Voice processing system, conference system, voice processing method and recording medium

Through the steps of voice reception, determination, command determination and object user determination, the problem of inaccurate transmission of voice command response information in the prior art is solved, and the accurate transmission of voice command information is realized, and the personalized needs of multiple users are met.

CN112053684BActive Publication Date: 2024-12-03SHARP KK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010426661.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-06-05
Filing Date
2020-05-19
Publication Date
2024-12-03
Estimated Expiration
2040-05-19

AI Technical Summary

Technical Problem

When the existing voice conference system delivers voice command responses, it is difficult to properly pass information to the users in need, resulting in information overload or insufficient information.

Method used

Through the steps of voice reception, determination, command determination, object user determination and command execution, the precise recognition and transmission of voice commands are realized to ensure that information is only passed to relevant users.

Benefits of technology

It realizes the appropriate transmission of information corresponding to voice commands to users, improves the accuracy and efficiency of information transmission, and meets the personalized needs of different users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112053684B_ABST
    Figure CN112053684B_ABST
Patent Text Reader

Abstract

The object of the present invention is to provide a speech processing system, a conference system, a speech processing method, and a speech processing program that can appropriately transmit information corresponding to a speech command to a user. The speech processing system comprises: a speech receiving unit that receives speech; a speaker determination unit that determines the speaker based on the received speech; a speech judgment unit that determines whether the speech contains a specific word for starting the acceptance of a specified command based on the received speech; a command determination unit that determines the command based on a command keyword contained in the speech and adjacent to the specific word when the speech contains the specific word; a target user determination unit that determines the target user who executes the command based on the content of the command; and a command execution unit that executes the command with respect to the target user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a speech processing system, a conference system, a speech processing method and a speech processing program. Background Art

[0002] Conventionally, a conference system has been proposed for transmitting and receiving voice, video, files, etc. via a network in remote locations. For example, a videophone device has been proposed that, when a sentence is recognized from a camera unit that captures a camera image and an input voice and the sentence matches a registered keyword, selects a specific auxiliary image associated with the registered keyword, and transmits the camera image and the auxiliary image in a switching manner.

[0003] In the prior art, for example, when the voice (voice command) of the first user is recognized in a conference, information (command response) corresponding to the voice command is transmitted to all users participating in the conference. However, sometimes the command response is information required by only some users and not required by other users. Therefore, in a system in which the command response is transmitted to all users participating in the conference, it is difficult to perform appropriate information transmission. Summary of the invention

[0004] An object of the present invention is to provide a speech processing system, a conference system, a speech processing method, and a speech processing program that can appropriately transmit information corresponding to a speech command to a user.

[0005] A speech processing system according to one embodiment of the present invention comprises: a speech receiving unit that receives speech; a speaker determining unit that determines a speaker based on the speech received by the speech receiving unit; a speech judging unit that determines whether the speech contains a specific word based on the speech received by the speech receiving unit, and the specific word is used to start accepting a specified command; a command determining unit that determines the command based on a command keyword contained in the speech and adjacent to the specific word when the speech judging unit determines that the speech contains the specific word; a target user determining unit that determines a target user who executes the command based on the content of the command determined by the command determining unit; and a command executing unit that executes the command determined by the command determining unit with respect to the target user determined by the target user determining unit.

[0006] A conference system according to another embodiment of the present invention is provided with a voice processing device and a display device in each area, and voice can be sent and received between the areas via the voice processing device. The conference system comprises: a voice receiving unit that receives the voice; a speaker determination unit that determines the speaker based on the voice received by the voice receiving unit; a voice judgment unit that determines whether the voice contains a specific word based on the voice received by the voice receiving unit, and the specific word is used to start accepting a specified command; a command determination unit that determines the command based on a command keyword contained in the voice and adjacent to the specific word when the voice judgment unit determines that the voice contains the specific word; a target user determination unit that determines a target user who executes the command based on the content of the command determined by the command determination unit; and a command execution unit that executes the command determined by the command determination unit in the display device of the area where the target user determined by the target user determination unit is located.

[0007] A speech processing method according to another embodiment of the present invention performs the following steps by one or more processors: a speech receiving step for receiving speech; a speaker determining step for determining a speaker based on the speech received by the speech receiving step; a speech judging step for determining, based on the speech received by the speech receiving step, whether the speech contains a specific word for starting acceptance of a specified command; a command determining step for determining the command based on a command keyword contained in the speech and adjacent to the specific word when the speech judging step determines that the speech contains the specific word; a target user determining step for determining a target user for executing the command based on the content of the command determined by the command determining step; and a command executing step for executing the command determined by the command determining step relative to the target user determined by the target user determining step.

[0008] A speech processing program according to another embodiment of the present invention is used to execute the following steps through one or more processors: a speech receiving step for receiving speech; a speaker determining step for determining a speaker based on the speech received by the speech receiving step; a speech judgment step for determining, based on the speech received by the speech receiving step, whether the speech contains a specific word for starting the acceptance of a specified command; a command determining step for determining the command based on a command keyword contained in the speech and adjacent to the specific word when the speech judgment step determines that the speech contains the specific word; a target user determining step for determining a target user for executing the command based on the content of the command determined by the command determining step; and a command execution step for executing the command determined by the command determination step relative to the target user determined by the target user determination step.

[0009] According to the present invention, it is possible to provide a speech processing device, a conference system, a speech processing method, and a speech processing program that can appropriately transmit information corresponding to a speech command to a user.

[0010] This specification is presented in a simplified form, with appropriate reference to the accompanying drawings, to summarize the concepts described in the following detailed description. This specification is not intended to limit the important features and essential features of the subject matter described in the claims, nor is it intended to limit the scope of the subject matter described in the claims. In addition, the subject matter described in the claims is not limited to implementations that solve some or all of the disadvantages described in any part of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a diagram showing a schematic configuration of a conference system according to an embodiment of the present disclosure.

[0012] Figure 2 It is a functional block diagram showing the structure of a conference system according to an embodiment of the present disclosure.

[0013] Figure 3 A diagram showing an example of a display screen displayed on a display device in a conference system according to an embodiment of the present disclosure.

[0014] Figure 4 A diagram showing an example of a display screen displayed on a display device in a conference system according to an embodiment of the present disclosure.

[0015] Figure 5 A diagram showing an example of a display screen displayed on a display device in a conference system according to an embodiment of the present disclosure.

[0016] Figure 6A diagram showing an example of a display screen displayed on a display device in a conference system according to an embodiment of the present disclosure.

[0017] Figure 7 A diagram showing an example of a display screen displayed on a display device in a conference system according to an embodiment of the present disclosure.

[0018] Figure 8 This is a diagram showing an example of conference information used in the conference system according to the embodiment of the present disclosure.

[0019] Fig. 9 This is a diagram showing an example of user information used in the conference system according to the embodiment of the present disclosure.

[0020] Fig.10 This is a diagram showing an example of participant information used in the conference system according to the embodiment of the present disclosure.

[0021] Fig.11 This is a diagram showing an example of command information used in the conference system according to the embodiment of the present disclosure.

[0022] Fig.12 This is a diagram showing an example of content information used in the conference system according to the embodiment of the present disclosure.

[0023] Fig.13 The flowchart is used to explain an example of a voice processing procedure in a conference system according to an embodiment of the present disclosure.

[0024] Fig.14 The flowchart is used to explain an example of a voice processing procedure in a conference system according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In addition, the following embodiment is an example of a specific embodiment of the present invention and does not limit the technical scope of the present invention.

[0026] The speech processing system of the present invention can be applied to a conference attended by multiple users in one place (area), a remote conference attended by multiple users by connecting multiple places (areas) to a network, etc. In addition, the speech processing system of the present invention can also have: a function of executing speech commands, a call function (telephone function, videophone function, etc.) that enables calls between users via a network. In addition, the speech processing system of the present invention has one or more speech processing devices that send and receive the speech of the meeting participants.

[0027] In the following embodiments, the case where a voice processing system is applied to a remote conference (conference system) is cited as an example for explanation. That is, the conference system involved in this embodiment is an example of the voice processing system involved in the present invention. For example, in the conference system involved in this embodiment, a voice processing device is configured in each place (conference room), and the voice processing device of one party's conference room receives the voice emitted by the user and sends it to the voice processing device of the other party's conference room, so that the users of each conference room can have a conversation with each other. In addition, in the conference system, there is a cloud server that analyzes the voice of the user received from the voice processing device to determine the command. In addition, in the conference system, there is a display device as an example of a terminal device for executing the command. In addition, the terminal device for executing the command is not limited to the display device, but can also be a voice processing device or a user terminal carried by the user.

[0028] [Conference system 100]

[0029] Figure 1 It is a diagram showing the general structure of a conference system involved in an embodiment of the present invention. Conference system 100 includes: a voice processing device 1, a cloud server 2, a display device 3 and a database DB. Voice processing devices 1A, 1B, and 1C are microphone-speaker devices respectively equipped with microphones and speakers, such as AI speakers, smart speakers, etc. Here, a voice processing device 1A arranged in conference room A, a voice processing device 1B arranged in conference room B, and a voice processing device 1C arranged in conference room C are shown. Display devices 3A, 3B, and 3C have a display unit that displays various information. Here, a display device 3A arranged in conference room A, a display device 3B arranged in conference room B, and a display device 3C arranged in conference room C are shown. Voice processing device 1A and display device 3A, voice processing device 1B and display device 3B, voice processing device 1C and display device 3C, cloud server 2, and database DB are interconnected via network N1. Network N1 is a communication network such as the Internet, LAN, WAN, or public telephone line. Cloud server 2 is constructed, for example, by one or more data servers (virtual servers). The database DB stores various data. The database DB may also be included in the cloud server 2, or in any one of the display devices 3A, 3B, and 3C, or may be distributed in multiple display devices 3. In addition, the database DB may also be included in any one of the voice processing devices 1A, 1B, and 1C, or may be distributed in multiple voice processing devices 1. The voice processing devices 1A, 1B, and 1C are each an example of a voice processing device of the present invention. The display devices 3A, 3B, and 3C are each an example of a display device and a terminal device of the present invention.

[0030] Here, list Figure 1Taking the structure shown in the figure as an example, an example of an application scenario of the conference system 100 is described. In addition, information such as the name of the conference (topic), the start date and time of the conference and the end date and time, the files (attachments) used in the conference, and the participants ( Figure 8 The meeting information D1 shown is pre-registered in the database DB (refer to Figure 2 ). The conference information D1 is registered, for example, by the person in charge of the conference. Here, users A, B, and C are registered in advance in the conference information D1 as participants of the conference.

[0031] First, user A inputs and registers the user ID on the login screen displayed by the display device 3A in the conference room A. Thus, the identification information (user ID) "U001" of user A is associated with the identification information (display device ID) "D001" of the display device 3A and registered in the participant information D3 (refer to Fig.10 ). Similarly, user B enters and logs in the user ID on the login screen displayed by the display device 3B in the conference room B. As a result, the identification information (user ID) "U002" of user B is associated with the identification information (display device ID) "D002" of the display device 3B and registered in the participant information D3. In addition, user C enters and logs in the user ID on the login screen displayed by the display device 3C in the conference room C. As a result, the identification information (user ID) "U003" of user C is associated with the identification information (display device ID) "D003" of the display device 3C and registered in the participant information D3.

[0032] Next, for example, user A issues a specific word (also called a start word or a wake-up word) for starting the acceptance of a predetermined command (in Figure 3 In the example, "***") and the command keyword ( Figure 3 The speech processing device 1A recognizes the specific word and sends the command keyword to the cloud server 2. The cloud server 2 determines the command based on the command keyword. Here, the cloud server 2 determines the command of "start meeting". The display device 3A executes the determined command. As a result, the connection of the display device 3A is completed and the meeting starts.

[0033] Similarly, for example, user B utters a voice containing the specific word and the command keyword ("Start today's scheduled meeting"). When the voice processing device 1B recognizes the specific word, it sends the command keyword to the cloud server 2. The cloud server 2 determines the command based on the command keyword. Here, the cloud server 2 determines the command of "start meeting". The display device 3B executes the determined command. As a result, the connection of the display device 3B is completed, and the display devices 3A and 3B are connected to the same network. As a result, for example, the identification information (facial image) of the user B is displayed on the display screen of the display device 3A, and the identification information (facial image) of the user A is displayed on the display screen of the display device 3B (refer to Figure 3 ).

[0034] Similarly, for example, user C utters a voice including the specific word and the command keyword ("Start today's scheduled meeting"). When the voice processing device 1C recognizes the specific word, it sends the command keyword to the cloud server 2. The cloud server 2 determines the command based on the command keyword. Here, the cloud server 2 determines the command of "start meeting". The display device 3C executes the determined command. Thus, the connection of the display device 3C is completed, and the display devices 3A, 3B, and 3C are connected to the same network. Thus, for example, the display screen of the display device 3A displays the identification information (facial images) of the user B and the user C, the display screen of the display device 3B displays the identification information (facial images) of the user A and the user C, and the display screen of the display device 3C displays the identification information (facial images) of the user A and the user B (refer to Figure 3 ).

[0035] When a conference starts, for example, the voice of user A is received by voice processing device 1A, which transmits the received voice to voice processing devices 1B and 1C via the network, and voice processing devices 1B and 1C respectively output the received voice from speakers. In this way, users A, B, and C have a conversation.

[0036] Here, for example, when user A utters a voice including the specific word and "display help" as the command keyword, the voice processing device 1A, when recognizing the specific word, sends the command keyword to the cloud server 2. When the cloud server 2 receives the command keyword, it determines the command of "help display" (refer to Fig.11). In addition, the cloud server 2 determines the target user to execute the command. Here, the cloud server 2 determines "user A" who is the speaker of the command keyword as the target user to display and browse the help screen. The display device 3A executes the determined command. As a result, the display screen of the display device 3A displays the help image P1 (refer to Figure 4 ). In this case, the help image P1 is not displayed on the display screens of the display devices 3B and 3C.

[0037] In addition, for example, when user A utters a voice including the specific word and "display attachment" as the command keyword, the voice processing device 1A, when recognizing the specific word, sends the command keyword to the cloud server 2. When the cloud server 2 receives the command keyword, it determines the command of "display attachment" (refer to Fig.11 ). In addition, the cloud server 2 determines the target user for executing the command. Here, the cloud server 2 determines all participants in the meeting, here "User A", "User B", and "User C", as the target users for displaying and viewing the attachment. The display devices 3A, 3B, and 3C respectively execute the determined command, thereby displaying the same attachment image P3 on the respective display screens of the display devices 3A, 3B, and 3C displaying the image P2 (refer to Figure 5 ). In addition, the attachment is stored in advance in the database DB, for example, and its identification information (attachment ID "f001") is registered in the conference information D1 (refer to Figure 8 ).

[0038] When the attachment image P3 is displayed on the display screen of the display device 3A, 3B, 3C, for example, when the user A speaks a voice including the specific word and "next page" as the command keyword, the voice processing device 1A recognizes the specific word and sends the command keyword to the cloud server 2. When the cloud server 2 receives the command keyword, it determines the command of "turning pages" (refer to Fig.11 ). The cloud server 2 identifies "user A", "user B", and "user C" as the target users for executing the command. The display devices 3A, 3B, and 3C respectively execute the identified commands. As a result, the attachment image P3 is switched to the image P4 of the next page on the display screens of the display devices 3A, 3B, and 3C (refer to Figure 5 ).

[0039] In addition, for example, when user A utters a voice including the specific word and "display" ... "" as the command keyword, the voice processing device 1A, when recognizing the specific word, sends the command keyword to the cloud server 2. When the cloud server 2 receives the command keyword, it determines the command of "displaying the designated file" (refer to Fig.11 ). Here, it is assumed that user A specifies "budget management table" as the designated file. The cloud server 2 determines the target user to execute the command. Here, the cloud server 2 refers to the content information D5 (reference Fig.12 ), "User A" and "User B" who are allowed to read the "Budget Management Table" are determined as the target users for displaying and reading the "Budget Management Table". The display devices 3A and 3B respectively execute the determined command. As a result, the same image P5 (refer to Figure 6 ). In addition, the designated file is stored in advance in the database DB, for example, and its identification information (content ID "C001") is registered in the content information D5 (refer to Fig.12 ).

[0040] In addition, for example, when user A utters a voice including the specific word and "show Mr. "..." my reservations for this week" as the command keyword, the voice processing device 1A, when recognizing the specific word, sends the command keyword to the cloud server 2. When receiving the command keyword, the cloud server 2 determines the command of "reservation display" (refer to Fig.11 ). Here, it is assumed that "User C" is designated as the object for user A to display the reservation (schedule). Cloud server 2 determines the target user to execute the command. Here, cloud server 2 determines the speaker "User A" and "User C" designated by user A as the target users for displaying and viewing user A's reservation. Display devices 3A and 3C respectively execute the determined commands. As a result, the image P6 of user A's reservation for this week is displayed on the respective display screens of display devices 3A and 3C (refer to Figure 7 ). In addition, the reservation is stored in advance in the database DB, for example, and its identification information (reservation ID "S001") is registered in the user information D2 (refer to Fig. 9 ).

[0041] As described above, the conference system 100 executes a command with respect to a user determined according to the content of the command, thereby being able to appropriately transmit information corresponding to the command to the user. The specific structure of the conference system 100 is described below. In addition, in the following description, when the voice processing devices 1A, 1B, and 1C are not distinguished, they are referred to as "voice processing device 1". In addition, the cloud server 2 is described as a virtual server. In addition, the cloud server 2 can also be replaced by a physical server.

[0042] [Speech processing device 1]

[0043] like Figure 2 As shown, the speech processing device 1 includes: a control unit 11, a storage unit 12, a speaker 13, a microphone 14, and a communication interface 15. The speech processing device 1 may also be, for example, an AI speaker, a smart speaker, or other device. The speech processing device 1 is, for example, arranged on a table in a conference room, and acquires the speech of a user participating in the conference via the microphone 14, or outputs (notifies) speech to the user from the speaker 13.

[0044] The communication interface 15 is a communication interface for connecting the voice processing device 1 to the network N1 via wire or wirelessly, and performing data communication corresponding to a specified communication protocol between other devices (for example, other voice processing devices 1, cloud server 2, display device 3, database DB) via the network N1.

[0045] The storage unit 12 is a non-volatile storage unit such as a flash memory that stores various information. The storage unit 12 stores information for causing the control unit 11 to perform speech processing (see Fig.13 ) of the speech processing device 1. For example, the speech processing program is transmitted and stored from the cloud server 2. In addition, the speech processing program can also be recorded non-temporarily on a computer-readable recording medium such as a CD or a DVD, or can be read and stored in the storage unit 12 by a reading device (not shown) such as a CD drive or a DVD drive of the speech processing device 1.

[0046] The control unit 11 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various arithmetic operations. The ROM stores control programs such as a BIOS and an OS in advance for the CPU to perform various processes. The RAM stores various information and is used as a temporary memory (operation area) for various processes to be performed by the CPU. In addition, the control unit 11 controls the speech processing device 1 by executing various control programs pre-stored in the ROM or the storage unit 12 through the CPU.

[0047] Specifically, the control unit 11 includes various processing units such as a voice receiving unit 111, a speaker determining unit 112, a voice determining unit 113, a voice sending unit 114, and a response processing unit 115. In addition, the control unit 11 performs various processing corresponding to the control program through the CPU so as to function as the various processing units. In addition, part or all of the processing units included in the control unit 11 may also be composed of electronic circuits. In addition, the voice processing program may also be a program for causing multiple processors to function as the various processing units.

[0048] The voice receiving unit 111 receives the voice uttered by the user using the voice processing device 1. The voice receiving unit 111 is an example of the voice receiving unit of the present invention. The user utters, for example, voices related to a meeting, voices of specific words (also called start words, wake-up words) for the voice processing device 1 to start accepting commands, and voices (command voices) of various commands to instruct the voice processing device 1. The voice receiving unit 111 receives various voices uttered by the user.

[0049] The speaker determination unit 112 determines the user (speaker) who made the speech based on the speech received by the speech receiving unit 111. The speaker determination unit 112 is an example of the speaker determination unit of the present invention. For example, the speaker determination unit 112 compares the speech received by the speech receiving unit 111 with the user speech pre-registered in the storage unit 12 to determine the speaker. In addition, the speaker determination unit 112 may also determine the speaker based on the speech received by the speech receiving unit 111 and the captured image captured by the camera (not shown). For example, the speaker determination unit 112 determines the direction in which the speech is received (the direction of the speaker) based on the audio collection direction of the microphone 14, and determines the speaker based on the captured image included in the direction. For example, when the captured image included in the direction includes a user, the speaker determination unit 112 determines the user as the speaker.

[0050] The speech determination unit 113 determines whether the speech contains the specific word based on the speech received by the speech receiving unit 111. The speech determination unit 113 is an example of the speech determination unit of the present invention. For example, the speech determination unit 113 performs speech recognition on the speech received by the speech receiving unit 111 and converts it into text data. In addition, the speech determination unit 113 determines whether the specific word is included at the beginning of the text data.

[0051] The speech transmission unit 114 switches the transmission destination of the speech received by the speech receiving unit 111 based on the determination result of the speech determination unit 113. Specifically, when the speech determination unit 113 determines that the speech received by the speech receiving unit 111 contains the specific word, the speech transmission unit 114 transmits the text data of the keyword (command keyword) contained in the speech and adjacent to the specific word to the cloud server 2. In addition, when the speech determination unit 113 determines that the speech received by the speech receiving unit 111 does not contain the specific word, the speech transmission unit 114 transmits the speech to other speech processing devices 1. For example, the speech transmission unit 114 of the speech processing device 1A transmits the speech that does not contain the specific word to the speech processing devices 1B and 1C.

[0052] Here, the voice transmission unit 114 may also have a structure for switching between the command transmission mode for transmitting the voice received by the voice receiving unit 111 to the cloud server 2 based on the determination result of the voice determination unit 113 and the voice transmission mode for transmitting the voice received by the voice receiving unit 111 to other voice processing devices 1. For example, when the voice determination unit 113 determines that the voice received by the voice receiving unit 111 contains the specific word, the voice transmission unit 114 sets (switches) the transmission mode to the command transmission mode. When the transmission mode is set to the command transmission mode, the voice transmission unit 114 transmits the command keyword (text data) next to the specific word to the cloud server 2. In addition, after the voice transmission unit 114 transmits the command keyword to the cloud server 2, it sets (switches) the transmission mode to the voice transmission mode. When the transmission mode is set to the voice transmission mode, the voice transmission unit 114 transmits the voice received by the voice receiving unit 111 to other voice processing devices 1. In this way, when the specific word is received, the voice sending unit 114 switches to the command sending mode and sends the command keyword to the cloud server 2, and switches to the voice sending mode when the sending process of the command keyword is completed. Thus, the command keyword is sent to the cloud server 2 every time the specific word is uttered, so it is possible to prevent the voice of the normal conversation from being mistakenly sent to the cloud server 2.

[0053] The response processing unit 115 obtains a response (command response) corresponding to the command determined in the cloud server 2 from the cloud server 2, and outputs the command response from the speaker 13. For example, when the command is content related to the output of information search, the response processing unit 115 obtains the result searched in the cloud server 2, and outputs the result from the speaker 13.

[0054] [Cloud Server 2]

[0055] like Figure 2 As shown, the cloud server 2 includes a control unit 21 , a storage unit 22 , a communication interface 23 , and the like.

[0056] The communication interface 23 is a communication interface used to connect the cloud server 2 to the network N1 via wired or wireless means, and to perform data communication corresponding to a prescribed communication protocol between other devices (e.g., voice processing devices 1A, 1B, 1C, display devices 3A, 3B, 3C, database DB) via the network N1.

[0057] The storage unit 22 is a non-volatile storage unit such as a flash memory that stores various information. The storage unit 22 stores information for causing the control unit 21 to perform speech processing (see Fig.13 ) of the speech processing program. For example, the speech processing program may be recorded non-temporarily on a computer-readable recording medium such as a CD or a DVD, or may be read and stored in the storage unit 22 by a reading device (not shown) such as a CD drive or a DVD drive provided by the cloud server 2. In addition, the storage unit 22 stores text data of the command keywords received from the speech processing device 1.

[0058] The control unit 21 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various arithmetic operations. The ROM pre-stores control programs such as BIOS and OS for the CPU to perform various processes. The RAM stores various information and is used as a temporary memory (operation area) for various processes to be performed by the CPU. In addition, the control unit 21 controls the cloud server 2 by executing various control programs pre-stored in the ROM or the storage unit 22 through the CPU.

[0059] In addition, the control unit 21 performs various processes by referring to the database DB. Figure 2 As shown, the database DB stores data such as conference information D1, user information D2, participant information D3, command information D4, content information D5, and content data D6.

[0060] exist Figure 8An example of conference information D1 is shown in . In conference information D1, for each conference, the corresponding “conference ID”, “name”, “start date and time”, “end date and time”, “attachment ID”, “participant ID” and other information are associated with each other and registered, “conference ID” is the identification information of the conference, and “name” is the name (agenda) of the conference. “Start date and time” is the start date and time of the conference, and “end date and time” is the end date and time of the conference. “Attachment ID” is the identification information of the file (material) used in the conference, and “participant ID” is the identification information (user ID) of the user participating in the conference. The file data corresponding to the attachment ID is stored in the database DB. The file data is included in the content data D6. If it is decided to hold a meeting, the conference information D1 is registered in advance by the person in charge. Figure 8 , it is shown that user A ("U001"), user B ("U002"), and user C ("U003") are registered as participants of the conference.

[0061] exist Fig. 9 An example of user information D2 is shown in FIG. In user information D2, corresponding information such as "user ID", "user name", and "reservation ID" are associated with each other and registered according to each user. In user information D2, not only the information of users participating in the meeting is registered in advance, but also the information related to all users who have the authority to use the conference system 100 is registered in advance. For example, the information of all employees of a company is registered in user information D2. "User ID" is the identification information of the user, and "user name" is the name of the user. "Reservation ID" is the identification information of the user's reservation (schedule). "Reservation ID" is registered as needed. The reservation data (schedule data) corresponding to the reservation ID is stored in the database DB. The reservation data is included in the content data D6.

[0062] exist Fig.10An example of participant information D3 is shown in FIG. In participant information D3, corresponding information such as “participant ID”, “participant name”, and “display device ID” are associated with each other and registered for each meeting. “Participant ID” is identification information of a user participating in a meeting, and “participant name” is the name of the user. “Display device ID” is the display device used by the participant, for example, identification information of display device 3 configured at the place (conference room) where the participant participates in the meeting. For example, a participant performs a login operation on display device 3 configured in the conference room, so that participant ID, participant name, display device ID, etc. are associated with each other and registered in participant information D3. For example, when user A enters and logs in user ID “U001” on the login screen displayed by display device 3A in conference room A, user ID “U001” is associated with identification information (display device ID) “D001” of display device 3A and registered in participant information D3. Similarly, when user B enters and logs in user ID "U002" on the login screen displayed by display device 3B in conference room B, user ID "U002" is associated with display device ID "D002" of display device 3B and registered in participant information D3, and when user C enters and logs in user ID "U003" on the login screen displayed by display device 3C in conference room C, user ID "U003" is associated with display device ID "D003" of display device 3C and registered in participant information D3. In addition, the login process is not limited to the method described. For example, a portable terminal (such as a smart phone) or an ID card carried by the user can also wirelessly communicate with display device 3 or voice processing device 1, so that each information is registered in participant information D3.

[0063] exist Fig.11 An example of command information D4 is shown in FIG. In command information D4, for each keyword (command keyword), corresponding information such as "keyword", "command", and "target user" are associated and registered. "Keyword" is information indicating the command keyword, and "command" is information indicating the content of the command. "Target user" is information indicating the user who is the target of executing the command. Fig.11 As shown, a predetermined command is registered for each keyword, and a target user is registered for each command.

[0064] For example, when the "command" is "start meeting", the "target user" is not registered. In addition, when the "command" is "help display", the "speaker" who wants to obtain information related to help is registered in the "target user". In addition, when the "command" is "attachment display", the attachment is registered in the meeting information D1 (refer to Figure 8) and is required for the meeting, so the "all participants" of the meeting are registered in the "target users". In addition, when the "command" is "turn pages", the "participants in the file display" that display the corresponding file are registered in the "target users".

[0065] Furthermore, when the "command" is "display of designated file", "permitted participants" are registered as participants who are allowed to view the designated file in the "target user". Fig.12 As shown, in the content information D5, for each content, the corresponding "content ID", "content name", "allowed user" and other information are associated with each other and registered. "Content ID" is the identification information of content such as files (document files, data files, reservations, etc.), images (static images, dynamic images, etc.). "Allowed user" is information indicating users who have access rights such as reading, displaying, and obtaining the content. For example, in the "budget management table" of content ID "C001", user A and user B have reading rights, but user C does not have reading rights. Therefore, for example, in the case where the "keyword" is "display budget management table", the "target user" becomes "user A" and "user B", and in the case where the "keyword" is "display patent drawings", the "target user" becomes "user A" and "user C".

[0066] Furthermore, when the "command" is "display reservations", the user designated as the speaker, that is, the "designated participant" corresponding to the user name (an example of the user identification term of the present invention) included in the keyword is registered in the "target users". For example, when the keyword is "show Mr. C my reservations for this week", "user A" and "user C" are registered in the "target users".

[0067] In addition, as another embodiment, part or all of the information such as conference information D1, user information D2, participant information D3, command information D4, content information D5, content data D6, etc. may be stored in any one of the voice processing device 1, cloud server 2, and display device 3, or may be stored in the above-mentioned multiple devices in a distributed manner. In addition, as another embodiment, the above-mentioned information may also be stored in a server that can be accessed from the conference system 100. In this case, the conference system 100 may also obtain the above-mentioned information from the server and perform the voice processing described later (refer to Fig.13 ) and other processing.

[0068] like Figure 2As shown, the control unit 21 includes various processing units such as a voice receiving unit 211, a command determining unit 212, a target user determining unit 213, and a command processing unit 214. In addition, the control unit 21 performs various processing corresponding to the control program through the CPU so as to function as the various processing units. In addition, a part or all of the processing units included in the control unit 21 may also be composed of electronic circuits. In addition, the control program may also be a program for causing a plurality of processors to function as the various processing units.

[0069] The speech receiving unit 211 receives the command keyword sent from the speech processing device 1. The command keyword is a word (text data) immediately adjacent to a specific word contained at the beginning of the text data of the speech received by the speech processing device 1. Specifically, when the speech processing device 1 detects the specific word and sends the command keyword to the cloud server 2, the cloud server 2 receives the command keyword.

[0070] The command determination unit 212 determines a command based on the command keyword received by the voice receiving unit 211. The command determination unit 212 is an example of the command determination unit 212 of the present invention. For example, the command determination unit 212 refers to the command information D4 stored in the database DB (refer to Fig.11 ), determine the command corresponding to the command keyword. In the present embodiment, a plurality of combinations of the command keywords and the commands are pre-registered in the command information D4, and the command consistent with the command keyword is determined from the command information D4, but the method of determining the command is not limited to this. For example, the command determination unit 212 may also interpret the meaning of the user's instruction content and determine the command based on the prescribed terms contained in the command keywords, such as "help", "file", "flip", etc., the overall phrase of the command keywords, the article structure, etc. For example, the command determination unit 212 may also determine the command from the command keywords using known methods such as morpheme analysis, article structure analysis, meaning analysis, and machine learning.

[0071] The target user determination unit 213 determines (decides) the target user to execute the command based on the content (category) of the command determined by the command determination unit 212. The target user determination unit 213 is an example of the target user determination unit of the present invention. For example, the target user determination unit 213 refers to the command information D4 (reference Fig.11), to determine the target user associated with the command determined by the command determination unit 212. For example, when a word (user determination word) for determining the target user is included in the command keyword, the target user determination unit 213 determines the target user based on the word. In addition, when the command is to display a specified content and the user's reading authority is set in the content, the target user determination unit 213 determines the user who is allowed to read the content as the target user.

[0072] The command processing unit 214 stores the information of the command determined by the command determination unit 212 in the command storage area (queue) corresponding to the display device 3 associated with the target user determined by the target user determination unit 213. For example, the storage unit 22 includes one or more command storage areas corresponding to the display device ID registered in the participant information D3. Here, the storage unit 22 includes a first queue K1 corresponding to the display device 3A with the display device ID "D001", a second queue K2 corresponding to the display device 3B with the display device ID "D002", and a third queue K3 corresponding to the display device 3C with the display device ID "D003".

[0073] For example, the command processing unit 214 stores the information of the command “help display” determined by the command determination unit 212 in the first queue K1 corresponding to the display device 3A with the display device ID “D001” associated with the user ID “U001” of the object user “user A” determined by the object user determination unit 213. In addition, for example, the command processing unit 214 stores the information of the command “attachment display” determined by the command determination unit 212 in: the first queue K1 corresponding to the display device 3A with the display device ID “D001” associated with the user ID “U001” of the object user “user A” determined by the object user determination unit 213, the second queue K2 corresponding to the display device 3B with the display device ID “D002” associated with the user ID “U002” of “user B”, and the third queue K3 corresponding to the display device 3C with the display device ID “D003” associated with the user ID “U003” of “user C”. Similarly, for example, the command processing unit 214 stores information of the command “scheduled display” determined by the command determination unit 212 in the first queue K1 corresponding to the display device 3A and the third queue K3 corresponding to the display device 3C.

[0074] The data (commands) stored in each queue are taken out by the display device 3 corresponding to each queue, and the display device 3 executes the commands.

[0075] [Display device 3]

[0076] like Figure 2As shown, the display device 3 includes a control unit 31 , a storage unit 32 , an operation unit 33 , a display unit 34 , a communication interface 35 , and the like.

[0077] The operation unit 33 is a mouse, keyboard, or touch panel that accepts user operations of the display device 3. The display unit 34 is a display panel such as a liquid crystal display or an organic EL display that displays various information. The operation unit 33 and the display unit 34 may also be an integrally formed user interface.

[0078] The communication interface 35 is a communication interface for connecting the display device 3 to the network N1 by wire or wirelessly, and performing data communication corresponding to a prescribed communication protocol between other devices (such as voice processing devices 1A, 1B, 1C, cloud server 2, database DB) via the network N1.

[0079] The storage unit 32 is a non-volatile storage unit such as a flash memory that stores various information. The storage unit 32 stores information for causing the control unit 31 to perform speech processing (see Fig.13 ) of the voice processing program. For example, the voice processing program may be recorded non-temporarily on a computer-readable recording medium such as a CD or a DVD, or may be read and stored in the storage unit 32 by a reading device (not shown) such as a CD drive or a DVD drive provided by the display device 3.

[0080] The control unit 31 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that performs various arithmetic operations. The ROM stores control programs such as a BIOS and an OS in advance for the CPU to perform various processes. The RAM stores various information and is used as a temporary memory (operation area) for various processes to be performed by the CPU. In addition, the control unit 31 controls the display device 3 by executing various control programs pre-stored in the ROM or the storage unit 32 through the CPU.

[0081] Specifically, the control unit 31 includes various processing units such as a command acquisition unit 311 and a command execution unit 312. In addition, the control unit 31 performs functions as the various processing units by executing various processes corresponding to the control program through the CPU. In addition, a part or all of the processing units included in the control unit 31 may also be composed of electronic circuits. In addition, the control program may also be a program for causing multiple processors to function as the various processing units.

[0082] The command acquisition unit 311 acquires the commands stored in the command storage area (queue) of the cloud server 2. Specifically, for example, the command acquisition unit 311 of the display device 3A monitors the first queue K1 corresponding to the display device 3A, and acquires the command when a command is stored in the first queue K1. Similarly, the command acquisition unit 311 of the display device 3B monitors the second queue K2 corresponding to the display device 3B, and acquires the command when a command is stored in the second queue K2. In addition, the command acquisition unit 311 of the display device 3C monitors the third queue K3 corresponding to the display device 3C, and acquires the command when a command is stored in the third queue K3. In addition, the command processing unit 214 of the cloud server 2 may also send data related to the command to the corresponding display device 3, and the command acquisition unit 311 acquires the command.

[0083] The command execution unit 312 executes the command determined by the command determination unit 212 of the cloud server 2 relative to the object user determined by the object user determination unit 213 of the cloud server 2. The command execution unit 312 is an example of a command execution unit of the present invention. Specifically, the command execution unit 312 executes the command acquired by the command acquisition unit 311. For example, the command execution unit 312 of the display device 3A executes the command stored in the first queue K1 acquired by the command acquisition unit 311. Similarly, the command execution unit 312 of the display device 3B executes the command stored in the second queue K2 acquired by the command acquisition unit 311. In addition, the command execution unit 312 of the display device 3C executes the command stored in the third queue K3 acquired by the command acquisition unit 311.

[0084] For example, the command execution unit 312 of the display device 3A displays the help image P1 on the display screen of the display unit 34 of the display device 3A (see Figure 4 ). In addition, the command execution unit 312 of each of the display devices 3A, 3B, and 3C displays the attachment image P3 on the display screen of each of the display units 34 of the display devices 3A, 3B, and 3C (see Figure 5 ). In addition, the command execution unit 312 of each display device 3A, 3B displays the image P5 of the designated file (for example, "budget management table") on the display screen of the display unit 34 of each display device 3A, 3B (refer to Figure 6 ). In addition, the command execution unit 312 of each display device 3A, 3C displays a predetermined image P6 (for example, "the predetermined image of user A") on the display screen of each display unit 34 of the display device 3A, 3C (see Figure 7 ).

[0085] In this way, when the first user is determined by the object user determination unit 213 as the object user for executing the first command, the command execution unit 312 displays the first content corresponding to the first command on the first display device 3. On the other hand, when the first user and the second user are determined by the object user determination unit 213 as the object users for executing the second command, the command execution unit 312 displays the second content corresponding to the second command on the first display device 3 and the second display device 3.

[0086] [Speech Processing]

[0087] Below, refer to Fig.13 as well as Fig.14 An example of a process of speech processing performed by the control unit 11 of the speech processing device 1, the control unit 21 of the cloud server 2, and the control unit 31 of the display device 3 is described. Figure 1 In the conference system 100 shown, the speech processing is described with an eye on the speech processing device 1A and the display device 3A. For example, the control unit 11 of the speech processing device 1A receives the speech of the user A to start the execution of the speech processing program, and then starts the execution of the speech processing. In addition, the speech processing is executed separately and in parallel in each of the speech processing devices 1A, 1B, and 1C.

[0088] In addition, the present invention can be an invention of a voice processing method for executing one or more steps included in the voice processing. In addition, one or more steps included in the voice processing described herein can also be appropriately omitted. In addition, the steps in the voice processing can also be executed in different orders within the scope of producing the same effect. Moreover, the case where the steps in the voice processing are executed by the control units 11, 21, and 31 is cited as an example for explanation. In other embodiments, the steps in the voice processing can also be executed in a distributed manner by one or more processors.

[0089] In step S101, the control unit 11 of the speech processing device 1A determines whether a speech is received from user A. When the control unit 11 receives the speech from user A (S101: Yes), the process moves to step S102. The control unit 11 waits until the speech is received from user A (S101: No). Step S101 is an example of a speech receiving step of the present invention.

[0090] In step S102, the control unit 11 determines whether to determine the speaker based on the received voice. When the control unit 11 determines the speaker (S102: Yes), the process transfers to step S103. When the control unit 11 does not determine the speaker (S102: No), the process returns to step S101. Step S102 is an example of the speaker determination step of the present invention.

[0091] In step S103, the control unit 11 recognizes the voice. Specifically, the control unit 11 recognizes the voice and converts the voice data into text data.

[0092] Then, in step S104, the control unit 11 determines whether the text data contains the specific word. When the control unit 11 determines that the text data contains the specific word (S104: Yes), the process transfers to step S105. On the other hand, when the control unit 11 determines that the text data does not contain the specific word (S104: No), the process transfers to step S106. When the text data does not contain the specific word, the voice is the voice of the conversation in the meeting, so in step S106, the control unit 11 sends the voice as voice data to other voice processing devices 1B, 1C. Step S104 is an example of the voice determination step of the present invention.

[0093] In step S105 , the control unit 11 transmits text data of a keyword (command keyword) next to the specific word to the cloud server 2 .

[0094] The control unit 21 of the cloud server 2 receives the text data of the command keyword from the speech processing device 1A. In step S107, the control unit 21 determines the command corresponding to the command keyword. For example, the control unit 21 refers to the command information D4 (reference Fig.11 ), determine the command corresponding to the command keyword. Step S107 is an example of the command determination step of the present invention.

[0095] Next, in step S108, the control unit 21 determines the target user who executes the determined command. Specifically, the control unit 21 determines the target user based on the content (category) of the command. For example, the control unit 21 refers to the command information D4 (reference Fig.11 ), determine the target user associated with the command. Step S108 is an example of the target user determination step of the present invention.

[0096] Next, in step S109, the control unit 21 stores the determined command in the command storage area (queue) corresponding to the display device 3 associated with the determined target user. For example, the control unit 21 stores the command in the display device 3A ("D001") associated with user A as the target user (refer to Fig.10 ) corresponds to the first queue K1 (refer to Figure 2 ).

[0097] Next, in step S110, the control unit 31 of the display device 3 obtains the command from the command storage area corresponding to the device and executes the command. For example, when the command is stored in the first queue K1, the control unit 31 of the display device 3A obtains and executes the command. Step S110 is an example of the command execution step of the present invention.

[0098] Here, specific examples of the command identification process of step S107 and the target user identification process of step S108 will be described. Fig.14 1 is a flowchart showing an example of the process S200 including the command determination process and the target user determination process.

[0099] In step S107, when a command corresponding to the command keyword is determined, in step S21, the control unit 21 of the cloud server 2 determines whether the command is "start a meeting". In the case where the control unit 21 determines that the command is "start a meeting" (S21: Yes), the process transfers to step S111. For example, the control unit 21 sends the command to the display device 3 of the target. In step S111, the control unit 31 of the display device 3 executes the "start a meeting" command, and the connection is completed (refer to Figure 3 On the other hand, when the control unit 21 determines that the command is not "start meeting" (S21: No), the process moves to step S22.

[0100] In step S22, the control unit 21 determines whether the command is "Help display". In the case where the control unit 21 determines that the command is "Help display" (S22: Yes), the processing transfers to step S221. In step S221, the control unit 21 determines the speaker as the target user. Thereafter, in step S110, the control unit 21 stores the command in the command storage area of ​​the display device 3 associated with the speaker. As a result, a helpful image P1 (refer to Figure 4 On the other hand, when the control unit 21 determines that the command is not "help display" (S22: No), the process moves to step S23.

[0101] In step S23, the control unit 21 determines whether the command is "attachment display". In the case where the control unit 21 determines that the command is "attachment display" (S23: Yes), the processing transfers to step S231. In step S231, the control unit 21 determines all participants of the meeting as the target users. Thereafter, in step S110, the control unit 21 stores the command in the command storage area of ​​each display device 3 associated with each participant. As a result, the display screen of the display unit 34 of each display device 3 displays the attachment image P3 (refer to Figure 5 On the other hand, when the control unit 21 determines that the command is not "display attachment file" (S23: No), the process proceeds to step S24.

[0102] In step S24, the control unit 21 determines whether the command is "turn the page". In the case where the control unit 21 determines that the command is "turn the page" (S24: Yes), the processing transfers to step S241. In step S241, the control unit 21 determines the participant in the file display as the target user. Thereafter, in step S110, the control unit 21 stores the command in the command storage area of ​​each display device 3 associated with each participant. As a result, in the display screen of the display unit 34 of each display device 3, the image being displayed (for example, the attachment image P3) is switched to the image P4 of the next page (refer to Figure 5 On the other hand, when the control unit 21 determines that the command is not "turn the page" (S24: No), the process proceeds to step S25.

[0103] In step S25, the control unit 21 determines whether the command is "specified file display". In the case where the control unit 21 determines that the command is "specified file display" (S25: Yes), the processing transfers to step S251. In step S251, the control unit 21 determines the user who is allowed to browse the specified file as the target user. Then in step S110, the control unit 21 stores the command in the command storage area of ​​each display device 3 associated with the allowed user. As a result, the display screen of the display unit 34 of each display device 3 displays the image P5 (refer to Figure 6 On the other hand, when the control unit 21 determines that the command is not "designated file display" (S25: No), the process moves to step S26.

[0104] In step S26, the control unit 21 determines whether the command is "scheduled display". In the case where the control unit 21 determines that the command is "scheduled display" (S26: Yes), the processing transfers to step S261. In step S261, the control unit 21 determines the user specified in the command keyword as the target user to display the scheduled (schedule). Then in step S110, the control unit 21 stores the command in the command storage area of ​​the display device 3 associated with the specified user. As a result, the display screen of the display unit 34 of the display device 3 displays the image P6 (refer to Figure 7 On the other hand, when the control unit 21 determines that the command is not "predetermined display" (S26: No), the process moves to step S27. In step S27, as shown in the above example, the control unit 21 specifies the command specified by the user and the target user of the command.

[0105] As described above, the conference system 100 performs the voice processing. As described above, the conference system 100 according to the present embodiment determines the target user for executing the command based on the content of the command issued by the user, and executes the command with respect to the determined target user, thereby providing the information corresponding to the command only to the user who needs the information. Thus, the information corresponding to the command can be appropriately delivered to the user.

[0106] Furthermore, the speech processing system of the present invention can be configured by freely combining the above-described embodiments, or by appropriately modifying or partially omitting the embodiments within the scope of the invention described in the claims.

[0107] The scope of the present invention is not limited to the above content, but is defined by the description of the claims, so it can be considered that the embodiments described in this specification are only illustrative, not limiting. Therefore, all changes that do not depart from the scope and limits of the claims and the contents that are equivalent to the scope and limits of the claims are included in the scope of the claims.

Claims

1. A speech processing system, comprising: Multiple terminal devices are configured in different locations; A plurality of speech processing devices are respectively arranged in the different locations; and a server, connected to the plurality of terminal devices and the plurality of voice processing devices respectively via a network, characterized in that: The server has: a plurality of command storage areas corresponding to the plurality of terminal devices respectively; a speech receiving unit that receives a speaker's speech from each of the plurality of speech processing devices; a speaker identifying unit that identifies a speaker from a plurality of users located in each of the different locations based on the voice received by the voice receiving unit; a speech determination unit that determines, based on the speech received by the speech receiving unit, whether the speech contains a specific word for starting acceptance of a predetermined command; a command determination unit that, when the speech determination unit determines that the speech contains the specific word, determines the command based on a command keyword that is contained in the speech and is adjacent to the specific word; a target user determination unit that determines a target user who executes the command from among a plurality of users located in each of the different locations based on the content of the command determined by the command determination unit; and a command processing unit that stores information of the command determined by the command determination unit in the command storage area corresponding to the terminal device used by the target user determined by the target user determination unit, among the plurality of command storage areas; Each of the plurality of terminal devices includes a command execution unit, and the command execution unit monitors the command storage area corresponding to the terminal device itself. The command execution unit executes the command when information on the command is stored in the command storage area corresponding to the command execution unit.

2. The speech processing system according to claim 1, characterized in that: The target user identification unit refers to a storage unit that stores the command keyword, the command, and the target user in advance while being associated with each other, and identifies the target user based on the content of the command identified by the command identification unit.

3. The speech processing system according to claim 1, characterized in that: The target user identification unit identifies the target user based on the user identification word when the voice received by the voice receiving unit includes a user identification word for identifying the target user.

4. The speech processing system according to claim 1, characterized in that: When the command indicates that a predetermined content is to be displayed and the presence or absence of a user's browsing authority is set for the predetermined content, The target user identification unit identifies a user who is permitted to browse the predetermined content as the target user.

5. The speech processing system according to any one of claims 1 to 4, characterized in that: Each terminal device that is a target for executing the command determined by the command determination unit includes a command storage area. Each of the terminal devices is provided with the command execution unit, The first command execution unit of the first terminal device executes the first command when the first command is registered in the first command storage area corresponding to the first terminal device. The second command execution unit of the second terminal device executes the second command when the second command is registered in the second command storage area corresponding to the second terminal device.

6. The speech processing system according to any one of claims 1 to 4, characterized in that: The device further comprises a speech transmitting unit configured to, when the speaker identifying unit identifies a first user as the speaker of the speech received by the speech receiving unit, When the speech determination unit determines that the speech uttered by the first user does not include the specific word, the speech received by the speech reception unit is transmitted to the second user.

7. A conference system, wherein a voice processing device and a display device are arranged in each of different areas, a plurality of users exist in each area, and voice can be sent and received between the areas via the voice processing device, characterized in that: The conference system has: A plurality of command storage areas, which correspond to the plurality of display devices respectively; a speech receiving unit for receiving a speaker's speech from the speech processing device in the first area; a speaker determination unit that determines a speaker from among a plurality of users in the first area based on the speech received by the speech receiving unit; a speech determination unit that determines, based on the speech received by the speech receiving unit, whether the speech contains a specific word for starting acceptance of a predetermined command; a command determination unit that, when the speech determination unit determines that the speech contains the specific word, determines the command based on a command keyword that is contained in the speech and is adjacent to the specific word; a target user determination unit that determines a target user who executes the command from among a plurality of users in the first area based on the content of the command determined by the command determination unit; as well as a command processing unit that stores information of the command determined by the command determination unit in a first command storage area among the plurality of command storage areas that corresponds to the display device in the first area where the target user determined by the target user determination unit is located, Each of the plurality of display devices includes a command execution unit, and the command execution unit monitors the command storage area corresponding to the display device itself. The command execution unit of the display device in the first region executes the command when information of the command is stored in the first command storage region corresponding to the command execution unit.

8. A speech processing method for a speech processing system, the speech processing system comprising: Multiple terminal devices are configured in different locations; A plurality of speech processing devices are respectively arranged in the different locations; and a server connected to the plurality of terminal devices and the plurality of voice processing devices via a network, the server having a plurality of command storage areas corresponding to the plurality of terminal devices, respectively. The speech processing method is characterized in that one or more processors execute the following steps: A speech receiving step of receiving a speaker's speech from each of the plurality of speech processing devices; a speaker determining step of determining a speaker from a plurality of users located in each of the different locations based on the voice received by the voice receiving step; a speech determination step of determining, based on the speech received by the speech receiving step, whether the speech contains a specific word for starting acceptance of a prescribed command; a command determination step of, when the speech determination step determines that the speech contains the specific word, determining the command based on a command keyword contained in the speech and adjacent to the specific word; a target user determining step of determining a target user for executing the command from a plurality of users located in each of the different locations based on the content of the command determined in the command determining step; as well as a command processing step of storing information of the command determined in the command determining step in the command storage area corresponding to the terminal device used by the target user determined in the target user determining step, among the plurality of command storage areas; Each of the plurality of terminal devices includes a command execution unit, and the command execution unit monitors the command storage area corresponding to the terminal device itself. The command execution unit executes the command when information on the command is stored in the command storage area corresponding to the command execution unit.

9. A computer-readable recording medium storing a speech processing program, wherein the speech processing program is used in a speech processing system, the speech processing system comprising: Multiple terminal devices are configured in different locations; A plurality of speech processing devices are respectively arranged in the different locations; and a server, connected to the plurality of terminal devices and the plurality of voice processing devices respectively via a network, the server having a plurality of command storage areas, which correspond to the plurality of terminal devices respectively, characterized in that the voice processing program is used to execute the following steps through one or more processors: A speech receiving step of receiving a speaker's speech from each of the plurality of speech processing devices; a speaker determining step of determining a speaker from a plurality of users located in each of the different locations based on the voice received by the voice receiving step; a speech determination step of determining, based on the speech received by the speech receiving step, whether the speech contains a specific word for starting acceptance of a prescribed command; a command determination step of, when the speech determination step determines that the speech contains the specific word, determining the command based on a command keyword contained in the speech and adjacent to the specific word; a target user determining step of determining a target user who executes the command from a plurality of users located in each of the different locations based on the content of the command determined by the command determining step; and a command processing step of storing information of the command determined in the command determining step in the command storage area corresponding to the terminal device used by the target user determined in the target user determining step, among the plurality of command storage areas; Each of the plurality of terminal devices includes a command execution unit, and the command execution unit monitors the command storage area corresponding to the terminal device itself. The command execution unit executes the command when information on the command is stored in the command storage area corresponding to the command execution unit.