 41 into sound and generates a sound. The speaker 43 constitutes the sounding means of the present invention.

  The CCD camera 45 captures an image around the object to be interacted 11 and includes a CCD image sensor 45a and a signal processing unit 45b. The CCD image sensor 45 a and the signal processing unit 45 b are mounted on the turning unit 37. Then, when the turning motor 27 is driven, the turning unit 37 turns to take an image of the periphery of the interacting body 11. In the first embodiment, the signal processing unit 45 b is mounted on the interactee 11, but may be mounted on the server 13. The CCD image sensor 45a constitutes the image pickup means of the present invention.

  The CCD image sensor 45a couples light emitted from a predetermined object including a person to a light receiving plane of an image sensor by an optical system such as a lens, and photoelectrically converts light and darkness of the image into an amount of electric charge. The information is sequentially read and converted into an electric signal, and the periphery of the interacting body 11 is imaged and converted into an electric signal.

  The signal processing unit 45b processes the electrical signal converted by the CCD image sensor 45a into a predetermined imaging signal. The recognition signal recognized by the signal processing unit 45b is modulated into any one of radio waves, light waves, and ultrasonic waves by the imaging signal modulation and transmission means 53, and a predetermined signal is received by the recognition signal reception demodulation means 67 provided in the server 13. Demodulated into a recognition signal. Then, it is transmitted to the image recognition means of the server 13.

  In the image recognition means, feature points of a predetermined object including a person are extracted from an image pickup signal obtained by picking up an image around the object 11 to be recognized. The CPU of the CPU board 57 controls the dialogue processing unit 71 and the operation determining unit 73 based on the result recognized by the image recognition means. An image captured by the CCD image sensor 45a and processed by the signal processing unit 45b can be displayed on an image monitor 79a described later.

  The signal processing unit 45b may be provided on the server 13 side. In this case, the image data captured by the CCD image sensor 45a is converted into any one of radio waves, light waves, and ultrasonic waves by the imaging signal modulation transmission unit 53. The signal may be modulated and demodulated into predetermined imaging data by the imaging signal reception demodulating means 67 provided in the server 13, and transmitted to the signal processing unit 45b.

  The command signal receiving / demodulating means 47 receives any one of radio waves, light waves and ultrasonic waves transmitted from the command signal modulation / transmitting means 61 mounted on the server 13 and demodulates them into a predetermined command signal.

  The audio signal modulation / transmission means 49 modulates the audio signal converted by the microphone 39 into one of a radio wave, a light wave, and an ultrasonic wave and transmits it to the audio signal reception / demodulation means 63 mounted on the server 13.

  The sound signal receiving / demodulating means 51 receives any one of radio waves, light waves, and ultrasonic waves transmitted from the sound signal modulating / transmitting means 65 mounted on the server 13 and demodulates it into a predetermined sound signal.

  Next, the server 13 will be described. The server 13 includes a voice recognition board 55, a CPU board 57, a controller 59, a command signal modulation / transmission means 61, a voice signal reception / demodulation means 63, a sound signal modulation / transmission means 65, an imaging signal reception / demodulation means 67, and an image signal modulation / transmission means. 69 is mounted and electricity is supplied from a power source (not shown).

  As shown in FIG. 2, the voice recognition board 55 includes an acoustic analysis unit, analyzes the voice of the other party input from the microphone 39, and extracts acoustic features. Then, the speech recognition engine recognizes the speech by comparing and comparing the acoustic feature extracted by the acoustic analysis unit with the acoustic model that is a statistical model of the distribution of the speech feature amount pattern in units of phonemes, The result is output to the dialogue processing unit 71 of the CPU board 57. In the first embodiment, in addition to the acoustic model, a language model that defines the connection relationship between words is provided, and a continuous word, a sentence including a prefix, and a conjunction can be recognized. The speech recognition board 55 constitutes speech recognition means of the present invention.

  In addition to the CPU, the CPU board 57 includes a memory including a RAM and a ROM, and the memory stores an interactive processing program, an operation determination program, pronunciation information, and image information. In the following description, the dialogue processing unit 71 is a predetermined memory area in which the dialogue processing program and the dialogue processing program are stored, and the action determination unit 73 is a predetermined memory area in which the operation determination program and the operation determination program are stored. A predetermined memory area in which the pronunciation information and the pronunciation information are stored is referred to as a pronunciation information storage section 75, and a predetermined memory area in which the image information and the image information are stored is referred to as an image information storage section 77.

  The controller 59 issues an operation command signal to the drive unit 17 so that the above-described upper arm unit 29, lower arm unit 31, hand 33, travel unit 35, and turning unit 37 perform the operations determined by the operation determination unit 73. .

  The command signal modulation / transmission means 61 modulates the operation signal transmitted from the controller 59 into one of radio waves, light waves, and ultrasonic waves, and transmits it to the command signal reception / demodulation means 47.

  The sound signal receiving / demodulating means 63 receives the sound signal modulated by the sound signal modulation / transmitting means 49 into any one of radio waves, light waves, and ultrasonic waves, and demodulates it into a predetermined sound signal.

  The sound signal modulation transmitting means 65 receives the sound signal modulated by the sound signal receiving / demodulating means 51 into any one of radio waves, light waves, and ultrasonic waves, and demodulates it into a predetermined sound signal.

  The image signal modulation / transmission means 69 modulates the image signal output from the signal processing unit 45 b of the CCD camera 45 into any one of radio waves, light waves, and ultrasonic waves, and transmits it to the image information reception / demodulation means 81.

  The dialogue processing unit 71 determines a voice to respond to the other party based on the voice recognized by the voice recognition board 55. The sound determined by the dialog processing unit 71 is converted into a predetermined voltage by the sound output board 41 via the sound signal modulation / transmission means 65 and the sound signal reception / demodulation means 51, and is sounded by the speaker 43. The dialog processing unit 71 also has a function of sounding by the voice dialog system 100 itself. The dialogue processing unit 71 determines an operation when a person is recognized by the CCD camera 45, during dialogue, or when the person to be interacted 11 himself / herself pronounces. The dialogue processing unit 71 constitutes dialogue control means of the present invention.

  The CPU board 57 also includes a pronunciation information storage unit 75 that stores predetermined sound information. When a person requests predetermined sound generation information via the microphone 39, the person generates a predetermined sound generation via the microphone 39. When the information is permitted, the predetermined sounding information is read out from the sounding information storage unit 75 and sounded from the speaker 43 in any of the cases where the interacting body 11 sounds itself using the predetermined sounding information.

  Further, an image display device 79 is provided separately from the interactee 11 and the server 13. The image display device 79 includes an image monitor 79a for displaying an image, and an image information receiving / demodulating unit that receives any one of radio waves, light waves, and ultrasonic waves transmitted from the image signal modulation / transmitting unit 69 and demodulates them into predetermined image information. 81 is provided. The image monitor 79a constitutes the image display means of the present invention.

  The pronunciation information is information transmitted to a person by pronunciation, and includes music and sound in addition to voice. The image information is information displayed to a person, and is configured by at least one of a still image, a moving image, characters, and light.

  Note that the pronunciation information storage unit 75 and the image information storage unit 77 may be arranged outside the CPU board 57 or may be arranged in the interactee 11.

  The image monitor 79a may display facial expressions by imitating human eyebrows, eyes, and mouth. The facial expression is, for example, an ordinary facial expression, a laughing facial expression, a crying facial expression, an angry facial expression, etc., and the facial expression is determined by a facial expression determination unit (not shown) based on the conversation content determined by the dialogue processing unit 71. .

  Next, the movable unit 15 will be described. The movable unit 15 is configured separately from the interacting body 11 and the server 13, and includes a drive unit 83, a solenoid 85, a pusher 87, and a command signal receiving / demodulating unit 89, and is supplied with electricity from a power source (not shown). ing.

  As shown in FIG. 2, when receiving the command signal of the operation received and demodulated by the command signal receiving / demodulating means 89, the drive unit 83 energizes the solenoid 85 shown in FIG. 2 and moves the pusher 87. The pusher 87 is disposed at a position for turning on / off the operation means 200a of the predetermined device 200 when the pusher 87 is moved.

  The movable unit 15 is not limited to the above configuration, and various forms are conceivable. For example, a plurality of movable parts and a motor that moves each of the plurality of movable parts may be mounted, and in addition to the plurality of movable parts and the motor, a drive unit that drives the motor may be mounted.

  Here, the dialogue operation of the voice dialogue system 100 will be described. When a person speaks to the interactee 11, the sound is converted into an audio signal by the microphone 39 mounted on the interactee 11 along with the ambient sound. The converted voice signal is transmitted to the voice recognition board 55 via the voice signal modulation / transmission means 49 and the voice signal reception / demodulation means 63. The voice recognition board 55 analyzes the other party's voice input from the microphone 39, extracts the acoustic features, the acoustic features extracted by the acoustic analysis unit in the voice recognition engine, and the voice features in units of phonemes. The voice is recognized by comparing with the acoustic model that is a statistical model of the distribution of the quantity pattern, and the result is output to the CPU board 57.

  At that time, the controller 59 outputs an operation command signal to the drive unit 17 so that the dialogue motor 11 and the CCD camera 45 mounted on the turning motor 27 turn to search for a person. . Then, the CCD camera 45 captures an image of the periphery of the person to be interacted 11 and extracts and recognizes feature points of a predetermined object including a person from the electric signal converted by the CCD image sensor 45a. When the person moves, the turning motor 27 and the CCD camera 45 mounted on the turning motor 27 turn to follow the person.

  Next, the dialogue processing unit 71 determines a voice to respond to the other party based on the voice recognized by the voice recognition board 55. The sound determined by the dialog processing unit 71 is converted into a predetermined voltage by the sound output board 41 via the sound signal modulation / transmission means 65 and the sound signal reception / demodulation means 51, and is sounded by the speaker 43. At this time, if it is set to perform a communication operation, the controller 59 causes the drive unit 17 to perform a communication operation for a person according to the content of the voice determined by the dialogue processing unit 71. The operation command signal is output to.

  In addition, when a person utters the interacting body 11 when the person requests predetermined pronunciation information via the microphone 39, or when the person permits the predetermined pronunciation information via the microphone 39, the predetermined pronunciation information When the person to be interacted 11 pronounces itself by using the, the predetermined sounding information is read from the sounding information storage unit 75 and sounded by the sounding means.

  In addition, when the person utters the interacting body 11 when the person requests predetermined image information via the microphone 39, or when the person permits the predetermined image information via the microphone 39, the predetermined image information Is used to display the image information on the image monitor 73a, the predetermined image information is read from the image information storage unit 77 and displayed on the image monitor 79a.

  In addition, when the content of the person uttering the interacting body 11 is a command for operating the predetermined device 200 when the voice of the person is an instruction to operate the predetermined device 200, a predetermined operation input is performed. When the predetermined device 200 is operated by the means, when the automatic execution program for operating the predetermined device 200 is executed, the CCD camera 45 images the operation means 200a of the predetermined device 200, and the image recognition means is the operation means. The position of 200a is recognized. Then, the controller 59 is moved to the drive unit 17 so that the traveling unit 35 is moved to a position where the operating unit 200a is operated, and the upper arm unit 29, the lower arm unit 31, the hand 33, and the traveling unit 35 operate the predetermined device 200. A command signal is output.

  Further, when a voice dialogue is performed with a person, if the image monitor 79a is set to display a facial expression by imitating a person's eyebrows, eyes, and mouth, the conversation content determined by the dialogue processing unit 71 is displayed. Based on this, a facial expression determination unit (not shown) determines the facial expression, and displays an ordinary facial expression, a laughing facial expression, a crying facial expression, an angry facial expression, and the like for the image monitor 79a.

  According to the above configuration, between the interactee 11 provided with the microphone 39 and the speaker 43, and the server computer comprising the speech recognition board 55 and the dialog processor 71, which is configured separately from the interactee 11. Are connected by either wired or wireless, and a person can have a voice conversation with the person to be interacted 11. In addition, a command signal for commanding the operation of the movable part is output from the controller provided in the server computer to the drive part provided in the object to be interacted with, and the motor is driven based on the command signal, thereby moving the command. The part can be moved.

  Further, according to the above configuration, since the voice recognition board 55 and the dialogue processing unit 71 are provided in the server 13, all of the microphone 39, the speaker 43, the voice recognition board 55, and the dialogue processing unit 71 are mounted on the interacting body 11. Compared to the case where the interactee 11 is made smaller and lighter, it is possible to easily carry the interactee 11.

  Further, since the voice recognition board 55 and the dialogue processing unit 71 are provided in the server 13, even when the interacted body 11 is dropped or submerged in a puddle, the expensive voice recognition board 55 and the dialogue processing unit 71 are provided. There is no failure.

  Further, according to the above configuration, since the controller 59 is provided in the server 13, the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 Compared to the case where all of the object 11 is provided, the object 11 can be made smaller and lighter, and the object 11 can be easily carried.

  In addition, since the controller 59 is provided in the server 13, the expensive controller 59 does not break down even when the interactee 11 is dropped or submerged in a puddle.

  Further, according to the above configuration, since the pronunciation information storage unit 75 and the image information storage unit 77 are provided in the server 13, compared with the case where the pronunciation information storage unit 75 and the image information storage unit 77 are provided in the interacting body 11. The interacting body 11 can be made small and light, and the interacting body 11 can be easily carried.

  Further, since the pronunciation information storage unit 75 and the image information storage unit 77 are provided in the server 13, even when the interacted body 11 is dropped or submerged in a puddle, the expensive pronunciation information storage unit 75 and the image information are stored. The storage unit 77 does not fail.

  Further, according to the above configuration, since the image display device 79 is configured separately from both the interactee 11 and the server 13, compared to the case where the image display 79 is provided in the interactee 11. The interacting body 11 can be made small and light, and the interacting body 11 can be easily carried.

  Further, since the pronunciation information storage unit 75 and the image information storage unit 77 are provided in the server 13, even when the interacted body 11 is dropped or submerged in a puddle, the expensive pronunciation information storage unit 75 and the image information are stored. The storage unit 77 does not break down.

Further, since the image display device 79 is configured separately from both the interactee 11 and the server 13, even when the interactee 11 is dropped or submerged in a puddle, expensive image display is performed. The device 79 will not fail.
Furthermore, since the interactee 11 and the server 13 are connected wirelessly, the interactee 11 can be moved without being restricted by the length of the wire.

  In addition, according to the above configuration, when a person not only has a voice conversation with the person to be interacted 11 but also requests a predetermined pronunciation information, if a person permits the predetermined pronunciation information via the microphone 39, It is possible to provide a highly functional voice dialogue system that can obtain predetermined pronunciation information in any case where the person to be interacted 11 pronounces itself using predetermined pronunciation information. In addition, when a person requests predetermined pronunciation information, an advanced user interface can be provided that reads out the predetermined pronunciation information and produces a sound from the speaker 43 when the person to be spoken uses the predetermined pronunciation information. . Further, since the pronunciation information storage unit is mounted on the server 13, even if the interactee 11 is dropped or submerged in a puddle, the pronunciation information stored in the pronunciation information storage unit 75 is damaged. There is no.

  Further, according to the above configuration, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the object to be interacted using the predetermined image information. It is possible to provide a high-performance voice interaction system capable of obtaining predetermined image information in any case where the user himself / herself displays a predetermined image. In addition, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the interactee 11 himself / herself uses the predetermined image information. In any case of displaying the image information, it is possible to realize an advanced user interface that obtains predetermined image information from the image information storage unit and displays it on the image monitor 79a.

  The image information storage unit may be mounted on the interactee 11, and the image monitor 79 a may be provided integrally with the interactee 11.

  Further, according to the above configuration, the CCD camera 45a images a predetermined object including a person, and the image recognition means performs a communication operation based on the result of recognizing the predetermined object, and pronounces with a sense of presence. An advanced voice dialogue system can be provided. Further, it is possible to realize an advanced user interface that captures an image of a predetermined object including a person, performs a communication operation based on a result of the image recognition unit recognizing the predetermined object, and pronounces with a sense of presence. .

  Further, according to the above configuration, it is possible to provide an advanced voice dialogue system that recognizes a predetermined object including a person by the CCD image sensor 45a and the image recognition means and performs voice dialogue with the person. Further, it is possible to realize an advanced user interface for recognizing a predetermined object including a person by the CCD image sensor 45a and the image recognizing means and having a voice conversation with the person.

  Moreover, according to the said structure, the controller 59 outputs a command signal to a drive part, and the high-level voice interactive system which the movable unit 15 operates the predetermined | prescribed apparatus 200 can be provided.

  Further, according to the above configuration, when the human voice is an instruction to operate the predetermined device 200, when the human voice is permission to operate the predetermined device, the predetermined device is operated by the predetermined operation input means. In this case, it is possible to provide an advanced voice dialogue system in which the movable units 29, 31, 33, 35, and 37 and the interactee 11 are moved to the operation position of the predetermined device 200 and operate the predetermined device 200. Further, when the human voice is an instruction to operate a predetermined device, when the human voice is permission to operate the predetermined device, or when operating the predetermined device by a predetermined operation input means, each movable part 29, 31, 33, 35, 37 and the interacting body 11 can be moved to the operation position of the predetermined device 200, and an advanced user interface for operating the predetermined device 200 can be realized.

(Second Embodiment)
In the first embodiment, the spoken dialogue system 100 is provided with the interactee 11, the server 13, and the movable unit 15. However, the spoken dialogue system 100 may be configured by only the interactee 11 and the server 13. .

(Third embodiment)
In the first embodiment, the interacting body 11 is provided with the movable parts 29, 31, 33, 35, and 37, the motors 19, 21, 23, 25, and 27, and the driving unit 17. Each movable part 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, and the drive part 17 do not need to be provided. Further, the voice interaction system 100 may be configured only by the interactee 11 and the server 13. Further, the image display device 79 may be configured separately from the interactee 11.

  According to the above configuration, the interacting body 11 includes the drive unit 17, the motors 19, 21, 23, 25, 27, the movable units 29, 31, 33, 35, 37, the microphone 39, the audio output board 41, and the speaker. 43, the CCD camera 45, the CPU board 57, the controller 59, the pronunciation information storage unit 75, the image information storage unit 77, and the image display device 79, when the microphone 39 and the speaker 43 are provided, FIG. As shown in FIG. 5, the interacting body 11 can be greatly downsized. In addition, since wireless communication is possible, for example, not only can it be used in a limited area in the home, but also only the object 11 can be moved to a remote area and used.

  Further, even when the interactee 11 is dropped or submerged in a puddle, the worst case is that only the microphone 39 and the speaker 43 are broken, and the damage can be minimized.

(Fourth embodiment)
In the first embodiment, the traveling unit 35 is provided in the interacting body 11, but the traveling unit 35 may not be provided in the interacting body 11. Moreover, although the traveling unit 35 is provided in the interactee 11, a walking means may be provided instead of the traveling unit 35.

(Fifth embodiment)
In the first embodiment, both the voice recognition board 55 and the dialogue processing unit 71 are mounted on the server 13. However, as shown in FIG. 6, the voice recognition board 55 is mounted on the interactee 11 and the dialogue processing unit 71. May be mounted on the server 13.

  According to the above configuration, since the dialogue processing unit 71 is provided in the server 13, the expensive dialogue processing unit 71 does not break down when the object 11 is dropped or submerged in a puddle. .

  Further, according to the above configuration, the movable body 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive unit 17, and the controller 59 are all provided in the interacting body 11. Compared to, the interactee 11 can be made smaller and lighter, and the interactee 11 can be easily carried.

(Sixth embodiment)
In the fourth embodiment, the speech recognition board 55 is mounted on the interactee 11 and the dialog processing unit 71 is mounted on the server 13. However, the dialog processing unit 71 is mounted on the interactee 11 and the speech recognition board 55 is It may be mounted on the server 13.

  According to the above configuration, since the voice recognition board 55 is provided in the server 13, the expensive voice recognition board 55 does not break down when the interacting body 11 is dropped or submerged in a puddle. .

(Seventh embodiment)
The microphone 39 may be configured separately from the interactee 11 and mounted on a head microphone (not shown). The head microphone is a device that places a microphone near the person's mouth, and can input voice to the microphone 39 even if the person does not approach the interactee 11.

  According to the above configuration, voice can be input to the microphone 39 even if a person does not approach the interactee 11, thereby improving the voice recognition rate. In general, when a human voice is recognized by the voice recognition board 55, it is known that the recognition rate of a human voice is reduced due to ambient sounds, noise, and the like. For this reason, a method of improving the speech recognition rate by arranging a plurality of microphones 39 or arranging a noise removal filter in front of the acoustic unit analysis unit has been considered. In the fourth embodiment, in addition to the above, the speech recognition rate is improved.

  Further, in the third embodiment, when the microphone 39 is configured separately from the interactee 11 and mounted on a head microphone (not shown), the interactee 11 is made smaller and lighter than the third embodiment. It is possible to carry the interactee 11 easily. Further, by using the head microphone, it is possible to reduce noise when a voice signal is input to the voice recognition board 55.

(Eighth embodiment)
In the first embodiment, the pronunciation information storage unit 75 is provided in the server 13, but the pronunciation information storage unit 75 may be provided in the interactee 11. Further, in the first embodiment, the image information storage unit 77 is provided in the server 13, but the image information storage unit 77 may be provided in the interactee 11.

(Ninth embodiment)
The pronunciation information described above may be downloaded from a predetermined storage location on the Internet.

  According to the above configuration, the pronunciation information storage unit 75 is configured to be connectable to the Internet, and the predetermined pronunciation information can be downloaded from a predetermined storage location on the Internet. Therefore, the predetermined pronunciation information is downloaded from the Internet. A high-performance spoken dialogue system can be provided. Further, since the predetermined pronunciation information can be downloaded from the Internet, even if the predetermined pronunciation information stored in the pronunciation information storage unit 75 is damaged, the predetermined pronunciation information can be restored immediately.

(10th Embodiment)
The image information described above may be downloaded from a predetermined storage location on the Internet.

  According to the above configuration, it is possible to provide a highly functional voice interaction system that can download predetermined image information from the Internet. Further, since the predetermined image information can be downloaded from the Internet, even if the predetermined image information stored in the image information storage unit 77 is damaged, the predetermined image information can be restored immediately.

(Eleventh embodiment)
In the first embodiment, the interacting body 11 includes movable parts 29, 31, 33, 35, 37, motors 19, 21, 23, 25, 27, and a drive part 17, and the server 13 is a controller 59. However, even if the interactee 11 includes all of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59. Good.

(Twelfth embodiment)
In the first embodiment, the interacting body 11 includes movable parts 29, 31, 33, 35, 37, motors 19, 21, 23, 25, 27, and a drive part 17, and the server 13 is a controller 59. However, the interacting body 11 includes the movable parts 29, 31, 33, 35, and 37, and the motors 19, 21, 23, 25, and 27, and the server 13 includes the drive part 17 and the controller 59. May be provided.

  According to the above configuration, the command signal for commanding the operation of the movable unit 11 is output from the controller 59 provided in the server 13 to the drive unit 17, and each of the commands provided in the interacting body 11 is based on the command signal. By driving the motors 19, 21, 23, 25, 27, the movable parts 29, 31, 33, 35, 37 can be moved.

  Since the drive unit 17 and the controller 59 are provided in the server 13, the expensive drive unit 17 and the controller 59 do not break down even when the interactee 11 is dropped or submerged in a puddle.

  Compared with the case where each of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 are all provided in the interacting body 11, The body 11 can be made small and light, and the carried body 11 can be easily carried.

(13th Embodiment)
In the first embodiment, the movable body 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, and the drive unit 17 are provided in the interacting body 11, and the controller 59 is provided in the server 13. However, instead of this, the movable unit 15 may include all of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59. Good.

  According to the above configuration, the movable unit 15 is provided separately from the interactee 11 and the server 13, and can be moved by being connected to the interactee either by wire or wirelessly.

  Since each movable part 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, drive part 17, and controller 59 are provided separately from the interactee 11, the interactee 11 Even when the camera is dropped or submerged in a puddle, the expensive movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 are broken. There is nothing to do.

  Compared with the case where each of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 are all provided in the interacting body 11, The body 11 can be made small and light, and the carried body 11 can be easily carried.

(14th Embodiment)
In the first embodiment, the movable body 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, and the drive unit 17 are provided in the interacting body 11, and the controller 59 is provided in the server 13. However, instead of this, the movable unit 15 may be provided with the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, and the drive part 17. In the above case, the controller 59 may be provided in either the interactee 11 or the server 13.

  According to the above configuration, a command signal for commanding the operation of each of the movable units 29, 31, 33, 35, and 37 is output from the controller 59 provided in either the interactee 11 or the server 13 to the drive unit. By driving the motors 19, 21, 23, 25, 27 provided in the movable unit 15 based on the command signal, the movable parts 29, 31, 33, 35, 37 can be moved.

  Since each movable part 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, and drive part 17 are provided separately from the interactee 11, the interactee 11 is dropped. In this case, even when submerged in a puddle, the expensive movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, and the drive part 17 do not break down.

  Compared with the case where each of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 are all provided in the interacting body 11, The body 11 can be made small and light, and the carried body 11 can be easily carried.

(Fifteenth embodiment)
In the first embodiment, the movable body 29, 31, 33, 35, 37, each motor 19, 21, 23, 25, 27, and the drive unit 17 are provided in the interacting body 11, and the controller 59 is provided in the server 13. However, instead of this, the movable unit 15 includes movable parts 29, 31, 33, 35, and 37, and motors 19, 21, 23, 25, and 27. 11 and the server 13, and the controller 59 may be provided in either the interactee 11 or the server 13.

  According to the above configuration, since at least each of the movable parts 29, 31, 33, 35, and 37 and the motors 19, 21, 23, 25, and 27 are provided, the object 11 is dropped or a puddle. Even when submerged in water, the expensive movable parts 29, 31, 33, 35, 37 and the motors 19, 21, 23, 25, 27 do not fail.

  Compared with the case where each of the movable parts 29, 31, 33, 35, 37, the motors 19, 21, 23, 25, 27, the drive part 17, and the controller 59 are all provided in the interacting body 11, The body 11 can be made small and light, and the carried body 11 can be easily carried.

(Sixteenth embodiment)
The interactee 11 and the movable unit 15 may be configured to be freely attachable.

  According to this, since the movable unit 15 can be attached to the interacting body 11, the interacting body 11 is configured separately from the movable unit 15, and the interacting body 11 is configured integrally with the movable unit 15. The two configurations can be used separately.

(17th Embodiment)
In the first embodiment, the image monitor 79 a that displays a predetermined image is provided in the server 13, but the image monitor 79 a that displays a predetermined image may be provided integrally with the interacting body 11.

(Eighteenth embodiment)
In the first embodiment, the image information storage unit 77 is mounted on the server 13, but the image information storage unit 77 may be mounted on the interactee 11, and a person requests predetermined image information via the microphone 39. In such a case, when the person permits the predetermined image information via the microphone 39, the interacting body 11 displays the predetermined image by itself using the predetermined image information. Predetermined image information may be read out and displayed on the image monitor 79a.

  According to the above configuration, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the person to be interacted with uses the predetermined image information. It is possible to provide a high-performance voice interaction system capable of obtaining predetermined image information in any case where a predetermined image is displayed. In addition, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the interactee uses the predetermined image information to display a predetermined image by himself / herself. In any case of display, it is possible to realize an advanced user interface that obtains predetermined image information from the image information storage unit 77 and displays it on the image monitor 79a.

(Nineteenth embodiment)
In the first embodiment, the image monitor 79 a is provided separately from any of the interactee 11, the server 13, and the movable unit 15, but the image monitor 79 a is provided in either the interactee 11 or the movable unit 15. Thus, an image information storage unit 77 that is connected to at least one of the interactee 11, the server 13, and the movable unit 15 by either wired or wireless, and stores predetermined image information in advance. 13, mounted on either of the movable units 15, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the predetermined image information In any of the cases where the interactee 11 displays a predetermined image by itself, the predetermined image information may be read from the image information storage unit 77 and displayed on the image monitor 79a.

  According to the above configuration, when the image monitor 79a is mounted on either the server 13 or the movable unit 15, an expensive image is obtained even when the interactee 11 is dropped or submerged in a puddle. The monitor 79a is not damaged. Further, when the image information storage unit 77 is mounted on either the server 13 or the movable unit 15, the image information storage unit 77 even when the interactee 11 is dropped or submerged in a puddle. The image information is not damaged. Note that the image monitor 79 a may be provided in the interactee 11, and the image information storage unit 77 may be provided in the interactee 11.

  Further, according to the above configuration, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the object to be interacted using the predetermined image information. It is possible to provide a high-performance voice interaction system capable of obtaining predetermined image information in any of the cases where the 11 displays a predetermined image by itself. In addition, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the interactee uses the predetermined image information to display the predetermined image information himself / herself. In any case of display, it is possible to realize an advanced user interface that obtains predetermined image information from the image information storage unit 77 and displays it on the image monitor 79a.

(Eighteenth embodiment)
In the first embodiment, the image information storage unit 77 is mounted on the server 13, but is mounted on either the interactee 11 or the movable unit 15, and a person requests predetermined image information via the microphone 39. In such a case, when the person permits the predetermined image information via the microphone 39, the interacting body 11 displays the predetermined image by itself using the predetermined image information. Predetermined image information may be read and displayed on the image monitor 79a.

  According to the above configuration, the image monitor 79a for displaying a predetermined image is provided separately from both the interacting body 11 and the movable unit 15, so that the interacting body 11 is dropped or submerged in a puddle. Even when the image information is stored, the image information in the image information storage unit 77 is not damaged.

  Further, according to the above configuration, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the object to be interacted using the predetermined image information. It is possible to provide a high-performance voice interaction system capable of obtaining predetermined image information in any case where the user himself / herself displays a predetermined image. In addition, when a person requests predetermined image information via the microphone 39, or when a person permits predetermined image information via the microphone 39, the interactee uses the predetermined image information to display the predetermined image information himself / herself. In any case of display, it is possible to realize an advanced user interface that obtains predetermined image information from the image information storage unit 77 and displays it on the image monitor 79a.

(Nineteenth embodiment)
The image information storage unit 77 described above may be configured to be connectable to the Internet, and the image information may be downloaded from a predetermined storage location on the Internet.

  According to this, it is possible to provide a high-performance voice interaction system that can download predetermined image information from the Internet. Further, since the predetermined image information can be downloaded from the Internet, even if the predetermined image information stored in the image information storage unit is damaged, the predetermined image information can be restored immediately.

(20th embodiment)
In the first embodiment, the CCD image sensor 45a is configured integrally with the interactee 11; however, the CCD image sensor 45a is configured separately from the interactee 11 and is captured by the CCD image sensor 45a. The image recognition means for recognizing a predetermined object from either of the objects 11 and the server 13 may be mounted.

  According to this, it is possible to recognize a predetermined object from the imaging data captured by the CCD image sensor 45a. In addition, it is possible to provide a highly functional voice dialogue system including the CCD image sensor 45a.

(21st Embodiment)
The movable unit 15 may be provided with a CCD camera 45a capable of imaging a predetermined object including a person.

According to the above configuration, the expensive CCD camera 45a is not damaged even if the interactee 11 is dropped or submerged in a puddle.
(Twenty-second embodiment)
An image monitor 79a for recognizing a predetermined object from image data captured by the CCD camera 45a may be mounted on any one of the interacting body 11 and the movable unit 15.

  According to the above configuration, when the image monitor 79a is mounted on the movable unit 15, the expensive image monitor 79a is not damaged. As described above, the image monitor 79a may be mounted on the interactee 11.

(23rd Embodiment)
A CCD camera 45a capable of imaging a predetermined object including a person is provided separately from both the interacting body 11 and the movable unit 15, and wired to at least one of the interacting body 11, the server 13, and the movable unit 15. And an image monitor 79a that is connected either wirelessly or for recognizing a predetermined object from image data captured by the CCD camera 45a is mounted on at least one of the interacting body 11, the server 13, and the movable unit 15. Also good.

(24th Embodiment)
The CCD camera 45a captures the progress status of the table game, and the image monitor 79a is configured to recognize the progress status of the table game. Each movable unit 29, Operation determining means for determining the next operation of 31, 33, 35, 37 is provided so that each movable part 29, 31, 33, 35, 37 executes the next operation determined by the operation determining means. In addition, the controller 59 may output a command signal to the drive unit.

  According to the above configuration, the progress status of the table game is picked up and recognized by the CCD camera 45a and the image monitor 79a, and the next operation of each movable unit 29, 31, 33, 35, 37 is determined by the operation determination unit 73. The moving part can perform the next action determined by the action determining part 73 to provide an advanced voice dialogue system for proceeding with the game.

(25th Embodiment)
A CCD image sensor 45a is mounted on any one of the movable parts 29, 31, 33, 35, and 37, and a command signal is output from the controller 59 to the drive part 17 so that the movable parts 29, 31, 33, 35, and 37 are connected. A predetermined object including a person may be searched by moving the object.

  According to the above configuration, it is possible to provide an advanced voice interactive system that searches for a predetermined object including a person.

(26th Embodiment)
In the voice interaction system according to any one of the first embodiment to the twenty-fifth embodiment, the operation signal output means for outputting the operation signal is further provided to the operation means of the operation body including the operation means operated by the operation signal. 11 and the server 13, and the operation means and the operation signal output means may be connected by any one of wireless and wired.

  According to the above-described configuration, the operating unit of the operating body is directly operated by the operation signal output from the operation signal output unit without using the movable unit 15 or the movable units 29, 31, 33, 35, and 37. Can provide a simple spoken dialogue system.

(27th Embodiment)
As shown in FIG. 7, the interactee 11 may be a mobile phone.

According to the above configuration, it is possible to provide an advanced voice dialogue system in which a person and a mobile phone perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted object” of the operation and effect described in any one of the first to 25th embodiments with “mobile phone”. Note that there is a server that responds to a voice during a call, but it is distinguished from the voice dialogue system of the present invention.
(Twenty-eighth embodiment)

  As shown in FIG. 8, the interactee 11 may be composed of a computer.

  According to the above configuration, it is possible to provide an advanced voice interaction system in which a person and a computer have a voice conversation. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted object” of the operation and effect described in any one of the first to 25th embodiments with “computer”.

(Twenty-ninth embodiment)
The interactee 11 may be a game machine.

  According to the above configuration, it is possible to provide an advanced voice dialogue system in which a person and a game machine perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted body” of the operation and effect described in any one of the first to 25th embodiments described above with a “game machine”.

(Thirty Embodiment)
The interactee 11 may be composed of a camera.

  According to the above configuration, it is possible to provide an advanced voice dialogue system in which a person and a camera perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interactive body” of the operation and effect described in any one of the first to 25th embodiments described above with “camera”.

(Thirty-first embodiment)
The interactee 11 may be a robot body.

  According to the above configuration, it is possible to provide an advanced voice dialogue system in which a person and a robot body perform voice dialogue. In addition, it is possible to obtain the operation and effect obtained by replacing the “interacted body” of the operation and effect described in any one of the first to 25th embodiments with the “robot body”.

(Thirty-second embodiment)
The interactee 11 may be composed of any one of a doll, a stuffed toy, and a toy.

  According to the above configuration, it is possible to provide an advanced voice dialogue system in which a person and any one of a doll, a stuffed animal, and a toy perform voice dialogue. Further, an effect obtained by replacing the “interactive body” of the action and effect described after any one of the means of claims 1 to 30 with any of “doll”, “stuffed animal”, and “toy”. Obtainable. Furthermore, since the person to be interacted 11 is composed of any one of a doll, a stuffed animal, and a toy, it is easy to get familiar.

(Other embodiments)
The configuration of the movable part described above is not limited to that of the first embodiment. For example, it may be appropriately adapted to the operation method of the operation means 200a of the predetermined device 200, or may be appropriately adapted to the operation method of operating a predetermined game machine. Each of the one or more movable parts may be configured by any one of a face part, an eye part, a mouth part, a head part, an arm part, a leg part, and a hip part. Further, the above-described movable part may be only the upper arm part 29 and the lower arm part 31, or may be a predetermined walking device instead of the turning part 37.

  Further, the pronunciation information storage unit 75 may be provided in the movable unit 15. Further, the image information storage unit 77 may be provided in the movable unit 15.

  Further, instead of the voice recognition board 55, a voice dialogue process may be performed using a voice dialogue program.

  The server 13 may be connected to a local network line including an Internet line, a telephone line, and a home LAN. Further, the interactee 11 may be connected to a local network line including an Internet line, a telephone line, and a home LAN. In addition, any of an access point, a relayable computer, and a telephone that relays between the interactee 11 and the server 13 is connected to the local network line including the Internet line, the telephone line, and the home LAN. The interactee 11 may be connected to the server 13 using any one of the access point, the relayable computer, and the telephone as a relay point.

  In addition, an emotion parameter storage unit that stores an emotion parameter when the interactant 11 produces a sound is provided in either the interactee 11 or the server 13, and refers to the parameter when the speaker 43 produces the sound, Of the facial expression and mouth shape, a facial expression and mouth shape corresponding to the parameters may be selected and displayed on the image display unit. According to the above configuration, when interacting with a person, when performing a predetermined explanation, any of the face, eyes, mouth, head, arms, legs, and buttocks can be moved to provide a sense of presence. It can provide an advanced spoken dialogue system that produces sounds with In addition, it is possible to realize an advanced user interface that can generate a realistic sensation by moving any of the face, eyes, mouth, head, arms, legs, and buttocks. There are various configurations of the control circuit including the voice recognition board 55, the CPU board 57, the image recognition means, and the like described above, and the configuration is not limited to this as long as it satisfies the claims.

1 is an external view of a voice interaction system according to a first embodiment of the present invention. 1 is a block diagram of a voice interaction system according to a first embodiment of the present invention. The front sectional view of the movable unit by a 1st embodiment of the present invention is shown. It is an external view of the voice interactive system by 3rd Embodiment of this invention. It is a block diagram of the voice dialogue system by a 3rd embodiment of the present invention. It is a block diagram of the voice dialogue system by a 5th embodiment of the present invention. It is an external view of the voice interactive system by 27th Embodiment of this invention. It is an external view of the voice interactive system by 28th Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Voice dialogue system 200 ... Predetermined apparatus 200a ... Operation means 11 ... Dialogue part 13 ... Server (server computer)
15 ... Moveable unit 16 ... Speaker (voice output means, dialogue means)
DESCRIPTION OF SYMBOLS 17 ... Drive part 19 ... Upper arm motor 21 ... Lower arm motor 23 ... Hand motor 25 ... Traveling motor 27 ... Turning motor 29 ... Upper arm part (movable part)
31 ... Lower arm (movable part)
33 ... Hand (movable part)
35 ... traveling part (movable part)
37 ... Turning part (movable part)
39 ... Microphone 41 ... Voice output board (voice recognition means)
43 ... Speaker 45 ... CCD camera 45a ... CCD image sensor (imaging means)
45b ... Signal processing unit 47 ... Command signal reception demodulation means 49 ... Sound signal modulation transmission means 51 ... Sound signal reception demodulation means 53 ... Imaging signal modulation transmission means 55 ... Sound recognition board 57 ... CPU board 59 ... Controller 61 ... Command signal modulation Transmission means 63 ... Audio signal reception demodulation means 65 ... Sound signal modulation transmission means 67 ... Imaging signal reception demodulation stage 69 ... Image signal modulation transmission means 71 ... Dialog processing section (dialog processing means)
73 ... Operation determination unit 75 ... Pronunciation information storage unit 77 ... Image information storage unit 79 ... Image display device 79a ... Image monitor (image display means)
81 ... Image information reception demodulating means 83 ... Driving section 85 ... Solenoid 87 ... Pusher 89 ... Command signal receiving demodulation means

Claims (35)

A voice conversion means for converting a human voice into a voice signal, and a to-be-interactive body provided with a sound generation means for generating a sound by changing a predetermined pronunciation signal into vibration;
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
With
The server computer determines the voice corresponding to the voice recognized by the voice recognition means by processing the voice signal converted by the voice conversion means and recognizing the voice of the person. A spoken dialogue system comprising dialogue control means for outputting a pronunciation signal. A to-be-interactive body provided with a sound generation means for changing a predetermined sound generation signal into a vibration;
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
Audio that is provided separately from the interactee and the server computer, and is connected to either the interactee or the server computer either by wire or wirelessly and converts human speech into an audio signal Conversion means;
With
The server computer determines the voice corresponding to the voice recognized by the voice recognition means by processing the voice signal converted by the voice conversion means and recognizing the voice of the person. A spoken dialogue system comprising dialogue control means for outputting a pronunciation signal. A voice conversion means for converting a human voice into a voice signal, and a to-be-interactive body provided with a sound generation means for generating a sound by changing a predetermined pronunciation signal into vibration;
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
With
Word recognition means for processing a voice signal converted by the voice conversion means to recognize a human word, dialog control for determining a word corresponding to the word recognized by the word recognition means and outputting the predetermined pronunciation signal One of the means is provided in the object to be interacted with, and the other is provided in the server computer. A to-be-interactive body provided with a sound generation means for changing a predetermined sound generation signal into a vibration;
A server computer provided separately from the interactee and connected to the interactee either by wire or wirelessly;
Audio that is provided separately from the interactee and the server computer, and is connected to either the interactee or the server computer either by wire or wirelessly and converts human speech into an audio signal Conversion means;
With
Voice recognition means for processing a voice signal converted by the voice conversion means to recognize a human voice; dialog control for determining a voice corresponding to the voice recognized by the voice recognition means and outputting the predetermined pronunciation signal One of the means is provided in the object to be interacted with, and the other is provided in the server computer. 5. The spoken dialogue system according to claim 1, further comprising a pronunciation information storage unit capable of storing predetermined pronunciation information mounted on either the interactee or the server computer. And
The predetermined pronunciation information is stored in the pronunciation information storage unit;
When the person requests the predetermined pronunciation information via the voice conversion means, and when the person permits the predetermined pronunciation information via the voice conversion means, the subject using the predetermined pronunciation information A spoken dialogue system, wherein the predetermined pronunciation information is read out from the pronunciation information storage unit and is pronounced from the pronunciation means in any case where the dialogue body pronounces itself. The pronunciation information storage unit is configured to be freely connected to the Internet,
6. The spoken dialogue system according to claim 5, wherein the pronunciation information can be downloaded from a predetermined storage location on the Internet. The interactee includes one or more movable parts;
A motor for moving each of the one or more movable parts;
Driving units for driving the motors;
A controller that outputs a command signal to command the operation of the movable unit to the drive unit;
The spoken dialogue system according to claim 1, further comprising: The interactee includes one or more movable parts;
A motor for moving each of the one or more movable parts;
Driving units for driving the motors;
With
7. The spoken dialogue system according to claim 1, wherein the server computer includes a controller that outputs an operation command signal to the drive unit. The interactee includes one or more movable parts;
A motor for moving each of the one or more movable parts;
With
7. The server computer according to claim 1, further comprising: a drive unit that drives each of the motors; and a controller that outputs an operation command signal to the drive unit. The spoken dialogue system described in 1. A movable unit provided separately from the interactee and the server computer, and connected to at least one of the interactee and the server computer in a wired or wireless manner and movable;
The movable unit includes one or more movable parts;
A motor for moving each of the one or more movable parts;
Driving units for driving the motors;
A controller that outputs a command signal to command the operation of the movable unit to the drive unit;
The spoken dialogue system according to claim 1, further comprising: A movable unit provided separately from the interactee and the server computer and connected to at least one of the interactee and the server computer either by wire or wirelessly;
The movable unit includes one or more movable parts;
A motor for driving each of the one or more movable parts;
Driving units for driving the motors;
With
7. The controller according to claim 1, wherein one of the interactee and the server computer includes a controller that outputs an operation command signal to the drive unit. 8. Spoken dialogue system. A movable unit provided separately from the interactee and connected to at least one of the interactee and the server computer either by wire or wirelessly;
The movable unit includes one or more movable parts;
A motor for moving each of the one or more movable parts;
With
A drive unit for driving each of the motors is provided in either the interactee or the server computer,
7. The controller according to claim 1, wherein a controller that outputs an operation command signal to the drive unit is provided in either the object to be interacted with or the server computer. 8. Voice dialogue system.   The spoken dialogue system according to any one of claims 10 to 12, wherein the interactee and the movable unit are configured to be freely attachable. In the voice interaction system according to any one of claims 1 to 9, an image display means for displaying a predetermined image is provided either integrally with the interactee or separately.
The image information storage unit in which the predetermined image information is stored in advance is mounted on either the interactee or the server computer,
When the person requests the predetermined image information via the sound conversion means, or when the person permits the predetermined image information via the sound conversion means, the predetermined image information is used to A spoken dialogue system, wherein the predetermined image information is read from the image information storage unit and displayed on the image display means in any case where the dialogue body displays the predetermined image by itself. 14. The spoken dialogue system according to claim 10, wherein an image display means for displaying a predetermined image is further provided in either the interactee or the movable unit, Connected to at least one of the body, the server computer, and the movable unit by wire or wireless,
The image information storage unit in which the predetermined image information is stored in advance is mounted on any of the interactee, the server computer, and the movable unit,
When the person requests the predetermined image information via the sound conversion means, or when the person permits the predetermined image information via the sound conversion means, the predetermined image information is used to A spoken dialogue system, wherein the predetermined image information is read from the image information storage unit and displayed on the image display means in any case where the dialogue body displays the predetermined image by itself. 14. The voice interaction system according to claim 10, further comprising an image display means for displaying a predetermined image provided separately from both the interactee and the movable unit. It is connected to at least one of the interactive body, the server computer, and the movable unit by either wired or wireless,
The image information storage unit in which the predetermined image information is stored in advance is mounted on any of the interactee, the server computer, and the movable unit,
When the person requests the predetermined image information via the sound conversion means, or when the person permits the predetermined image information via the sound conversion means, the predetermined image information is used to A spoken dialogue system, wherein the predetermined image information is read from the image information storage unit and displayed on the image display means in any case where the dialogue body displays the predetermined image by itself. The image information storage unit is configured to be freely connected to the Internet,
The voice dialogue system according to any one of claims 14 to 16, wherein the image information can be downloaded from a predetermined storage location on the Internet. An imaging means capable of imaging a predetermined object including the person is configured to be integral with or separate from the interactee,
The image recognition means for recognizing the predetermined object from the image data picked up by the image pickup means is mounted on either the interactee or the server computer. 9. The voice interaction system according to any one of claims 14 and 14. An imaging means capable of imaging a predetermined object including the person is provided in either the interactee or the movable unit, and is wired to at least one of the interactee, the server computer, and the movable unit. And wirelessly connected,
The image recognition means for recognizing the predetermined object from the image data picked up by the image pickup means is mounted on at least one of the interactee, the server computer, and the movable unit. The voice interactive system according to any one of claims 10 to 13, 15 and 16. An imaging means capable of imaging a predetermined object including the person is provided separately from either the interacted body or the movable unit, and at least one of the interacted body, the server computer, and the movable unit. Connected to either cable or wirelessly,
The image recognition means for recognizing the predetermined object from the image data picked up by the image pickup means is mounted on at least one of the interactee, the server computer, and the movable unit. The voice interactive system according to any one of claims 10 to 13, 15 and 16.   The controller outputs the command signal to the drive unit so that the movable unit performs a predetermined communication operation in at least one of a case where a dialogue with the person is performed and a predetermined explanation is performed. 21. The spoken dialogue system according to any one of claims 7 to 20. The movable part is arranged at a position for operating a predetermined device;
When the voice of the person is an instruction to operate a predetermined device, when the voice of the person is permission to operate the predetermined device, when operating the predetermined device by a predetermined operation input means, The said controller outputs the said command signal to the said drive part so that the said predetermined | prescribed apparatus may be operated when the automatic execution program to operate is performed, The Claim 13 thru | or 13 characterized by the above-mentioned. The spoken dialogue system according to claim 15.   The controller is configured so that the imaging unit images a predetermined object including the person and the image recognition unit performs a predetermined communication operation with the person based on the result of the recognition of the predetermined object. 21. The spoken dialogue system according to claim 18, wherein the command signal is output to the drive unit.   The imaging means picks up a predetermined object including the person, and the image recognition means selects at least one of the sound generation data based on the result of recognition of the predetermined object, and the sound generation 21. The spoken dialogue system according to any one of claims 18 to 20, wherein pronunciation is made to the person via means. The imaging means images the operation means of the predetermined device,
When the voice of the person is an instruction to operate a predetermined device, when the voice of the person is permission to operate the predetermined device, when operating the predetermined device by a predetermined operation input means, When the automatic execution program to be operated is executed, based on the result of the image recognition means recognizing the position of the operation means, the movable part and the interactee move to the operation position of the means, 21. The spoken dialogue system according to claim 18, wherein the controller outputs the command signal to the drive unit so as to operate a predetermined device. The imaging means is configured to image the progress of the table game, and the image recognition means is configured to recognize the image of the progress of the table game.
An operation determining means for determining a next operation of the movable part from the progress status recognized by the image recognition means;
21. The controller according to claim 18, wherein the controller outputs the command signal to the driving unit so that the movable unit executes a next operation determined by the operation determining unit. The spoken dialogue system according to one.   21. The controller according to claim 18, wherein the controller outputs the command signal to the drive unit to move the movable unit to search for a predetermined object including the person. Voice dialogue system. According to the first embodiment, a tracking program for tracking the predetermined object recognized by the image recognition means is mounted on either the interactee or the server computer,
21. The moving unit is moved by outputting the command signal from the controller to the driving unit so that the imaging unit tracks a predetermined object including the person. The spoken dialogue system according to any one of the above. 29. The voice interaction system according to any one of claims 1 to 28, wherein an operation signal output means for outputting the operation signal is provided to the operation means of an operation body further comprising an operation means operated by an operation signal. It is mounted on at least one of the dialog and the server computer,
The voice interaction system, wherein the operation means and the operation signal output means are connected by one of wireless and wired.   The spoken dialogue system according to any one of claims 1 to 30, wherein the interactee is configured by a mobile phone.   The spoken dialogue system according to any one of claims 1 to 30, wherein the interactee is configured by a computer.   The spoken dialogue system according to any one of claims 1 to 30, wherein the interactee is configured by a game machine.   The spoken dialogue system according to any one of claims 1 to 30, wherein the interactee is configured by a camera.   The spoken dialogue system according to any one of claims 1 to 30, wherein the object to be interacted with is constituted by a robot.   The spoken dialogue system according to any one of claims 1 to 30, wherein the object to be interacted with is constituted by any one of a doll, a stuffed toy, and a toy.

Images