JP2002182679A - Apparatus control method using speech recognition and apparatus control system using speech recognition as well as recording medium recorded with apparatus control program using speech recognition - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problems that, when plural apparatus having a speech recognition function exist in a limited space and if a speech command is applied to any thereof, the other apparatus make recognition operation as well and makes erroneous operation in many cases. SOLUTION: The plural apparatus (air conditioner 2, TV 3, acoustic apparatus 4, etc.), which have the speech recognition function and exists in one room is connected to a network 10 and the information individually possessed by the respective apparatus is exchanged with each other through the network 10. The information of the other apparatus sent through the network 10 in addition to the information possessed by user's own apparatus is referenced with respect to the speech command uttered by the user, by which the arrangement relations of the respective apparatus and the noise information collected by the respective apparatus are referenced and the speech recognition is carried out.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to voice recognition in which a plurality of devices such as home appliances having a voice recognition function exist in a limited space, and these devices recognize voice commands and perform operation control. The present invention relates to a device control method used, a device control system using voice recognition, and a recording medium recording a device control program using voice recognition.

[0002]

2. Description of the Related Art In recent years, microcomputers (referred to as microcomputers) have been used in a wide range of fields due to higher performance and lower prices of semiconductor products. In particular, microcomputers are used in many home electric appliances (home electric appliances), and multi-functionality and high performance are further increasing.

As described above, since microcomputers can be easily mounted on home electric appliances and the like, it has become easy to provide various kinds of functions that have not been considered so far in such devices. For example, a voice recognition function or a voice synthesis function is one example, and various devices having a voice interactive user interface function by providing the voice recognition function or the voice synthesis function have been considered. The same can be said for other than home appliances.

[0004]

Consider a situation in which a plurality of devices having such a voice interactive user interface function exist in a limited space. FIG.
In one room 1 as a limited space, audio equipment such as an air conditioner (referred to as an air conditioner) 2, a television (referred to as a TV) 3, and a stereo as devices having a voice interactive user interface function. 4 shows a state where 4 exists.

As described above, when a plurality of devices having a voice interactive user interface function exist in one room 1, the user gives a voice command for causing the air conditioner 2 to perform some operation, for example. Then, the air conditioner 2 recognizes the voice command and performs an operation in accordance with the recognition result. At this time, other devices may also perform a voice recognition operation on the voice command and malfunction.

If a voice command issued by a user is
Even if the content is recognizable only by the air conditioner and not recognizable by the TV 3 or the audio device 4, the TV 3
In some cases, the audio device 4 also starts a voice recognition operation in an attempt to recognize the voice command, which may cause erroneous recognition and malfunction. In particular, devices that have a voice interaction function that responds to the voice command given by the user by voice from the device side have various problems such as a response that is completely unrelated to the voice command given by the user. Tends to occur.

Therefore, the present invention provides a method for controlling a plurality of devices such as home appliances having a voice recognition function in a limited space.
Avoids erroneous recognition and erroneous operations by allowing each device to perform voice recognition from the user while exchanging information with each other while performing independent operation as the device. It is another object of the present invention to make it possible to perform noise removal and the like functionally and to appropriately control equipment.

[0008]

In order to achieve the above object, a device control method using voice recognition according to the present invention comprises a plurality of devices having a voice recognition function in a limited space. A device control method using voice recognition in which a voice command is given to one of the devices, and the device given the voice command recognizes the voice command and performs predetermined operation control according to the recognition result. In, the plurality of devices are connected to a network, information exchanged by each device is exchanged with each other through the network, and in response to a voice command spoken by the user, in addition to the information held by the device itself, Voice recognition is performed with reference to information on other devices transmitted via the network, and operation control of the devices is performed according to the recognition result.

Further, in the device control system using voice recognition of the present invention, a plurality of devices having a voice recognition function exist in a limited space, and a voice command is given to any of these devices. In a device control system using voice recognition in which a device given the voice command recognizes the voice command and performs predetermined operation control in accordance with the recognition result, the plurality of devices are mutually Connected to a network so that information can be exchanged, each of the plurality of devices connected to the network includes a device operation unit originally included in the device and a user operation unit for setting an operation state of the device operation unit. And at least receive a voice command, recognize the voice command, and control the device operation unit based on the recognition result. It has a device operation control unit using voice recognition and a network connection unit for connecting its own device to a network, and mutually exchanges information individually owned by each of the plurality of devices via the network. In response to the voice command spoken by the user, voice recognition is performed with reference to the information of other devices sent via the network in addition to the information held by the user, and the voice recognition is performed according to the recognition result. The operation of the device is controlled.

In each of these inventions, the mutually exchanged information includes at least device identification information for identifying each device, and noise information collected by each device.

[0011] In the processing procedure until the operation control of the device according to the recognition result is performed, device identification information for identifying the respective device is obtained via the network, and the device identification information for identifying the device exists on the network. In addition to recognizing the devices to exchange information, measuring the positional relationship of each device, and then inputting a voice command, based on the positional relationship of each device, the voice command spoken by the user is transmitted to the own device. It is determined whether or not the voice command is issued to the own device, and if it is determined that the voice command is issued to the own device, the voice command is recognized and the device based on the recognition result is performed. Operation control.

When performing the voice recognition, the noise information collected by the respective devices is exchanged with each other, and using the noise information, noise superimposed on the voice command is removed to perform voice recognition. Like that.

At this time, the noise superimposed on the voice command includes a steady driving sound of the device or a steady sound that is constantly present in the environment, a voice generated by the operation of the device connected to the network, For the stationary sound, each device acquires the stationary noise information as stationary noise information, and the acquired stationary noise information is exchanged with another device through a network to exchange the stationary noise information with each other. When the data is stored in the device and speech recognition is performed, the stationary noise information is removed from the speech command and speech recognition is performed.

[0014] In addition, as for the sound such as voice or music, a device that emits the sound obtains the sound as noise information in real time, and other devices connected to the network also transmit the noise information in real time through the network. When acquiring and performing voice recognition, the noise information is removed from the voice command to perform voice recognition.

[0015] In the speech recognition for the voice command performed by each device, the devices exchange information with each other so that a recognizable word in one device can be recognized by another device.

Further, the recording medium for recording the device control program using voice recognition according to the present invention connects a plurality of devices having a voice recognition function existing in a limited space to a network, and each device is connected to a network. As information to have individually,
At least, device identification information for identifying each device, noise information collected by each device can be exchanged with each other through the network, and the own device has a voice command spoken by the user. Performs voice recognition with reference to information of other devices sent via the network in addition to the information, and records a device control program using voice recognition for controlling operation of the device according to the recognition result. In the recording medium, the device control program acquires device identification information for identifying each device via the network, and recognizes a device to be exchanged for information existing on the network, A procedure for measuring the positional relationship of each device,
After the measurement of the positional relationship, the apparatus waits for a voice command from the user, and when the voice command is input, based on the positional relationship between the respective devices, whether the voice command spoken by the user has been issued to the own device. The procedure for determining whether or not the voice command has been issued to the own device. If the voice command is determined to have been issued to the own device, the voice command is recognized, and the operation of the device according to the recognition result is performed. And a procedure for performing control.

[0017] In the invention of the recording medium in which the device control program using the voice recognition is recorded, when performing the voice recognition, the noise information collected by the respective devices is exchanged with each other, and the noise information is used. In addition, the voice recognition is performed by removing noise superimposed on the voice command.

At this time, the noise superimposed on the voice command includes a steady driving sound of the device or a steady sound that is constantly present in the environment, a voice generated by the operation of the device connected to the network, and For the stationary sound, each device acquires the stationary noise information as stationary noise information, and the acquired stationary noise information is exchanged with another device through a network to exchange the stationary noise information with each other. When the data is stored in the device and speech recognition is performed, the stationary noise information is removed from the speech command and speech recognition is performed.

In addition, as for the sound such as voice and music, a device that emits the sound acquires the sound as noise information in real time, and other devices connected to the network also transmit the noise information in real time through the network. When acquiring and performing voice recognition, the noise information is removed from the voice command to perform voice recognition.

In the voice recognition for the voice command performed by each device, the devices exchange information with each other so that a recognizable word in one device can be recognized by another device.

As described above, according to the present invention, a plurality of devices having a voice recognition function are connected to a network, and voice recognition is performed while mutually exchanging information individually owned by each device via the network. Therefore, the operation of the device is controlled according to the recognition result.
As in the past, in response to a voice command spoken to one device by another user, another device performs an operation of recognizing the voice command, thereby preventing a malfunction such as a malfunction and preventing the user's intention. The operation control of the device can be performed accurately.

Note that the information individually owned by each device described above is at least device identification information for identifying each device and noise information collected by each device. You can know what devices are on the network, know the devices on the network that need to exchange information, and then send and receive sound between devices, and the arrival time of the sound From such, find the distance between each device,
Based on this, the positional relationship between the devices can be estimated.

Also, by sharing the noise information collected by a certain device with other devices, when recognizing a voice command, the voice recognition process can be performed after removing noise information superimposed on the voice command. A high recognition rate can be obtained.

Further, the processing procedure of the present invention recognizes what kind of equipment exists on the network by acquiring the equipment identification information for identifying each equipment through the network, The arrangement of the devices is estimated by measuring the positional relationship between the devices, and thereafter, the voice recognition process is performed while exchanging information between the input voice commands between the devices. With this, it is possible to accurately determine to which device the user's voice command is issued, and when it is determined that the voice command is directed to the own device, the recognition process for the voice command is performed. Since the operation of the device is controlled based on the recognition result, malfunction of the device not intended by the user can be prevented.

Also, noise information collected by a certain device is exchanged with each other, and noise superimposed on a voice command is removed using the noise information to perform voice recognition.

As described above, since all devices connected to the network can share the noise information, no matter which device receives the voice command, the noise superimposed on the voice command is appropriately removed, and then the voice command is removed. It can be recognized, and a high recognition rate can be obtained.

When the noise superimposed on the voice command is a stationary sound (such as an air conditioner operating sound) which is constantly present in the environment, the stationary sound is set as stationary noise information in advance in each device. Can be saved.

Therefore, when recognizing a voice command,
Even if the stationary noise information is superimposed on the voice command, by reading out the stored stationary noise information, the stationary noise information can be removed from the voice command to perform speech recognition. As described above, since appropriate noise removal can be performed on a voice command on which stationary noise information is superimposed, a high recognition rate can be obtained.

When the noise to be superimposed on the voice command is a voice or music emitted from a TV or an audio device, the device issuing the voice command acquires the sound information as noise information in real time and connects to the network. Other devices are also able to acquire the noise information in real time through a network.

Thus, when recognizing the voice command, the noise information is removed from the voice command to perform voice recognition. As described above, since a suitable noise removal can be performed for a voice command in which a sound of a TV or an audio device is superimposed as noise, a high recognition rate can be obtained.

Further, by sharing information, a recognizable word in a certain device can be recognized by another device, thereby preventing malfunction due to erroneous recognition. In other words, it goes without saying that in the conventional system in which each device independently recognizes, each device can recognize only words that can be recognized by itself. On the other hand, as in the present invention, if each device is connected to a network and can share each piece of information, words that can be recognized by each device can be regarded as words that can be recognized by all devices. it can. As a result, detailed and highly accurate recognition processing is performed,
Since confusing words and the like can be accurately recognized and processed, a malfunction due to erroneous recognition can be prevented.

[0032]

Embodiments of the present invention will be described below. The contents described in this embodiment are as follows.
It is a description of a device control method using voice recognition and a device control system using voice recognition according to the present invention, and a specific example of a device control program on a recording medium that stores a device control program using voice recognition according to the present invention. It also includes various processing contents.

In this embodiment, as described with reference to FIG. 5, an air conditioner 2 and a TV 3 are provided in one living space 1 as devices having a voice interactive user interface function.
In the present invention, these devices are connected to a network 10 as shown in FIG. 1, and each device can operate independently. In spite of this, each device can perform voice recognition while exchanging information with each other.

It should be noted that this network 10
For convenience, a network using a wired communication path is used, but a network using wireless communication using short-range wireless communication (such as Blue Tooth) may be used. In addition, a network using a wired communication path includes a method using electric wiring in a building or the like, and means for constructing the network is not limited in the present invention. Further, in this embodiment, a device having a voice interactive interface function is considered. However, the present invention may be any device that recognizes a voice command and performs an operation according to the recognition result. It is not always necessary to have a function of responding by voice to the user.

FIGS. 2 and 3 are block diagrams respectively showing the configuration of the device having the voice interactive user interface function shown in FIG.
(See FIG. 2) and TV3 (see FIG. 3) will be described.
Since these devices have a voice interactive user interface function, they have a voice recognition function and a voice synthesis function, and have a voice input unit and a voice output unit in accordance with those functions. Have. The details will be described below.

FIG. 2 shows the configuration of the air conditioner 2. The air conditioner 2 includes a device operating section 21 which operates as a normal air conditioner which has been conventionally used and an air conditioner such as start / stop of an air conditioner and timer setting. In addition to the user operation unit 22 in which various settings can be made by the user, the equipment control unit 23 using voice recognition for realizing a voice interactive user interface function, and the air conditioner 2
A network connection unit 24 for connecting to the network 0 is provided.

FIG. 3 shows the structure of the TV 3.
The air conditioner 2 basically has almost the same configuration as the air conditioner 2 shown in FIG. 2, and includes a device operation unit 31 that operates as a normal TV that has been used conventionally, a start / stop of the operation of the TV, a channel setting, and the like. In addition to the user operation unit 32 in which various settings made by a normal TV can be performed by the user, similarly to the air conditioner 2 in FIG. 2, a device control unit 33 using voice recognition for realizing a voice interactive user interface function. , T
A network connection unit 34 for connecting V3 to the network 10 is provided.

The equipment control units 23 and 33 using voice recognition in the air conditioner 2 or the TV 3 have the same configuration, and therefore the same parts will be described with the same reference numerals. In this embodiment, since a voice interactive user interface function is provided, a microphone 41 for inputting a voice command, an amplifier 42 for amplifying the voice input to the microphone 41, and an A for digitally converting the voice. A / D converter 43, a D / A converter 44 for converting voice data for response to the user into an analog signal, an amplifier 45 for amplifying the data, and a speaker 46 for outputting the same are provided. To generate voice data for response thereto, generate a device control signal corresponding to the recognition result, and further generate self-device information (for example, device identification information assigned to the The noise information collected by the device) to the network connection unit 24
(For the TV 3, the network connection unit 34), the information is transmitted to the network 10, and information from other devices existing on the network 10 (for example, device identification information assigned to each device and each device) The noise information collected by the network connection unit 24 (TV
In the case of No. 3, an information processing unit 47 that receives and processes it via the network connection unit 34) and an information processing unit 4
That stores the operation processing program executed by PC7
An information recording unit 48 including a RAM for storing various information necessary for processing performed by the information processing unit 47, such as M, the above-described self-device information, and information from other devices.

The information processing section 47 is provided by the user operation section 2
2 (the user operation unit 32 in the case of the TV 3), and the user operation unit 22 (the user operation unit 32 in the case of the TV 3) controls the volume of the output sound and the like and controls the device operation unit 21 (the TV 3). In this case, the user can set various items such as control contents for the device operation unit 31).

Since the TV 3 originally has a function of emitting sound, an amplifier and a speaker for outputting sound as a TV and an amplifier and a speaker for responding to a user can be shared. Therefore, in FIG. 3, the audio output from the device operation unit 31 as the TV 3 and the response output to the user are both amplified by the amplifier 45 and then output from the speaker 46.

In the air conditioner 2, the driving sound is usually always generated as stationary noise during the operation, but the driving sound may be superimposed on the voice command, which may adversely affect the recognition performance. .

In order to cope with this, each device collects its driving sound with its own microphone 41, analyzes it in the information processing section 47 and outputs it as noise information, and the noise information is stored in the information storage section 48. And also sends it to the network 10 so that each device can share the noise information. When recognizing the voice command, the voice recognition is performed after removing the driving sound superimposed on the voice command as noise using the noise information.

Note that such stationary noise may not only be generated by equipment connected to the network 10 but may also be generated by equipment not connected to the network 10. In some cases. These stationary noises also occur in network 1
Each device connected to the communication device 0 collects the information with its own microphone 41, analyzes the information with the information processing unit 47, outputs the noise information, stores the noise information in the information storage unit 48, and stores the noise information in the network 10. , So that the devices share the noise information.

On the other hand, in the case of the TV 3, the audio of the TV 3 (the audio on the output side of the amplifier 45) is input to the information processing section 47 via the A / D converter 43 in real time, and analyzed by the information processing section 47. When the voice command is output as noise information and the voice command is used for voice recognition using the noise information, the voice recognition is performed while removing the TV voice superimposed on the voice command as noise. Further, the noise information obtained by being analyzed by the information processing unit 47 can be given to other devices in real time via the network 10, and thereby,
When performing voice recognition for a command from a user, the other devices also perform voice recognition while removing the TV voice superimposed on the voice command as noise.

Also, in FIG.
There is an acoustic device 4 in addition to the TV and the TV 3, and the acoustic device 4 can be considered in the same manner as in FIGS. In addition,
Since the audio device 4 originally has a function of outputting sound similarly to the TV 3, the audio device 4 has the same function as the TV 3 shown in FIG.
An amplifier or speaker for audio output as the audio device 4 and an amplifier or speaker for user response can be shared.

Further, similarly to the TV 3, the sound emitted from the audio equipment 4 is taken out from the output side of the amplifier 45 and input to the information processing section 47 in real time.
7 to obtain noise information, and using the noise information,
When recognizing a voice command, a TV voice superimposed on the voice command is removed as noise.
This noise information can be provided to other devices in real time via the network 10.

As described above, the present invention considers a situation where a plurality of devices having a voice interactive user interface function exist in one room 1 as a certain limited space. Each device (here, the air conditioner 2, the TV 3, and the audio device 4) performs its own operation independently and in parallel while operating as its own information processing unit 4.
7 transmits its own device information to the network 10 and receives information (other device information) from other devices existing on the network 10 and exchanges information with each other to control devices using voice recognition. To do. Hereinafter, the operation will be described with reference to the flowchart of FIG.

The flowchart of FIG. 4 shows the processing performed by the information processing section 47 in each device.
When the operation of each device is started (for example, when the power switch or the like is turned on and the operation of the device is started), the processing shown in FIG. 4 is performed in parallel in each device.

As the processing procedure, when individual devices are connected to the network 10 (step s1), the respective devices mutually exchange their own device information (step s2). Thus, it is possible to know which device is connected to the network 10 from the viewpoint of the own device. This is because when a device is connected to the network 10, device identification information (referred to as a device ID) of each device is transmitted over the network 10, and the device ID is acquired by another device. Is connected to the network 10.

Then, it is determined whether or not to measure the positional relationship of each device for each device (step s).
3). This is to check whether or not a plurality of devices currently connected to the network 10 are in a positional relationship from the viewpoint of the own device. The measurement of the positional relationship is as follows.
The sound of a certain device is acquired by the microphone of another device (for example, the sound emitted from the speaker 46 of the TV 3 is acquired by the microphone 41 of the air conditioner 2), and the distance between the two devices is determined by the delay in the arrival time of the sound. Is measured, and the positional relationship is checked based on the distance. For example, when three devices (air conditioner 2, TV 3, and audio device 4) are considered as in this embodiment, if the distance between the three devices is known, the room 1 shown in FIG. It is possible to estimate the positional relationship between the three devices within the device.

The measurement of the positional relationship is performed only when the mode is the positional relationship measuring mode. The conditions for setting the positional relationship measurement mode include, for example, a case where a self-device newly joins the network 10 and a case where another device newly joins the network 10. And so on.

As an example of the condition for the above-described positional relationship measurement mode, when the own device newly joins the network 10 or when another device newly joins the network 10, for example, TV
3 is already operating, these two devices are already connected to the network 10, and the power switch of the audio device 4 is newly turned on and connected to the network 10. is there.

In this case, from the viewpoint of the audio device 4, the self-device has newly joined the network 10, so that the audio device 4 enters the positional relationship measurement mode. On the other hand, the air conditioner 2 already connected to the network 10
For the TV 3 and the TV 3, since the audio device 4 is newly connected to the network 10, when the audio device 4 detects this, the mode is set to the position measurement mode at that time.

As described above, when the mode is set to the position measurement mode, the position is measured by the method described above (step s4), and the positional relationship of each device is obtained, and other devices are viewed from their own devices. Estimate the positional relationship between the devices.

Next, it is checked whether or not to perform noise analysis (step s5). If it is necessary to perform noise analysis, noise analysis is performed (step s6). The noise here is, as described above, a steady noise existing in the environment, such as the operating noise of the air conditioner 2 and the operating noise of other devices. These stationary noises are input by their respective microphones connected to the network 10 using their own microphones, and the respective devices analyze the noises. Then, the analysis result is stored in its own information storage unit 48 as stationary noise information, and is also transmitted to other devices via the network 10 so that each device shares the stationary noise information. I do.

If there is no stationary noise, the processing in step s6 is unnecessary, and even if there is stationary noise, once the stationary noise information is obtained, the processing is performed. After that, it is not necessary to perform the noise analysis processing in particular, but when there is a large change in the stationary noise,
It is desirable to perform the noise analysis processing again. Examples of such a large change in the stationary noise include, for example, a case where the source of the stationary noise is an air conditioner, a case where the setting of the operation content is changed by the user, and the like (for example, a case where the From "weak" to "strong").

In this way, after the measurement of the positional relationship is completed and the noise is analyzed for stationary noise and the like, each device is in a state of waiting for the input of a voice command from the user (step s7). ). Here, when a voice command is issued and input to the microphone of each device, each device enters a voice recognition processing mode (step s8). In the voice recognition processing mode, each device exchanges information with each other via the network 10, determines which device the user has given a voice command to, and determines whether the device given the voice command has a voice. Perform voice recognition for commands.

In the process, the device specifies the device to which the user has issued the voice command based on the positional relationship between the devices. For example, if it is determined that the user's voice command is given to the air conditioner 2, the air conditioner 2 performs an operation based on the recognition result of the user's voice command. Then, when performing the recognition process for the voice command, the voice recognition process is performed after removing noise superimposed on the voice command.

Here, the noise information refers to noise information obtained by analyzing the steady driving sound generated by the air conditioner 2 or the like, or sound such as voice or music generated by the TV 3 or the audio equipment 4. This is the noise information obtained as a result. Then, the noise information of the known sound source is collected by a device that is the source of the noise, analyzed, and transmitted to the network 10 as noise information. Thereby, other devices connected to the network 10 can also acquire the noise information, and all the devices connected to the network 10 share the noise information.

Accordingly, when recognizing a voice command, it is possible to recognize the voice command after removing those noises superimposed on the voice command.

As described above, for the steady operation sound generated by the air conditioner 2 or the like, the collected noise can be analyzed in advance and the noise can be stored in the information storage unit 48 of each device. . Therefore, when recognizing voice,
The noise information is read from the information storage unit 48, and the operation sound of the air conditioner 2 superimposed on the voice command is removed to perform voice recognition.

On the other hand, TV3 superimposed on the voice command
It is necessary to recognize the sound emitted from the audio device 4 by removing noise while analyzing noise information in real time.
Therefore, it is necessary to acquire the sound information from the TV 3 or the audio device 4 in real time and send the obtained sound to other devices in real time. In this case, the actual voice recognition processing may be performed with a slight time delay while synchronizing the two and buffering voice commands from the user and sound information from the TV 3 and the audio device 4. it can.

As described above, when a voice command is given by the user, it is specified to which device the user has spoken the voice command based on the positional relationship between the devices. For example, by using the timing of the time when each device inputs the voice uttered by the user, the power of the input voice, and the like, further, it is analyzed from the positional relationship of each device to which device the user uttered. It becomes possible.

Then, the device (here, the air conditioner 2) to which the voice command from the user has been given performs voice recognition processing while removing noise from the user's voice command, and performs an operation on the recognition result. Note that information is always exchanged with other devices even when the voice recognition processing is being performed.

The operation procedure for the above speech recognition result is as follows.
First, it is determined whether or not a response is made by voice (step s9). In other words, if the air conditioner 2 is of the voice interactive type and needs to respond by voice, it responds by voice to the user's voice command (step s).
10) Next, it is determined whether or not to control the device according to the recognition result (step s11). If the device is to be controlled, the device is controlled according to the recognition result (step s11). s12).

For example, if the voice command of the user is “switch off”, the voice recognition is performed, and based on the recognition result, for example, a response such as “switch off” from the device side to the user is given. And then switch off the device (in this case,
Control such as stopping the operation of the air conditioner 2) is performed.

On the other hand, if the determination in step s9 is that the voice response is not to be made, it is directly determined whether or not to control the device based on the recognition result (step s11). If the control is to be performed, the device is controlled based on the recognition result (step s).
12). For example, if the voice command of the user is “switch off”, the voice recognition is performed, and based on the recognition result, the switch is turned off and the device (in this case,
Control such as stopping the operation of the air conditioner 2) is performed.

If the determination in step s9 is that no response is made by voice and the determination in step s11 is not to control the equipment, the process returns to step s2. Return, step s2
After s6, the process enters a process of waiting for the input of the next voice command in step s7. At this time, if it is not necessary to perform the measurement of the positional relationship, the measurement of the stationary noise, or the like, steps s2 to s6 may be omitted and the process may jump directly to step s7.

As described above, in this embodiment, in one room 1 as a limited space, the air conditioner 2, the TV 3, and the audio device 4 are provided as devices having a voice interactive user interface. The devices exist and are connected to the network 10 so that the devices can mutually exchange information while performing operations as the devices independently and in parallel.

As a result, each device is
It is possible to recognize what kind of equipment exists on the network 10 and to estimate what kind of positional relationship each equipment has. It can be determined whether a voice command has been issued. Further, each device can share noise information output from another device.

As described above, each device is connected to the network 10 and exchanges information with each other.
Since it is possible to determine on which device the user is issuing a voice command to each device,
It is possible to prevent a device that is not intended by the user from malfunctioning.

Further, when a device collects voice or music emitted from a certain device or the above-mentioned stationary noise information, the collected noise can be given to other devices through the network 10. When recognizing, even if those noises are superimposed on the voice command,
The speech recognition processing can be performed after removing the noise, and the speech recognition rate in an environment where the device is operating can be improved.

The ability to share information also allows each device to recognize words that can be independently recognized by other devices, and has the effect of preventing malfunction due to erroneous recognition. That is, in the conventional system in which each device independently recognizes, for example, the air conditioner 2 can recognize 20 words, the TV 3 can recognize 30 words, and the audio device 4 can recognize 10 words. If so, it goes without saying that each device can only recognize words that can be recognized by itself.

Therefore, when these devices are present in one limited space, and the operation is controlled by a voice command spoken by the user, the user can control the air conditioner 2 for example.
If only the air conditioner 2 utters a voice command that can be recognized, the voice command
The device is also input to other devices, and the device other than the air conditioner 2 tries to forcibly recognize it. Then, there is a possibility that a device other than the air conditioner 2 recognizes the command as a command relatively close to the voice command and performs operation control according to the recognition result.

On the other hand, as in the present invention, if each device is connected to a network and can share each information, 20 words recognizable by the air conditioner 2, 30 words recognizable by the TV 3, All 10 words that can be recognized by the audio device 4 can be recognized words.

For example, consider the case where the user issues a voice command “switch off” to air conditioner 2. This voice command “switch off”
It is assumed that the command is common to all devices and can be recognized by any device. Therefore, if one device responds to the user such as "which device" and the user utters "air conditioner", the "air conditioner" uttered by the user is reciprocal in all devices. As a result, the voice recognition is performed while exchanging information. As a result, only the air conditioner 2 can perform an operation in response to the voice command of “switch off” of the user.

This is because each device is connected to the network 1
0 and can be shared by recognizable words. That is, even if the air conditioner 2 has the word “air conditioner” as a recognizable word,
The TV 3 and the audio device 4 are each independently used as an “air conditioner”
Usually do not have as a recognizable word,
As described above, by sharing recognizable words, words that cannot be recognized originally can be recognized.

As a result, fine and accurate recognition processing is performed, so that confusing words and the like can be accurately recognized, so that malfunction due to erroneous recognition can be prevented.

The present invention is not limited to the embodiments described above, but can be variously modified without departing from the gist of the present invention. For example, in the above-described embodiment, a device having a voice interactive interface function, that is, a function of recognizing a user's voice command, performing a response by voice, and performing device control according to the recognition result. However, the present invention does not necessarily require a function of making a voice response to the user.

Further, all the devices connected to the network 10 need not have the function of performing voice recognition and controlling the operation of the devices according to the recognition result. For example, devices that emit sounds such as voice and music, such as the TV 3 and the audio device 4, are connected to the network 10 even if they do not have a voice recognition function and are not devices to be controlled by voice commands. In addition, it is also possible to provide a sound such as a sound or music emitted by these devices as noise information to another device connected to the network 10 and having a voice recognition function.

As a result, the TV 3 and the audio device 4
When a voice command from a user is given to a device having a voice recognition function while the device is operating, the TV 3 or the audio device 4 superimposed on the voice command.
After removing such sounds, voice recognition can be performed.

In the above-described embodiment, home appliances are mainly assumed as devices to be controlled. However, the present invention is not limited to home appliances, and voice commands are recognized and the recognition result is obtained. The present invention can be widely applied to a case where a plurality of devices having a voice recognition function performing corresponding operations exist in a limited space.

According to the present invention, a processing program describing processing procedures for realizing the above-described present invention is created, and the processing program is recorded on a recording medium such as a floppy disk, an optical disk, or a hard disk. The present invention also includes a recording medium on which the processing program is recorded. Further, the processing program may be obtained from a network.

[0084]

As described above, according to the present invention, a plurality of devices having a voice recognition function are connected to a network, and information individually held by each device is mutually exchanged via the network. While performing, the voice recognition is performed, and the operation of the device is controlled according to the recognition result. Therefore, it is possible to accurately determine to which device the user's voice command is issued, It is possible to prevent unintended devices from malfunctioning.

Further, since the information can be exchanged among the devices, the noise information collected by a certain device can be shared by all the devices connected to the network, so that the voice command is given to any device. Also, voice recognition can be performed after appropriately removing noise superimposed on the voice command, and a high recognition rate can be obtained.

Further, by sharing information, a recognizable word in a certain device can be recognized by another device, thereby preventing malfunction due to erroneous recognition. In other words, it goes without saying that in the conventional system in which each device independently recognizes, each device can recognize only words that can be recognized by itself. On the other hand, as in the present invention, if each device is connected to a network and can share each piece of information, words that can be recognized by each device can be regarded as words that can be recognized by all devices. it can.

As a result, fine and accurate recognition processing is performed, so that confusing words and the like can be accurately recognized, so that malfunction due to erroneous recognition can be prevented.

[Brief description of the drawings]

FIG. 1 is a diagram showing a device arrangement example for explaining an embodiment of the present invention, schematically showing a state where devices having a plurality of voice recognition functions are connected to a network in a limited space. It is.

FIG. 2 is a block diagram showing a configuration diagram of an air conditioner as the device shown in FIG.

FIG. 3 is a block diagram showing a configuration diagram of a TV as the device shown in FIG. 1;

FIG. 4 is a flowchart illustrating a processing procedure according to the embodiment of the present invention.

FIG. 5 is a diagram illustrating a conventional technique in a case where a plurality of devices having a voice recognition function exist in a limited space.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Room as a limited space 2 Air conditioner 3 TV 4 Audio equipment 10 Network 21 Equipment operation part in air conditioner 22 User control part in air conditioner 23 Equipment control part using voice recognition in air conditioner 24 Network connection part in air conditioner 31 Equipment in TV Operating unit 32 User control unit in TV 33 Device control unit using voice recognition in TV 34 Network connection unit in TV 41 Microphone 42 Amplifier 43 A / D converter 44 D / A converter 45 Amplifier 46 Speaker 47 Information processing unit 48 Information storage unit

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification code FI Theme coat ゛ (Reference) H04Q 9/00 301 H04Q 9/00 331A 311 G10L 3/00 551Z 321 531P 331 3/02 301D

Claims (16)

[Claims] A plurality of devices having a voice recognition function are present in a limited space, and when a voice command is given to any of these devices, the device given the voice command receives the voice command. In a device control method using voice recognition for performing predetermined operation control according to the recognition result based on the recognition result, the plurality of devices are connected to a network, and information individually owned by each device is transmitted via the network. It exchanges each other, and performs voice recognition for voice commands spoken by the user by referring to information of other devices sent through the network in addition to the information of the own device, and performs the recognition. A device control method using voice recognition, wherein operation control of the device is performed according to the result. 2. The speech recognition according to claim 1, wherein said mutually exchanged information includes at least device identification information for identifying each device, and noise information collected by each device. Device control method using 3. A processing procedure until the operation control of a device according to the recognition result is performed is performed by acquiring device identification information for identifying the respective devices via the network, and acquiring the device identification information on the network. In addition to recognizing the devices to exchange information, measuring the positional relationship of each device, and then inputting a voice command, based on the positional relationship of each device, the voice command spoken by the user is transmitted to the own device. It is determined whether or not the voice command is issued to the own device, and if it is determined that the voice command is issued to the own device, the voice command is recognized and the device based on the recognition result is performed. 3. The apparatus control method according to claim 2, wherein the operation control is performed. 4. When the voice recognition is performed, noise information collected by the respective devices is exchanged with each other, and noise superimposed on a voice command is removed using the noise information to perform voice recognition. 4. The method according to claim 2, wherein
A device control method using the described speech recognition. 5. The noise superimposed on the voice command includes a steady driving sound of the device or a steady sound that is constantly present on the environment, and a voice or music generated by the operation of the device connected to the network. For the stationary sound, each device acquires the stationary noise information as stationary noise information, and exchanges the acquired stationary noise information with another device through a network to exchange each device with each other. When performing speech recognition, the stationary noise information is removed from the voice command and speech recognition is performed. For the sound such as the voice or music, the device that emits the sound converts the sound in real time into noise information. As well as other devices connected to the network also acquire the noise information in real time through the network,
5. The apparatus control method using voice recognition according to claim 4, wherein when performing voice recognition, the noise information is removed from the voice command and voice recognition is performed. 6. The voice recognition for a voice command performed by each device is characterized in that the devices exchange information with each other so that a recognizable word in one device can be recognized by another device. An apparatus control method using voice recognition according to any one of claims 1 to 5. 7. A plurality of devices having a voice recognition function are present in a limited space, and when a voice command is given to any of these devices, the device to which the voice command is given becomes the voice command. In a device control system using voice recognition that performs predetermined operation control according to the recognition result by recognizing the plurality of devices, the plurality of devices are connected to a network such that each device can mutually exchange information, Each of the plurality of devices connected to the network has a device operation unit originally included in the device and a user operation unit for setting an operation state of the device operation unit, and at least receives a voice command and receives the voice command. And a device operation control unit using voice recognition for controlling the device operation unit based on the recognition result. It has a network connection unit for connecting its own device, and mutually exchanges information individually possessed by the plurality of devices via the network, for voice commands spoken by the user, Speech recognition characterized by performing speech recognition by referring to information of another device sent via the network in addition to information owned by itself, and performing operation control of the device according to the recognition result. Equipment control system using. 8. The speech recognition according to claim 7, wherein the mutually exchanged information includes at least device identification information for identifying each device, and noise information collected by each device. Equipment control system using. 9. The processing procedure until the operation control of the device according to the recognition result performed by the device operation control unit using the speech recognition is performed by transmitting device identification information for identifying each device to the network. Acquisition via, and recognize the devices that exist on the network to exchange information, measure the positional relationship of each device, and then
When a voice command is input, it is determined whether or not a voice command spoken by the user has been issued to the own device based on the positional relationship between the respective devices, and the voice command is issued to the own device. 9. A device control system using voice recognition according to claim 8, wherein when it is determined that the voice command has been received, the voice command is recognized and the operation of the device is controlled based on the recognition result. . 10. When performing the voice recognition, the respective devices exchange noise information collected with each other, and use the noise information to remove noise superimposed on a voice command to perform voice recognition. An apparatus control system using voice recognition according to claim 8 or 9, wherein: 11. The noise superimposed on the voice command includes a steady driving sound of the device or a steady sound constantly present in the environment, and a voice or music generated by the operation of the device connected to the network. For the stationary sound, each device acquires the stationary noise information as stationary noise information, and exchanges the acquired stationary noise information with another device through a network to exchange each device with each other. When performing speech recognition, the stationary noise information is removed from the voice command and speech recognition is performed. For the sound such as the voice or music, the device that emits the sound converts the sound in real time into noise information. As well as other devices connected to the network also acquire the noise information in real time through the network,
The apparatus control system using voice recognition according to claim 10, wherein, when performing voice recognition, the noise information is removed from the voice command to perform voice recognition. 12. The voice recognition for a voice command performed by each device, wherein each device exchanges information with each other so that a recognizable word in one device can be recognized by another device. An apparatus control system using voice recognition according to any one of claims 7 to 11. 13. A device identification device for connecting a plurality of devices having a voice recognition function existing in a limited space to a network and identifying at least each device as information individually owned by each device. Information, the noise information collected by each device can be exchanged with each other via the network, and in response to a voice command spoken by the user, in addition to the information possessed by the device itself, transmitted via the network A recording medium that records a device control program using voice recognition that performs voice recognition with reference to information of another device that comes and performs operation control of the device according to the recognition result, and the device control program is It is necessary to acquire device identification information for identifying each device via the network and exchange information existing on the network. A procedure for recognizing the device and measuring the positional relationship between the devices, and after measuring the positional relationship, waiting for a voice command from the user, and when a voice command is input, the positional relationship between the devices. A procedure for determining whether or not the voice command spoken by the user has been issued to the own device; and, if the voice command has been determined to be issued to the own device, Recording a device control program using voice recognition, comprising: performing a recognition process for a voice command and controlling operation of the device in accordance with the recognition result. 14. When performing the voice recognition, the respective devices exchange noise information collected with each other, and use the noise information to remove noise superimposed on a voice command to perform voice recognition. 14. A recording medium storing a device control program using voice recognition according to claim 13. 15. The noise superimposed on the voice command,
A steady driving sound of a device or a steady sound that is constantly present on the environment, and a sound such as a sound or music generated by the operation of a device connected to a network. When the device obtains the stationary noise information, and exchanges the acquired stationary noise information with other devices through the network and saves them in each device, and performs speech recognition, The noise information is removed from the voice command to perform voice recognition. For the sound such as the voice or music, a device that emits the sound obtains the sound as noise information in real time, and other devices connected to the network. Also obtains the noise information in real time through the network,
15. The recording medium according to claim 14, wherein when performing voice recognition, the noise information is removed from the voice command to perform voice recognition. 16. The speech recognition for a speech command performed by each device is characterized in that each device exchanges information with each other so that a recognizable word in one device can be recognized by another device. A recording medium recording a device control program using voice recognition according to any one of claims 13 to 15.