Information processing device

Abstract

To utilize multiple speech recognition devices linked with each other.SOLUTION: A speech recognition device consists of: a speech input unit; a speech output unit; a communication control unit that transmits and receives data to and from other speech recognition devices; a conversation mode execution unit that transmits speech data input from the speech input unit to the other speech recognition devices, and outputs the speech data received from the other speech recognition devices from the speech output unit; a speech recognition unit that converts speech input from the speech input unit into text data; a hot word detection unit that detects conversation activation hot words that instruct the conversation mode execution unit to activate from the text data; and a command transmission unit that transmits control commands to the other voice recognition devices. When the hot word detection unit detects the conversation activation hot words, the command transmission unit transmits the control commands to the other speech recognition devices to activate the conversation mode execution unit provided in the other speech recognition devices.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a voice recognition device and a method for coordinating voice recognition devices. [Background technology]

[0002] In recent years, speech recognition and analysis of the speech content of the speaker have become more common. A so-called smart speaker that outputs a response based on the user's voice from an attached speaker, or A voice recognition device called an AI speaker is being developed that uses voice recognition technology and artificial intelligence technology. For example, Patent Document 1 lists an example of speech recognition technology as The interpretation candidates obtained by applying the recognition algorithm are integrated to reduce redundancy. Present the user with an opportunity to choose from possible interpretations to provide a method "The guidelines are structured to present these options without duplication (summary excerpt)." In addition, Patent Document 2 states, "Speech recognition model and data in an automatic speech recognition system" As a feature to manage data usage, when users may use the system It states that "these data can be tracked to predict future outcomes (summary excerpt)." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2013-68952 A [Patent Document 2] Special Publication No. 2015-537258 Summary of the Invention [Problem to be solved by the invention]

[0004] The voice recognition devices such as the smart speakers mentioned above can A person in the vicinity of the device can give voice instructions, etc., which are then processed by the device and a response is obtained. However, there is no disclosure about using multiple devices in cooperation with each other. In other words, an example of use at home is when family members share the device in the living room to check the weather forecast, When you request information available on the Internet, such as news, music, etc., the corresponding content will be By simply outputting the voice, the device can be recognized by another voice recognition device in a room other than the living room, for example, a child's room. It is not assumed that there will be any communication or coordination between the device and the chair. Therefore, multiple voice recognition devices cannot be used in conjunction with each other, and There is room for innovation in new ways of using it.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and is a system for utilizing a plurality of voice recognition devices in cooperation with each other. The present invention provides a voice recognition device and a voice recognition device cooperation method that can be used The purpose is. [Means for solving the problem]

[0006] In order to achieve the above object, the present invention has the configurations described in the claims. Effect of the Invention

[0007] According to the present invention, a voice recognition device capable of using a plurality of voice recognition devices in cooperation with each other is provided. The present invention provides a method for linking a voice recognition device and a voice recognition device. The effects are shown in the following embodiments. [Brief description of the drawings]

[0008] [Figure 1]1 is a diagram showing a hardware configuration of a voice recognition device according to an embodiment of the present invention; [Diagram 2] Functional block diagram of the voice recognition device [Figure 3A] FIG. 1 is a diagram showing an example of hot word data stored in a reference memory; [Figure 3B] FIG. 1 is a diagram showing an example of voice authentication data stored in a reference memory. [Figure 4] A diagram showing a collaboration system using a voice recognition device [Diagram 5] Flowchart showing a first calling operation in a linkage system [Figure 6] FIG. 13 is a diagram showing an example of location estimation data. [Figure 7] A flowchart showing a first switching process between normal mode and conversation mode. [Figure 8] A flowchart showing a second switching process between normal mode and conversation mode. [Figure 9] Conceptual diagram showing the first setting process at the time of new installation [Figure 10] Conceptual diagram showing the second setting process for new installation [Figure 11] Flowchart showing the flow of the second setting process at the time of new installation [Figure 12] FIG. 13 is a diagram showing a schematic configuration of a coordination system for voice recognition devices in a house according to a second embodiment. [Figure 13] FIG. 13 is a diagram showing an example of usage status data in which usage status for a person is recorded for each time period; [Figure 14] FIG. 13 is a diagram showing an example of call priority data that records call destination priorities for a person by time period. [Figure 15] FIG. 1 is a diagram showing an example of connecting a voice recognition device and a mobile communication terminal with a dock. [Figure 16] Flowchart showing switching process to answering machine mode DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, examples of embodiments of the present invention will be described with reference to the drawings. The same functions are denoted by the same reference symbols, and duplicate explanations will be omitted.

[0010] First Embodiment 1 is a hardware configuration diagram of a voice recognition device 1 according to this embodiment. Device 1 may be a device dedicated to voice recognition, a mobile phone terminal, a smartphone, a personal computer, or any other device. Electronic devices with communication functions that have existed for a long time, such as personal computers, game consoles, etc. The voice recognition device 1 may also have a communication function such as a wired LAN or a wireless LAN. , wireless communication over mobile phone lines, Bluetooth (registered trademark), RFID and other proximity wireless , etc., and a communication interface corresponding to the communication function may be used. It has one or more.

[0011] Specifically, the voice recognition device 1 includes a CPU 101, a memory 103, an external interface Wired LAN I / F 104, wireless LAN I / F 105, and wireless communication I / F 1 06, a voice input unit 107 (for example, a microphone), a voice output unit 108 (for example, a speaker), a display The output units 109 (for example, liquid crystal displays) are connected to each other via the bus 102. 2 includes a human detection sensor I / F 110, a timer 111, an RTC 112, and a camera 113. It may be connected.

[0012] The memory 103 includes an internal memory 1031 that is a volatile memory and a non-volatile memory. The reference memory 1032 includes a

[0013] The human detection sensor I / F110 can be used with any type of sensor, such as a human presence sensor or a sound collection sensor. This is an interface for attaching an external human detection sensor.

[0014] FIG. 2 is a functional block diagram of the voice recognition device 1.

[0015] The voice recognition device 1 includes a voice processing engine 120. The voice processing engine 120 The main components are a voice processing unit 1201, a voice recognition unit 1202, a hot word detection unit 1203, and a voice analysis unit 1204. The image processing unit 1202 includes a feature analysis unit 1204 and a feature extraction unit 1205 .

[0016] The voice processing engine 120 is a CPU 101 that reads voice processing data stored in the reference memory 1032. The program is read and loaded into the internal memory 1031, and the program is processed according to the audio processing program. The functions of the voice processing engine 120 are realized by executing the above-mentioned processing.

[0017] Specifically, when a person speaks something to the voice recognition device 1, the voice is input to the voice input section. The voice (analog data) is captured in 107 and converted into digital voice data. will be done.

[0018] The audio processing unit 1201 performs adjustments such as removing ambient noise contained in the audio data.

[0019] The voice recognition unit 1202 performs voice recognition processing to convert voice data into character string data.

[0020] The hot word detection unit 1203 detects whether the character string data is an operation start for the voice recognition device 1. A specific phrase that requests startup, such as returning from standby mode (hereinafter referred to as "hot word") Determine whether the character string data contains

[0021] FIG. 3A is a diagram showing an example of hot word data 150 stored in the reference memory 1032. The hot word data 150 includes a registered hot word 1501 and A type 1502 that specifies the operation of the voice recognition device 1 of the hotkey 1501 and a registered hotkey Device-specific information for identifying the voice recognition device 1 that is called using the code 1501 is defined. The hot word detection unit 1203 detects the hot word by the call destination 1503. , hotword detection is performed based on whether the character string data is listed in the hotword data 150. Make an exit.

[0022] The voice analysis unit 1204 interprets what is spoken to the voice recognition device 1, i.e., converts the The response data and the control command corresponding to the data are determined, and the response data is output from the voice output unit 108. and outputs a control command to the CPU 101, and executes the process indicated by the audio data. 1 to execute the control command. For example, a control command may be to play a specific piece of music.

[0023] The voice recognition unit 1202 is not the voice recognition device 1 but is connected to the voice recognition device 1. The speech recognition process may be executed by the external server 201 (see FIG. 4). This reduces the load on the voice recognition device 1. When performing speech recognition processing in 1, the amount of data communication with the external server 201 can be reduced. can.

[0024] In addition, as a characteristic function of the voice recognition device 1 according to the first embodiment, In addition to working independently like a smartphone, it can also detect voices spoken to it in a specific location, such as inside a house or building. A private communication network (hereinafter, a home LAN 210: FIG. 4) is installed in the space. The voice can be transferred to another voice recognition device 1 existing on the same network (see FIG. 1 for an example) for conversation. Therefore, the hot word detection unit 1203 switches to a conversation mode for conversation. The hot word that is the trigger for the transition is detected. Furthermore, the voice recognition device 1 detects the hot word that is the trigger for the transition. Extract voice and image characteristics from people who can participate in conversations via 210 and match them with registered data It has a feature extraction unit 1205 that performs the determination.

[0025] FIG. 3B is a diagram showing an example of voice authentication data 160 stored in the reference memory 1032.

[0026] The voice authentication data 160 uniquely identifies people who can participate in a conversation over the home LAN 210. The speaker 1601 as the information to be used, and the speaker's attributes, for example, the voice recognition device 1 and the communication network A “master” who has the authority to set up the network, or a “master” who does not have the authority to set up the network and is connected to the home LAN 210 The speaker type 1602 indicates whether the person is a “general” or a “person” who has only the right to participate in the conversation. The data is associated with a speaker template 1603 indicating the characteristics.

[0027] FIG. 4 is a diagram showing a linkage system 100 using the voice recognition device 1, which is used in a home. This example shows an example of a case where the user is inside a house. This embodiment can also be applied to spaces where specific people gather, such as offices and classrooms. It is.

[0028] (First calling action) In FIG. 4, the first voice recognition system is installed in each room 1, room 2, room 3, and room 4 in the house. Device 1A, second voice recognition device 1B, third voice recognition device 1C, fourth voice recognition device The voice recognition device 1D has the same functions as the voice recognition device 1 in FIG. The first to fourth voice recognition devices 1A to 1D in the house are installed in the rooms 2 to 4, respectively. The second AP 2032 to the fourth AP 2034 are access points or wireless repeaters. The first to fourth voice signals are then connected to the router 202 installed in the room 1 via the four voice signals. Each of the recognition devices 1A to 1D is connected to the external Internet 200 via a router 202. is connected to

[0029] The first call operation in the linkage system 100 will be described below in accordance with the steps in FIG. 5. When starting the process of this step, the first to fourth voice recognition devices 1A to 1D are all powered on, and the voice input unit 107 and the voice processing engine 120 This state is called standby mode.

[0030] When person A in room 1 calls out to the first voice recognition device 1A, The voice is captured by the voice input unit 107 of the first voice recognition device 1A, and then a hot word detection The output unit 1203 judges whether the first hot word indicates a start request. When the detection unit 1203 determines that the call voice is the first hot word (S101 / Y s) The voice response data of a predetermined fixed phrase such as "Is there anything I can help you with?" is sent to the voice output unit. The hot word detection unit 1203 detects the first hot word from the voice analysis unit 108. 204, and the voice analysis unit 1204 issues an execution command to the normal mode execution unit 1406. This causes the first voice recognition device 1A to switch to the normal mode. This mode is an operation mode in which all of the functions of the first voice recognition device 1A can be executed.

[0031] If the hot word detection unit 1203 determines that the word is not a hot word (S101 / No), , maintain standby mode.

[0032] Next, if person A calls out to person B in another room, saying "B-kun!", The voice is input as voice data via the voice input unit 107, and then the voice is processed by the voice processing engine After the sound processing unit 1201 in 120 performs adjustments such as removing ambient noise, the hot word detection unit In 1203, whether the hot word is a second hot word (a hot word for requesting switching to a conversation mode) or not Determine (S102).

[0033] The voice data of the call "Mr. B!" is used as the hot word data 150 The hot word detection unit 1203 detects that the word "B-kun!" is the second hot word. If it is determined that the hot word is a word (S102 / Yes), the voice analysis unit 1204 receives the second hot word. In this embodiment, a hot word that triggers a transition to a conversation mode is output to the home. The name of a living person, but is not limited to this, and can be another fixed phrase, for example, It can be anything, such as "talk" or "connect."

[0034] The voice analysis unit 1204 analyzes that the second hot word is a request to switch to the conversation mode, The control command required for this is selected (S103). A mode switching command to switch chairs 1A to 1D to conversation mode, and a command to say "B-kun!" The voice data is transmitted from the first voice recognition device 1A to the second to fourth voice recognition devices 1B to 1D. The voice transfer command and the voice playback frame are transmitted to each of the voice output units 108. This applies to the following brands:

[0035] The conversation mode execution unit 1403 of the first voice recognition device 1A is also activated and switches to the conversation mode. Replace (S104).

[0036] The command transmission unit 1402 of the first voice recognition device 1A receives a voice transfer command. "Mr. B!" is sent to the second to fourth voice recognition devices 1B to 1D via the communication control unit 1410. The voice data is transferred to the device, and the device is switched to a conversation mode. The first voice recognition device 1A also transmits a command and a voice playback command. The transmission unit 1402 transmits the call voice data to the second to fourth voice recognition devices 1B to 1D. Then, measurement of the elapsed time from the transfer of the data is started (S105).

[0037] Each of the second to fourth voice recognition devices 1B to 1D has a call voice data. The voice output unit 108 reproduces the voice "Mr. B!", and the conversation mode execution unit 1403 is started. The voice data is played back in the order of the second to fourth voice recognition. The devices 1B to 1D may play back audio simultaneously, or in a predetermined order. The voice may be output from the first to fourth voice recognition devices 1B to 1D in this predetermined order. For example, the order in which voice recognition devices were installed or the priority of each room can be used. The order may be the same as above (see FIG. 14), etc.

[0038] Person B in room 2 answers and responds with a response such as "Yes!" When the voice is received, the second voice recognition device 1B receives the voice as voice data via the voice input unit 107. The response voice data is then returned to the first voice recognition device 1A, which is the call source. Then, the second voice recognition device 1B is associated with the person B. The linking information that the person in room 2 where room 1B is present is person B is the first, third, and fourth The voice recognition device 1A, 1C, and 1D also share and register the voice recognition device 1A, 1C, and 1D.

[0039] FIG. 6 shows an example of location estimation data.

[0040] As an example of linking and registering the person B and the second voice recognition device 1B, When A receives the response voice data, it responds as "Person B = second voice recognition device 1B" The location estimation data may be added to the location estimation data (see FIG. 6) registered in advance in the reference memory 1032. The first to fourth voice recognition devices 1A to 1D in the home are identified by the MAC addresses of the devices and A specific identifier such as an IP address assigned to a device in the LAN 210 may be used.

[0041] Furthermore, the location estimation data is transmitted from the first voice recognition device 1A to other voice recognition devices in the house. The registration request is sent to the second to fourth voice recognition devices 1B to 1D. The second to fourth voice recognition devices 1B to 1D are stored in the reference memory 1032. The estimated data is already stored in the reference memory 1032 in each of the first to fourth voice recognition devices 1A to 1D. If the person is already registered, no linking operation is performed. The name part included in the voice of the call "You!" is processed by the voice processing engine 120 or an external When the server 201 extracts the name data and uses it as name data, the name of person B is This will allow for matching with "Chair 1B".

[0042] The method for registering hot words to determine whether to switch to conversation mode will be explained later. This is done when installing the voice recognition device during initial setup or when setting up a new registration using the method described below.

[0043] The command transmission unit 1402 of the first voice recognition device 1A receives the time measured by the timer 111. If the elapsed time exceeds the waiting time threshold for determining whether or not a response has been received (S106 / Yes ), the second to fourth voice recognition devices 1B to 1D that have not responded are connected to the A command to return the talk mode to the standby mode is transmitted (S107).

[0044] A response of voice data from at least one of the second to fourth voice recognition devices 1B to 1D. If there is a response within the time threshold (S106 / No), the first voice recognition device The second voice recognition device 1B is maintained in a conversation mode with the second voice recognition device 1A. Hold (S108).

[0045] The conversation mode execution unit 1403 is switched to the conversation mode in step S104. After that, the voice input to the voice input unit 107 of the first voice recognition device 1A and the step In step S105, the voice input to the voice input unit 107 of the second voice recognition device 1B is Speech is transmitted and received between a first voice recognition device 1A and a second voice recognition device 1B.

[0046] Either the first voice recognition device 1A or the second voice recognition device 1B is in a conversation mode. When the third hot word that ends the hot word detection is detected (S109 / Yes), The selected device, for example the second voice recognition device 1B, switches to standby mode (S110 ), together with a command to the first voice recognition device 1A to switch to standby mode. In response to this, the first voice recognition device 1A also enters the standby mode (S107). and conversation mode ends.

[0047] Also, if the second hot word is not detected in step S102 (S102 / No ), the first voice recognition device 1A maintains the normal mode without switching to the conversation mode. The process ends without changing the setting (S111).

[0048] In the above example, the first voice recognition device 1A of the person who first called out to the other party performs the linking operation. The second to fourth voice recognition devices 1B to 16 of the person in the house 2 who is called are the star devices. Although control instructions are given to each of the 1D, they are not limited to this. The second voice recognition device 1B that responded may become the master.

[0049] Another method of linking is, for example, when the fourth voice recognition device 1D is installed in a home for the first time. , and register that the main user or operator of the fourth voice recognition device 1D is person D. By doing so, the first to third voice recognition devices 1A can be connected to the home LAN 210 immediately after installation. 1C, and the linked data is expanded to the reference memory in the first to fourth voice recognition devices 1A to 1D. It is also possible to register "Person D = fourth voice recognition device 1D" in 1032.

[0050] The above example is a call from the first voice recognition device 1A to the second voice recognition device 1B. This is an example, but this procedure can be applied to all voice recognition devices in the home. Even if a voice recognition device other than the above examples is calling another voice recognition device, You can do the same.

[0051] In the above example, the first to fourth voice recognition devices 1A to 1D use wireless LAN for communication with each room. Although it uses AN, it can be connected via wired LAN or via a mobile phone line. Furthermore, it is possible to change the communication mode to a different interface only when in conversation mode. For example, in normal mode, wireless LAN is used, and in conversation mode, Bluetooth is used. Alternatively, a different wireless system such as IEEE 802.11b may be used.

[0052] (Second calling action) As in the above embodiment, once the voice recognition device 1 and the person are associated, When an object A and a person B have a conversation, a first voice recognition device 1A used by the person A and a second voice recognition device 1B used by the person B are used. The communication between the second voice recognition device 1B used by the user is opened, and the communication between the second voice recognition device 1B used by the user is opened. By closing communications between the two, the confidentiality of the conversation content can be increased.

[0053] For example, when person A calls person B for the second or subsequent times, the command of the first voice recognition device 1A is The transmitting unit 1402 transmits a second address associated with the person B registered in the location estimation data (FIG. 6). Establish communication with the voice recognition device 1B (by sending a mode switching command and responding to it). This establishes communication), and the voice data is sent to the second voice recognition device 1B.

[0054] The conversation mode execution unit 1403 executes the conversation mode from now on by controlling the first voice recognition device 1A and the second voice recognition device 1B. The voice data is transmitted only between person A and person B, and person A and person B talk directly to each other. This enables voice transmission to all voice recognition devices in the home. There is no need to send data.

[0055] During execution of this conversation mode, for example, a response from person B within a predetermined time from the call is If no voice data is received, the conversation mode execution unit 1403 of the first voice recognition device 1A It is determined that the conversation partner is absent. Then, the conversation mode execution unit 1403 sends a command. The communication unit 1402 can now communicate with other voice recognition devices in the house that have been closed until now. Restart the channel, i.e., other voice recognition devices (third and fourth voice recognition devices 1C and 1D) Send voice data to and wait for a response.

[0056] Here, for example, if there is a response from the fourth voice recognition device 1D located in room 4, the first voice The voice recognition device 1A starts communication with the fourth voice recognition device 1D and resumes the conversation. In this case, the first voice recognition device 1A uses the location estimation data of the internal reference memory 1032. The linking information between the person B and the fourth voice recognition device 1D is not stored in the database 190. It is also possible to consider that person B has temporarily moved to another location, or to consider that person B and the fourth voice Create a linking information for the recognition device 1D, assign a priority to it, and link person B and the second voice recognition device The association between person B and the fourth voice recognition device 1D is given a higher priority than the association between person B and the fourth voice recognition device 1D. It is also possible to set the priority, and the devices will be connected in order of priority and await a response.

[0057] Furthermore, if there is no response from the fourth voice recognition device 1D, the other voice recognition devices in the house are sequentially detected. The voice data is sent to a recognition device (the third voice recognition device 1C in this example) and a response is received. Then, the voice data is sent to the third voice recognition device 1C and a response is awaited. If there is no response from any of the voice recognition devices in any room within the specified time, The first voice recognition device 1A judges that the user does not have the voice recognition function and issues a message to the operator, for example, " "There was no response." Or, as above, Instead of determining that one voice recognition device, 1A, is not responding to another voice recognition device, Then, the other voice recognition device determines that there is no response voice from person B within a predetermined time, By returning no-response information to the first voice recognition device 1A, the first voice recognition device 1A becomes a no-response When the call is answered, a predetermined voice response such as "There was no response" is output. But that's okay.

[0058] The predetermined response voice data may be stored in advance in the memory 103 or may be input via the Internet. It is also possible to use one stored on an external server 201 on the network 200 .

[0059] (Third calling action) In this example, the human detection sensor I / F 110 of the voice recognition device 1 in FIG. The camera is equipped with an image sensor capable of capturing images, or a human detection sensor that can determine the presence or absence of people. The device detects the presence of a voice and responds to the user's request based on the results of the detection. Alternatively, a camera 113 may be used.

[0060] For example, in response to a call from person A, the first voice recognition device 1A recognizes a voice of a person in each room. When transmitting the call voice data of person A to the second to fourth voice recognition devices 1B to 1D, The second to fourth voice recognition devices 1B to 1D each have a human detection sensor to detect the presence or absence of a person. If a room is determined to be empty, a voice recognition device installed in that location will notify the user of the absence. is returned to the first voice recognition device 1A and received by the command transmission unit 1402.

[0061] Then, the command transmission unit 1402 of the first voice recognition device 1A transmits the absence notification in the form of the first voice. The voice of the call is not output to the voice recognition device that sent the signal to the recognition device 1A. .

[0062] On the other hand, the command transmission unit 1402 of the first voice recognition device 1A transmits the absence notification to the first voice recognition device 1B. The voice recognition device 1A transmits voice data to the voice recognition device, and the voice data The voice recognition device that receives the data plays it back and calls out. The subsequent operations are the same as those described above. This can be done in the same manner as in the embodiment.

[0063] The above person recognition and judgment may be performed by a commonly used method. It is possible to detect the presence or absence of people from the movements of people detected by the human presence sensor.

[0064] Furthermore, a camera 113 may be used as a human detection sensor. 04 extracts human features (e.g., face images) from images taken by the camera 113 and detects the presence or absence of a person Furthermore, face recognition data in which face images and people are associated with each other may be stored in advance in a reference memory 1. 032 checks whether the person being called is present in the room by comparing it with the corresponding information of the person stored in the If the person being called is captured by the camera 113 and is determined to be in the room, A communication connection between the first voice recognition device 1A and the second voice recognition device 1B is established between person A and person B. You will be able to talk to B.

[0065] (Fourth calling action) In another embodiment, person A in FIG. 4 calls person B, and a person other than person B If the user replies, the communication connection between the first voice recognition device 1A and the second voice recognition device 1B is established. The call will be made again without establishing a new one.

[0066] First, the first to fourth voice recognition devices 1A to 1D installed in each room are Voice authentication data 160 (FIG. 3B) of people residing in is stored in advance in the reference memory 1032. The voice authentication data 160 is extracted by the feature extraction unit 1205 of the voice processing engine 120 based on the person's voiceprint, Create a speaker template 1603 using voice intonation or frequency characteristics of the voice. Then, the voice authentication data 160 is stored in the reference memory 1032 of the first to fourth voice recognition devices 1A to 1D. It is generated by storing the data in advance as

[0067] The voice authentication data 160 is generated at the time of initial setting of each of the first to fourth voice recognition devices 1A to 1D. Then, the voice recognition unit 1405 of the first voice recognition device 1A recognizes the voice. The voice characteristic data of person B registered in the authentication data 160 is compared with the voice characteristic of the person who responded. If they match, the image is determined to be person B, and the determination result is sent to the command transmission unit 1402. In response to this, the command transmission unit 1402 transmits the command to the second voice recognition device 1B. Send a command to switch to talk mode.

[0068] If the voice recognition unit 1405 determines that the voice characteristics do not match, it is not person B. and process it.

[0069] The voice authentication data 160 is generated by all the first to fourth voice recognition devices in each room as described above. The voices of the people in each room, 1A to 1D, are stored in advance, and the voices of the people in each room answer the calls of person A. It is also possible to compare the voice of the person B with the voice of the person B that is expected to be called by the voice call, but instead In addition, the voice recognition is stored only in the reference memory 1032 of the first voice recognition device 1A, which is a specific master. The authentication data 160 is stored in the first voice recognition device 1A, and whether the voice characteristics match is determined on the first voice recognition device 1A. You may make a judgment.

[0070] Alternatively, voice authentication data 160 is stored in a device such as a server installed in a home, and the first ~Fourth voice data and voice authentication data 1 sent from each of the voice recognition devices 1A to 1D 60 to determine whether it matches or does not match.

[0071] Furthermore, voice authentication data 160 is stored on an external server installed outside the home, and voice characteristics are recorded. It's also good to compare.

[0072] As in the above example, by determining the voice characteristics of speaker 1601, the family members living in the house can be identified. Prevent outsiders from participating in conversations, other than those authorized by family members, from participating in conversations. This can prevent unauthorized access and improve security.

[0073] In addition, if the voice characteristics of a speaker other than those registered are detected, the system may, for example, call out to the user. The display output unit 109 of the first voice recognition device 1A on the other side displays an alarm. Then, the voice output unit 108 outputs a voice such as "There is a response from an outsider." It would be good to issue a warning like this.

[0074] (Switch between normal mode and conversation mode 1) FIG. 7 is a flowchart showing the flow of a first switching process between the normal mode and the conversation mode. Contrary to the example in Figure 5, conversation mode is set as the default.

[0075] In this example, after the first to fourth voice recognition devices 1A to 1D are installed, the main power is turned on. In this state, the conversation mode execution unit 1403 is activated, and a conversation mode is started to wait for the operator to call another person. At this time, the operator can enter a hot word for switching modes, for example, "mode change When a predetermined word such as "I'm sorry" is uttered (S201 / Yes), the mode switching unit 14 01 switches to the normal mode (S202), and the normal mode execution unit 1406 starts up (S2 03).

[0076] In step S201, if the mode switching hot word is not detected (S20 1 / No), the conversation mode is maintained by the conversation mode execution unit 1403.

[0077] The normal mode execution unit 1406 continues to execute the normal mode while the condition for returning to the conversation mode is not satisfied (S204 / No), maintain normal mode.

[0078] When the condition for returning from the normal mode to the conversation mode is met (S204 / Yes), the conversation starts again. The mode execution unit 1403 is started and the mode is returned to the conversation mode. You can also set a hot word for the user to return to the system if there is no response from the operator within a certain period of time. It may be arranged to do so.

[0079] (Switch between normal mode and conversation mode 2) FIG. 8 is a flowchart showing the flow of a second switching process between the normal mode and the conversation mode. be.

[0080] In this example, the voice recognition device 1 starts up the voice input unit 107 and detects only the presence or absence of voice. When the voice input unit 107 detects a voice (S301 / No), the process continues to monitor the voice (S301 / If yes, the hot word detection unit 1203 detects that the detected voice is for the voice recognition device 1. The first hot word to request activation (request activation of normal mode) or activation of conversation mode It is determined whether the hot word is the second hot word requested (S302). If the voice does not match any of the two hot words (S302 / No), the process returns to the voice detection process.

[0081] If the first hot word is detected (S302 / first hot word), execute normal mode For example, the setting for starting the voice recognition device 1 is If the user is called by the specified nickname, the process will proceed in normal mode.

[0082] If the second hot word is detected (S302 / second hot word), the conversation mode The execution unit 1403 is started (S304). For example, when calling the name of a family member or a person in the house, If so, it is determined that the mode is the conversation mode and the following process is carried out.

[0083] The first and second hot words may be set in advance, or may be set by the operator after installation. You can also change the hot words to suit your needs. To use the camera, install the dedicated application software for setting on your smartphone or computer. Alternatively, a master operator 501 can be determined in advance. Change hot words by voice of star operator 501 to 1st to 4th voice recognition devices 1A to 1D Alternatively, the master voice recognition device, e.g., the first voice recognition device 1 A to slave devices in other homes, for example, second to fourth voice recognition devices 1B to 1 The master operator 501 may issue a command to change the position of the target object D. Hotwords can be changed only when the user recognizes them, making them easily changeable. The voice setting of the master operator 501 is set by a voice input device dedicated for setting on a smartphone or a PC. A voice application is prepared and the voice is registered. The voice of the master operator 501 is the first sound. The voice feature data is extracted by the feature extraction unit 1205 in the voice processing engine 120 of the voice recognition device 1A. You can create it and register it in the reference memory 1032, or you can use a smartphone or a PC. It is also possible to create voice authentication data 160 and register it in the reference memory 1032. When the home server 601 connected to the network environment in the home is provided, the voice feature data is stored. The home server 601 stores the information and the server and the voice recognition device communicate with each other. It is also possible to compare the characteristics of the voice that was spoken with the characteristics of the voice in the stored data.

[0084] (New installation setting 1) FIG. 9 is a conceptual diagram showing the first setting process at the time of new installation.

[0085] When installing a new voice recognition device1 in your home, it is important to use a device that is similar to a smartphone or computer. The electronic device 401 is provided with dedicated application software (initial setting application software). Then, the network connection to the router 202 in the home is established. Continue setting, register the device if there is an existing voice recognition device1, and perform voice recognition with family members and other people in the home. data relating to the correspondence with the recognition device 1, voice recognition data 160 of family members, etc. In this example, a new voice recognition device and a wireless The connection settings for communication devices such as wired routers can be done using the above smartphones, computers, etc. How to set it up or use automatic methods such as WPS (WiFi Protected Setup) The connection is set up using a dynamic configuration method.

[0086] In addition, the correspondence between the above persons and the voice recognition device 1 is that person A mainly uses The device that person B mainly uses is the first voice recognition device 1A, and the device that person B mainly uses is the second voice recognition device 1B. Set up the association with the voice recognition device 1B, such as the smartphone or computer This is done on the application software.

[0087] Furthermore, the person's voice authentication data 160 can be acquired from an existing device, e.g., a third voice recognition device 1C The data stored on the electronic device may be read and shared, or may be managed on the electronic device. It is also possible to understand the number of times the data is to be stored and set the data.

[0088] (New installation settings 2) FIG. 10 is a conceptual diagram showing the second setting process at the time of new installation, and FIG. 10 is a flowchart showing the flow of a second setting process when the camera is placed in a position.

[0089] In this example, a master operator 501 who has the authority to set up communication devices in the home can Set up the connection for the new voice recognition device 1S.

[0090] First, the master operator 501 starts speaking to the new voice recognition device 1S. When the input unit 107 receives a voice input, the connection setup process is started. Measurement is started (S401).

[0091] The hot word detection unit 1203 of the new voice recognition device 1S detects the fourth hot word for initial setting. When the device detects the target word W501 (S402 / OK), the initial settings for the new voice recognition device 1S are The initial setting unit 1408 starts the initial setting process. The voice data and the initial setting request data of the operator 501 are transmitted to an existing device in the home, for example, The first to fourth voice recognition devices 1A to 1D and the home server 601 (S403 The above transmission process is carried out within a predetermined time (S404).

[0092] The reason for limiting the transmission process to a certain time is to prevent the initial setting request data from being spread outside the home during transmission. This is to reduce the possibility that the voice data of the master operator 501 will be intercepted.

[0093] The transmitted request data and voice data are processed by the first to fourth voice recognition devices already installed in the home. The signal is received by the stations 1A to 1D (S403).

[0094] The feature extraction unit 1205 of each of the first to fourth voice recognition devices 1A to 1D extracts the broad The voice data transmitted based on the cast initial setting request data is sent to the master operator 50 The feature extraction unit 1205 verifies whether the received voice signal is one of the first to fourth voice recognition features (S405). The sound of the master operator 501 stored in the reference memory 1032 of each of the devices 1A to 1D Voice features are extracted from the speaker template and the broadcasted voice data. The data is extracted and compared, and if it matches (S405 / OK), it is applied to the new voice recognition device 1S. Then, the initial settings are executed (S406), and the connection setting process is terminated.

[0095] If the judgment results are NG in steps S402 and S405 (S402 / NG), 405 / NG), this process will also end.

[0096] The initial setting is performed by setting all the voices in the house among the first to fourth voice recognition devices 1A to 1D. This is done by a master voice recognition device that controls the voice recognition devices. Master Voice Recognition Device For example, a device installed in the living room of a house (used relatively frequently by family members) This role will be played by the voice recognition device installed in the home or the device that is first installed in the home. may be set by the master operator 501 as the master voice recognition device.

[0097] Or, the home server 601 in the house is used as a master device to verify the above voice data. Or, the initial settings of a newly connected device may be performed. When this is implemented, the voice data and initial setting request data of the master operator 501 are input to the existing first - The fourth voice recognition device 1A-1D receives the signal and transfers it to the home server 601, or The home server 601 itself receives the data. The home server 601 then receives the data from the master operator 5. The voice template, which is the voice feature data of 01, is stored and a match is made between the voice features. If the verification is successful, the home server 601 notifies the new voice recognition device 1S of the home Various communication settings are instructed to enable connection to the internal LAN 210 .

[0098] <Second embodiment> In this embodiment, a home conversation system using a voice recognition device 1 is FIG. 12 shows the voice recognition device in the home in the second embodiment. 1 is a diagram showing a schematic configuration of a linkage system 100a of a chair 1.

[0099] The difference from FIG. 4 is that a home server 601 is provided on the home LAN 210. The server 601 stores voice authentication data including voice data of people present in the house and voice feature points. The home server 601 stores the first to fourth voice recognition devices 160. The system detects the presence or absence of people in the house based on the voice data sent from A to D. It is determined which of the first to fourth voice recognition devices 1A to 1D a person present in the vicinity of Always monitor.

[0100] As a result, even when person A calls person D in FIG. 12, The first voice recognition device 1A that receives the voice from the home server 601 is closer to the person D. Information on the voice recognition device to be determined (fourth voice recognition device 1D) is obtained.

[0101] Then, voice data is sent only to the first voice recognition device 1A to the fourth voice recognition device 1D. By sending a message to the person you want to call, you can send a message to the person you want to call without having to check the location of the person you want to call. It will be possible to have a conversation only with the voice recognition device.

[0102] In FIG. 12, the people present are person B in room 2 and person D in room 4. Each of the first to fourth voice recognition devices 1A to 1D is a person detection sensor I / F provided in the device. The presence status is grasped at 110, and the result is transmitted to the home server 601. The voice recognition device 1A notifies the home server 601 of which voice recognition device is detecting a person. By inquiring whether the second voice recognition device in the room 2 and the room 4 is the same as the first voice recognition device in the room 2, Priority is given to communication connections with 1B and the fourth voice recognition device 1D.

[0103] Furthermore, the home server 601 collects information such as the presence or absence of people and the presence or absence of voice, It is possible to always know which person is in which room. In this way, the first voice recognition The home server 601 checks the destination of the call data from the device 1A to the person D. Then, the call data is sent to a fourth voice recognition device 1D located in the room 4 where the person D is present. This can be done.

[0104] Next, the person D responds to the call played on the fourth voice recognition device 1D, A communication connection between the voice recognition device 1A and the fourth voice recognition device 1D is established, and the person A A conversation between person A and person D becomes possible.

[0105] In the above example, the home server 601 controls the first to fourth voice recognition devices 1A to 1D. The presence status of each room is monitored by the person detection sensor installed in each room, but instead of this, Or, in addition, data on the usage status of each voice recognition device may be used.

[0106] FIG. 13 shows the usage status data 170 that records the usage status of person A for each time period. FIG. 14 shows an example of the time for person A determined based on the usage status data 170. An example of the priority data 180 of calls for each time zone is shown. Similar data will be created for the same.

[0107] The reference memory 1032 of each of the first to fourth speech recognition devices 1A to 1D stores a usage status data. For example, for person A, When the first voice recognition device 1A responds to the call, the first to fourth voice recognition devices Each of the devices 1A to 1D has a usage status data 170 stored in its own device and a call priority. The response record and the call priority are written and updated in the data 180.

[0108] Additionally, the first voice recognition device 1A receives the updated usage data 170 and the call priority. The ranking data 180 is broadcast to the home LAN 210. Each of the devices 1B to 1D receives the updated usage status data 170 and the call priority. The usage status data 170 stored in the reference memory 1032 of the own machine using the ranking data 180 and updating the call priority data 180.

[0109] In this state, Person B calls Person A at 7:00 on Monday from the fourth voice recognition device 1D. The command transmission unit 1402 of the fourth voice recognition device 1D sends the command in the order of calling priority. The priority data 180 is referred to, and the priority is determined among the first to third voice recognition devices 1A to 1C other than the own device. In descending order of priority, the second voice recognition device 1B, the first voice recognition device 1A, the third voice recognition device 1B, and so on. The recognition devices are read out in order of 1C.

[0110] The call priority data 180 is generated not only based on the usage status data 170 but also based on the user For example, if you know that you are near a specific device during a certain period of time, If so, temporarily change the call priority data 180 to that of the device. You may set the priority to 1.

[0111] Also, for example, in the first usage status data 170, the person A uses the second voice recognition device 1 It can be seen that B is frequently used between 8pm and 8am on Saturdays and Sundays. If the time is within that range, it will be determined that person A is likely to be in the room and will connect in conversation mode. During times other than the above, the home server 601 treats person A as absent. It can also be understood.

[0112] (Conversation with someone outside the house) In the above example, if the called person D is determined to be absent, It is also possible to transfer voice data to communication devices such as smartphones owned by users.

[0113] In this case, the Internet address, line information, and device ID of Person D and his / her communication device Such device information is registered in the reference memory 1032 of the home server 601, Based on this information, call data is transferred to the communication device.

[0114] When the call message arrives at the communication device owned by person D, the device notifies the person by displaying the screen, outputting a sound, vibrating, etc. When person D responds, the first voice recognition device in the home A call can also be initiated between 1A and a communication device owned by person B outside the house.

[0115] If person D does not respond to the call at this stage, the home server 601 will play the first sound. The first voice recognition device 1A issues absence notification data to the first voice recognition device 1A. If the object D does not come out, a specified voice output will be generated, such as "There is no response at the moment." conduct.

[0116] In the embodiment described above, the first voice recognition device 1A is connected to the other second to fourth voice recognition devices 1A and 1B. Although an example of calling out to the voice recognition devices 1B to 1D is shown, the present invention is not limited to this. Instead, a call can be made from any of the second to fourth voice recognition devices 1B to 1D. Therefore, it is possible to call other voice recognition devices from any voice recognition device in the home. In addition, multiple voice recognition devices according to this embodiment can be installed. When installing a new system, the system can be expanded by using the above installation method.

[0117] (Notification from outside the home) FIG. 15 shows an example in which the voice recognition device 1 and the portable communication terminal 71 are connected by a dock 701. vinegar.

[0118] The voice recognition device 1 further includes a dock 701. The dock 701 is connected to a mobile communication terminal 7 A charge control interface 711 that charges the battery 1 and a communication interface 712 that communicates via a connection terminal and a control interface 712. Specific functions include USB (Universal Serial Bus) or wired connection via certain mobile communication terminal interfaces, or This can be achieved through features such as wireless charging and wireless communication.

[0119] When a call is received by the portable communication terminal 71, the portable communication terminal 71 receives a communication control input. The voice output unit 108 outputs the voice to the voice recognition device 1 via the interface 712. It will output incoming call notification sounds such as "This is a call" or "This is an email."

[0120] The owner of the mobile communication terminal 71 may ask, "Please play it," "Who is it from?", or "What is the content?" When the user responds, the mobile communication terminal 71 is instructed to receive the call or to transfer the contents of the mail. It can announce the name of the person you're notifying, act as a speakerphone for your phone calls, and send you emails. The contents of the email can be output as audio.

[0121] Furthermore, if the owner of the portable communication terminal 71 is not present, whether or not there is a response within a predetermined time Then, the home server 601 shown in FIG. 12 assumes that the user is in another location in the house and sends the mobile communication terminal Identify the voice recognition device 1 that is determined to be closest to the current location of the last 71 owner, The incoming call notification is forwarded to the voice recognition device 1. Based on the forwarded incoming call notification, The same operation as the above calling operation is performed.

[0122] As a method for recognizing the current location of the owner of the portable communication terminal 71, a home server is used. The server 601 detects the usage status of each voice recognition device 1 in the house, The extracted voice characteristics of the voice spoken to the device 1, the sounds picked up by each voice recognition device 1, 701 and the mobile communication terminal 71, the person in the house is using which voice recognition device It may also be possible to determine whether the user is near station 1.

[0123] Furthermore, devices such as the mobile communication terminal 71 that are usually worn by their owners (wearable devices) A wireless device (which may be a wireless device) is close enough to the voice recognition device 1, such as the connection to the dock 701. Can the camera of the voice recognition device 1 communicate using short-distance communication that can determine whether the person is in If you can confirm that the device is in the same room by calling 113, the device owner will It is assumed that the person in the room is a voice recognition device. It is acceptable to take measures such as

[0124] <Third embodiment> (Home surveillance) The third embodiment is an application of the configuration of the second embodiment shown in FIG. 12 to a different mode of use. FIG. 16 is a flowchart showing the process of switching to the answering mode. This is a low chart.

[0125] Those in the home who are authorized to access each voice recognition device1 can use the answering machine. The fifth hot word to switch to the mode, for example, "Please stay home!". When any one of the voice recognition devices 1A to 1D detects the fifth hot word (S501 / Yes), the feature extraction unit 1205 of the voice recognition device that detected the fifth hot word The voice of a person who is registered in the authentication data 160 as a person who is authorized to access the home LAN The characteristics are compared with voice characteristic data extracted by the voice recognition device 1 for judgment.

[0126] This determination can be made by using the methods described in the above embodiments. Also, the procedure of checking hotwords and determining whether access is allowed can be done either first or second. stomach.

[0127] If the feature extraction unit 1205 determines that there is a match (S502 / Yes), the command transmission unit 1 The mobile phone 402 transmits an instruction to the home server 601 to switch to the answering machine mode (S503).

[0128] When the home server 601 receives an instruction to switch to the answering machine mode, the home server 601 After a certain period of time has elapsed, the first to fourth voice recognition devices 1A to 1D in the house are all notified of the predetermined volume. When the above sound is detected, a notification of the occurrence of an abnormal sound is sent to the home server 601. In order to switch to the answering mode, an instruction to switch to the answering mode is issued (S504).

[0129] Each of the first to fourth voice recognition devices 1A to 1D includes a mode switching unit 14 01, the answering machine mode is switched to, and the answering machine mode execution unit 1407 processes the answering machine mode. is executed (S505).

[0130] At least one of the first to fourth voice recognition devices 1A to 1D receives voice messages during an answering machine mode. When the first to fourth voice recognition devices 1A to 14 detect the voice (S506 / Yes), The 1D feature extraction unit 1205 extracts voice feature data of a person (family member) registered in the voice authentication data 160. The detected voice is compared with the voice characteristic data registered in the voice authentication data 160. If so (S507 / Yes), the mode switching unit 1401 switches from the answering machine mode to the normal mode. Then, the power is restored (S508).

[0131] In step S507, the feature extraction unit 1205 extracts the detected voice data as voice authentication data. If it is determined that the voice characteristic data does not match that of the person (family member) registered in the voice recorder 160 (S507 / No), the mode switching unit 1401 switches to the alert mode (S509), and the alert mode execution unit 1409 starts.

[0132] The alert mode execution unit 1409 is configured to execute an alert mode, for example, for the first to fourth voice recognition devices 1A to The camera 113 installed in each 1D can be activated to record image data in the room and record audio. The input unit 107 executes a process of recording the detected voice. When the home server 601 receives the abnormality occurrence information, the home server 601 Sending e-mails and the like to mobile communication terminals 71 such as mobile phones and smartphones owned by registered family members Send an alarm.

[0133] The family member who receives the alarm can also connect to the home server 601 for communication. The server 601 converts the sound picked up by the voice input unit 107 of the voice recognition device 1 that detected the abnormal sound into a voice signal. The data is received and sent directly to the household members to check the situation inside the home. It is also possible.

[0134] While the security mode is active, the conditions for canceling the security mode are met, for example, a call from a family member who has just returned home. When the first hot word that commands the return to normal mode is detected (S510 / Yes), the mode The mode switching unit 1401 releases the alert mode and returns to the normal mode (S508).

[0135] Although the above shows an example in which multiple voice recognition devices 1 are used, the voice recognition device 1 can be used alone. When operating independently, the voice recognition device 1 is connected to the home server 6. Alternatively, the home server 601 may be replaced by the Internet. It is also possible to use a cloud server or the like that exists on the Internet.

[0136] According to this embodiment, the voice recognition device 1 in the house is linked to recognize voices of the family members while they are away. The system can activate the alarm mode based on whether or not there is an input and whether the voice characteristics are registered or not. This makes it possible to detect intruders into a house using the voice recognition devices 1 installed in multiple rooms. If an abnormality is detected, the voice recognition devices1 throughout the house will go into alarm mode and detect the intruder. It is possible to track visitors, record their movements and facial images, and also report them to family members.

[0137] In addition, if the above abnormal sounds are detected, a warning sound or voice will be emitted from the voice recognition device 1. It is also possible to output a warning sound such as a siren, or a voice message such as "Who is it?" If you register such sounds, they can be played back when an abnormal sound is detected, which can be effective in crime prevention. .

[0138] The above embodiment describes a one-to-one call between voice recognition devices. However, this is not limited to this, and one-to-many and many-to-many communication modes are also possible. In this case, voice data of a person in a conversation mode is sent to a plurality of voice recognition devices.

[0139] According to this embodiment, a plurality of voice recognition devices can be used in cooperation with each other to realize a network environment in a home or the like. In other words, you can communicate with other rooms and It is as if people in the same room or place were communicating with a voice recognition device installed in another location. This allows users to communicate with each other like a human, and can be used with voice recognition devices in other locations. This allows for smooth communication with others. [Explanation of symbols]

[0140] 1: Voice recognition device 100: Collaboration system 100a: Collaboration system 101: CPU 102: Bus 103: Memory 104:Wired LANI / F 105: Wireless LAN I / F 106: Wireless communication I / F 107: Audio input section 108: Audio output section 109: Display output section 111: Timer 113: Camera

Claims

1. An information processing device, A voice input unit; An audio output unit; A communication interface for transmitting and receiving data to and from a voice recognition device; a storage unit that stores voice authentication information linking a person permitted to have a conversation using the voice recognition device with voice feature information of the person, and first usage status information linking a person permitted to have a conversation with a number of responses from each voice recognition device of the person; A control unit, The communication interface includes: Communicating with a plurality of speech recognition devices; Transmitting voice information input from the voice input unit to the voice recognition device; receiving speech information from the speech recognition device; The audio output unit is outputting the audio information received by the communication interface; The control unit is When the voice input from the voice input unit includes a conversation start hot word, a conversation mode is executed; The voice input unit is Accept input of a call voice to call a specific person, The control unit is Detecting whether the voice feature information of the calling voice matches the voice authentication information stored in the storage unit; If a match is detected with the voice authentication information, a control command for activating the conversation mode is transmitted to the plurality of voice recognition devices in descending order of the number of responses in the first usage status information; If the specific person does not respond, control is performed to transmit the voice information to a communication device of the specific person.

23. An information processing apparatus comprising:

2. An information processing device, A voice input unit; An audio output unit; A communication interface for transmitting and receiving data to and from a voice recognition device; a storage unit that stores voice authentication information linking a person who is permitted to have a conversation using the voice recognition device with voice feature information of the person; A human sensor and A control unit, The communication interface includes: Communicating with a plurality of speech recognition devices; Transmitting voice information input from the voice input unit to the voice recognition device; receiving speech information from the speech recognition device; The audio output unit is outputting the audio information received by the communication interface from the audio output unit; The voice input unit is Accepts voice input to call a specific person, The control unit is When the voice input from the voice input unit includes a conversation start hot word, a conversation mode is executed; If the specific person does not respond, control is performed to transmit the voice information to a communication device of the specific person; Furthermore, when there is an answering machine hot word, the answering machine is controlled to execute an answering machine mode that detects the intrusion of a person based on the detection of the human sensor, and when a match between the voice feature information and the voice authentication information is detected during execution of the answering machine mode, the answering machine mode is controlled to be stopped.

23. An information processing apparatus comprising:

3. 3. The information processing device according to claim 1, When the control unit detects the conversation starting hot word, the control unit transmits voice information in which the conversation starting hot word is detected and a playback command for the voice information to the voice recognition device.

23. An information processing apparatus comprising:

4. 2. The information processing device according to claim 1, the control unit transmits the control command to the voice recognition device when a match between the voice feature information and the voice authentication information is detected.

23. An information processing apparatus comprising:

5. 2. The information processing device according to claim 1, Further comprising an imaging unit, the storage unit further stores face authentication information linking a person who is permitted to have a conversation using the voice recognition device with a captured image of the person; The control unit further detects whether an image captured by the imaging unit matches the face authentication information, When a match between the captured image and the face authentication information is detected, the control command is transmitted to the voice recognition device.

23. An information processing apparatus comprising:

6. 2. The information processing device according to claim 1, the control unit transmits the control command to the voice recognition device that outputs the person detection information based on person detection information indicating that the voice recognition apparatus has detected the presence of a person.

23. An information processing apparatus comprising:

7. 3. The information processing device according to claim 1, Further comprising a timer; The voice input unit receives a voice input for calling a specific person, the control unit transmits to the voice recognition device a voice for calling the specific person and a playback command for playing back the voice in the voice recognition device; obtaining, from the timer, a voice for calling the specific person and an elapsed time since the playback command was transmitted; outputting, from the audio output unit, a response message notifying that there is no response message from the specific person after the elapsed time has elapsed a predetermined waiting time; 23. An information processing apparatus comprising:

8. 2. The information processing device according to claim 1, the control unit transmits, to all of the plurality of voice recognition devices, a voice for calling the specific person and a playback command for playing the voice in each of the plurality of voice recognition devices; when the communication interface receives a response message from the specific person from one of the plurality of voice recognition devices, the communication interface maintains communication with the voice recognition device that has transmitted the response message and disconnects communication with the remaining voice recognition devices; 23. An information processing apparatus comprising:

9. 3. The information processing device according to claim 2, The voice input unit receives a voice input for calling a specific person, the control unit transmits, to all of the plurality of voice recognition devices, a voice for calling the specific person and a playback command for playing the voice in each of the plurality of voice recognition devices; when the communication interface receives a response message from the specific person from one of the plurality of voice recognition devices, the communication interface maintains communication with the voice recognition device that has transmitted the response message and disconnects communication with the remaining voice recognition devices; 23. An information processing apparatus comprising:

10. 2. The information processing device according to claim 1, Further comprising a time measurement unit, the storage unit further stores second usage status data that defines an order in which the voice recognition device calls the plurality of voice recognition devices according to a time period; the control unit acquires from the time measurement unit a time when the conversation activation hotword was detected, and transmits the control command to each of the plurality of voice recognition devices in accordance with a call priority order defined for a time period including the time of the second usage status data.

23. An information processing apparatus comprising:

11. 3. The information processing device according to claim 2, Further comprising a time measurement unit, the storage unit further stores second usage status data that defines an order in which the voice recognition device calls the plurality of voice recognition devices according to a time period; the control unit acquires from the time measurement unit a time when the conversation activation hotword was detected, and transmits a control command to each of the plurality of voice recognition devices to activate the conversation mode in accordance with a call priority order defined for a time period including the time of the second usage status data.

23. An information processing apparatus comprising:

Images