JP2018017764A - Robot and voice interactive method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable a natural conversation between robots.SOLUTION: A robot which structures a conversation system for dialogue between robots has: communication means for performing radio communication with other robot; speech sentence acquisition means for acquiring a speech sentence for the other robot; voice output means for outputting the speech sentence by a synthetic voice; speech transmission means for transmitting speech data which is data related to the speech sentence output by the voice output means to the other robot by radio communication; and speech reception means for acquiring the contents of a speech uttered by the robot by receiving the speech data transmitted by the robot that is an interactive mate.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a robot that interacts by voice.

  In recent years, robots that provide various information by interacting with people have been developed. For example, Patent Document 1 discloses a communication robot that processes voice input by a microphone on a network and returns a response to the input by voice.

  Further, when a plurality of robots capable of voice conversation are used, conversation between the robots becomes possible. For example, it can be enjoyed such that a plurality of users bring a robot and have a conversation with each other.

Japanese Patent Laid-Open No. 2015-013351 JP 2010-166377 A JP 2002-307354 A

  However, when a plurality of robots capable of voice recognition are tried to interact with each other, several problems occur. One problem is the accuracy of speech recognition. Since a general speech recognition model is intended for human voice, sufficient recognition accuracy may not be obtained for synthesized speech. Another problem is that it is difficult to determine which robot is talking to which robot. Since the synthesized speech has similar characteristics, it is difficult to discriminate, and when the number of speakers increases, the conversation may not be established correctly.

  The present invention has been made in consideration of the above-described problems, and an object of the present invention is to provide a technique that enables a natural dialogue between robots.

The robot according to the present invention is a robot constituting an interactive system in which robots interact with each other.
Specifically, a communication means for performing wireless communication with another robot, an utterance sentence acquisition means for acquiring an utterance sentence for the other robot, an audio output means for outputting the utterance sentence by synthesized speech, By receiving utterance data that is data related to the utterance sentence output by the voice output means to another robot by wireless communication, and by receiving the utterance data transmitted by the robot of the conversation partner, the robot And utterance receiving means for acquiring the content of the utterance uttered by.

The robot according to the present invention outputs an utterance sentence by voice and transmits utterance data, which is data related to the utterance sentence, by wireless communication. The utterance data may be, for example, text data including an utterance sentence, or data summarizing the contents of the utterance. Further, it may be data including the type of utterance and the emotion of the robot. Further, it may be data including information for identifying a robot that is a speech source and a robot that is a conversation partner.
According to such a configuration, it is possible to transmit data necessary for establishing a conversation to the robot on the other side while producing an effect that the robot is actually speaking through voice. That is, the conversation between the robots can be correctly established regardless of the accuracy of voice recognition.

  Further, the utterance sentence acquisition means may acquire an utterance sentence that becomes a reply to the robot using utterance data transmitted by the robot of the conversation partner.

  By using the utterance data transmitted from the robot of the conversation partner, an accurate response can be acquired.

  The speech data may include information for identifying a robot that performs speech. Further, the utterance data may include information for identifying the robot of the conversation partner.

  When the robot speaks, information identifying “who spoke” and “who spoke” is transmitted at the same time, so that the robot of the conversation partner can react correctly. In particular, when three or more robots interact with each other, the opponent can be correctly identified. In this way, there may be two or more robots as conversation partners.

  The utterance data includes information for identifying the owner of the robot that performs the utterance and the owner of the robot of the conversation partner, and the utterance sentence acquisition means acquires the utterance sentence by further using information about the owner. This may be a feature.

  There is a case where a robot owned by a user is brought into a conversation. In such a case, the robot acquires information about the owner, and generates an utterance sentence using the information, so that the conversation contents of the robot become rich in variety.

  In addition, this invention can be specified as a robot containing at least one part of the said means. It can also be specified as a voice interaction method performed by the robot. The above processes and means can be freely combined and implemented as long as no technical contradiction occurs.

  ADVANTAGE OF THE INVENTION According to this invention, the technique which enables the natural dialogue between robots can be provided.

1 is a system configuration diagram of a voice interaction system according to an embodiment. It is a data flow figure in an embodiment. It is a data flow figure in an embodiment.

Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.
The voice interaction system according to the present embodiment is a system in which a robot interacts with a user and other robots in a natural language.

<System configuration>
FIG. 1 is a system configuration diagram of a spoken dialogue system according to the present embodiment. The voice interaction system according to this embodiment includes a robot 10 and an interaction server 20. Although not shown in FIG. 1, the voice interaction system according to this embodiment can be configured to include a plurality of robots 10.

  First, the robot 10 will be described. The robot 10 is a robot having a function of acquiring a voice from the outside, a function of acquiring a utterance content sentence (hereinafter referred to as a uttered sentence) by communicating with the dialogue server 20, and a function of outputting the uttered sentence by voice. is there. The robot 10 is a communication robot, for example, but does not necessarily have a character shape. For example, it may be a general-purpose computer that can be incorporated into a robot.

  The robot 10 includes a communication unit 11, a voice input unit 12, a voice output unit 13, a short-range communication unit 14, and a control unit 15.

The communication unit 11 is means for communicating with the dialogue server 20 by accessing the network via a communication line (for example, a mobile phone network).
The voice input unit 12 is a means for acquiring voice. Specifically, sound is converted into an electrical signal (hereinafter referred to as sound data) using a microphone (not shown). The acquired voice data is transmitted to the control unit 15. The voice input unit 12 is mainly used to acquire voice uttered by the user.
The sound output unit 13 is a means for outputting sound. Specifically, voice data transmitted from the control unit 15 is converted into voice using a speaker (not shown).

  The short-range communication unit 14 is means for performing wireless communication between the robots 10. In the present embodiment, the short-range communication unit 14 performs communication using a Bluetooth (registered trademark) connection. In the present embodiment, two functions of “detection of another robot as a conversation partner” and “information exchange between robots” are realized using the short-range communication unit 14.

The control unit 15 is a means for controlling the overall voice conversation performed by the robot 10.
Specifically, a function for detecting the presence of a conversation partner (for example, a user or another robot) and starting a conversation, a function for acquiring an utterance sentence from the conversation server 20, and converting the acquired utterance sentence into voice data The function of outputting via the audio output unit 13 is executed.

  In the present embodiment, when the conversation partner is another robot, the control unit 15 converts the utterance sentence into voice data and outputs it, and at the same time, the text representing the contents of the utterance sentence (hereinafter referred to as utterance). Data) is transmitted to the robot of the conversation partner via the short-range communication unit 14 together with the identifier of the robot. In addition, when the utterance data is transmitted from another robot, the control unit 15 acquires the content of the utterance performed by the other robot based on the utterance data. Detailed processing contents will be described later.

  The dialogue server 20 is a server device that generates an utterance sentence based on data transmitted from the robot 10. The dialogue server 20 acquires voice data, utterance data, or information about a robot that is a dialogue partner from the robot 10 and generates an utterance sentence. The dialogue server 20 includes a communication unit 21, a voice recognition unit 22, and an utterance generation unit 23.

Since the function which the communication part 21 has is the same as that of the communication part 11 mentioned above, detailed description is abbreviate | omitted.
The voice recognition unit 22 is means for performing voice recognition on the voice data transmitted from the robot 10 and converting the voice data into text. Speech recognition can be performed by known techniques. For example, the speech recognition unit 22 stores an acoustic model and a recognition dictionary, extracts features by comparing the acquired speech data with the acoustic model, and matches the extracted features with the recognition dictionary to generate speech. Recognize.

The utterance generation unit 23 is a unit that generates an utterance sentence based on the data acquired from the robot 10 or the text output by the voice recognition unit 22. Specifically, based on one of (1) utterance data acquired from the robot 10, (2) information about a conversation partner acquired from the robot 10, and (3) text obtained as a result of voice recognition. Generate utterance sentences. When the conversation partner of the robot 10 is another robot 10, an utterance sentence is generated by the above-described (1) and (2), and when the conversation partner of the robot 10 is a human being, the utterance sentence is converted by the aforementioned (3). Generated. Each specific processing example will be described later with reference to a data flow diagram.

The utterance sentence may be generated by, for example, a dialogue scenario (a dialogue dictionary). Further, it may be information obtained by searching a database, or information obtained by web search.
The information acquired by the utterance generation unit 23 is transmitted to the robot 10 in a text format, and then output as synthesized speech.

  Both the robot 10 and the dialogue server 20 can be configured as an information processing apparatus having a CPU, a main storage device, and an auxiliary storage device. Each unit shown in FIG. 1 functions by loading a program stored in the auxiliary storage device into the main storage device and executing it by the CPU. Note that all or part of the illustrated functions may be executed using a circuit designed exclusively.

<Process flowchart>
Next, the content of specific processing performed by the robot 10 will be described.
First, the process in which the robot 10 and the user interact by voice will be described with reference to FIG. 2 which is a data flow diagram between apparatuses.

  First, in step S11, the voice input unit 12 acquires voice from the user of the apparatus through a microphone (not shown). The acquired voice is converted into voice data and transmitted to the dialogue server 20 (voice recognition unit 22).

  Next, the voice recognition unit 22 included in the dialogue server 20 performs voice recognition on the voice data transmitted from the robot 10 (step S12). The text as a result of recognizing the voice is transmitted to the utterance generation unit 23.

Next, the utterance generation unit 23 of the dialogue server 20 generates an utterance sentence based on the text output by the speech recognition unit 22 (step S13). The generated utterance sentence is transmitted to the robot 10 (control unit 15).
In step S <b> 14, the control unit 15 included in the robot 10 synthesizes speech based on the uttered sentence and outputs the synthesized speech via the speech output unit 13.

Next, processing when the robots 10 interact with each other will be described with reference to FIG.
Here, the first robot is referred to as the robot 10, and the second robot that interacts with the robot 10 is referred to as the robot 10 '. Further, each means possessed by the robot 10 ′ is distinguished by adding an apostrophe to the code.

First, in step S21, the control unit 15 generates a trigger (dialog start trigger) for starting a dialog between robots. In this example, when the robot 10 detects the presence of another robot in the vicinity of the robot 10 via the short-range communication unit 14, it is assumed that a dialogue start trigger is generated. For example, each robot may be configured to periodically broadcast its own identifier wirelessly, and when another robot is detected within a predetermined distance, an interaction start trigger may be generated. At this time, the control unit 15 further acquires an identifier of another detected robot (that is, a robot that is a conversation partner).

  Next, information for generating an utterance sentence is transmitted to the dialogue server 20 (the utterance generation unit 23). The information transmitted here is information regarding the robot of the conversation partner. For example, information on other robots detected in step S21 (for example, the number of conversation partners or identifiers) may be transmitted, or only information indicating that a conversation partner has been detected may be transmitted.

Next, the utterance generation unit 23 included in the dialogue server 20 generates an utterance sentence based on the information acquired from the robot 10 (step S22). The generated utterance sentence is transmitted to the robot 10 (control unit 15).
In step S <b> 23, the control unit 15 included in the robot 10 synthesizes speech based on the uttered sentence and outputs it through the speech output unit 13. At the same time, in addition to (1) utterance data, (2) the identifier of the robot that made the utterance and (3) the identifier of the partner robot are transmitted to the robot 10 ′ that is the conversation destination by wireless communication. Hereinafter, these three data are referred to as an utterance data set.

In step S24, when the robot 10 'receives the utterance data, it is determined whether or not the utterance data set is addressed to itself with reference to (3) above. Here, when the received utterance data set is addressed to itself, a dialog start trigger is generated.
And the information for producing | generating an utterance sentence is transmitted to the dialogue server 20 (utterance production | generation part 23). The information transmitted here is the utterance data set itself transmitted from the robot 10.
In this example, the utterance data set itself is transmitted to the dialog server 20, but other information may be additionally transmitted to the dialog server 20 as long as the information is related to the dialog partner. For example, a summary of the utterance content, the type of the utterance sentence, and the emotion of the partner robot may be transmitted.

Next, the utterance generation unit 23 included in the dialogue server 20 generates an utterance sentence based on the information acquired from the robot 10 ′ (step S25). The generated utterance sentence is transmitted to the robot 10 ′ (control unit 15 ′).
In the generation of the spoken sentence, the identifier of the robot that made the utterance and the identifier of the partner robot may be taken into account. For example, the dialog server 20 stores the robot profile, the owner profile of the robot, the contents of past conversations with the robot, etc., in association with the identifier of the robot, and uses them for generating spoken sentences. May be.

In step S26, the control unit 15 ′ of the robot 10 ′ synthesizes speech based on the utterance sentence acquired from the dialogue server 20, and outputs it through the speech output unit 13 ′. At this time, a new utterance data set is generated and transmitted to the robot 10 in parallel with the voice output.
Thereafter, the robots interact with each other by repeating the process described above.

As described above, in this embodiment, when a robot utters, the content of the utterance is transmitted to the partner robot by wireless communication. That is, the voice output performed by the robot is an effect for the user, and actual information is transmitted by wireless communication.
When the robots actually interact with each other via voice, depending on the environment in which the robot is placed, the voice recognition accuracy may not be ensured, and a correct response may not be generated. A highly accurate dialogue can be performed.

(Modification)
The above embodiment is merely an example, and the present invention can be implemented with appropriate modifications within a range not departing from the gist thereof.

For example, in the description of the embodiment, the dialogue server 20 performs voice recognition, but the robot 10 may be provided with means for performing voice recognition. Further, in the description of the embodiment, the response sentence is generated by the dialog server 20, but the robot 10 may generate the response sentence.
In the description of the embodiment, the robot 10 has interacted with the user. However, the means for performing input / output with the outside may be separated from the robot 10. For example, the audio output unit 13 and the audio input unit 12 may be independent.

  In the description of the embodiment, the presence of another robot is detected using short-range wireless communication, but other robots may be detected using means other than wireless communication. For example, another robot that is a conversation partner may be detected by capturing an image using a built-in camera and analyzing the image. Alternatively, the detected robot may be identified using a known technique such as pattern matching or barcode reading.

In the description of the embodiment, the utterance data and the robot identifier are included in the utterance data set, but other additional data may be added. For example, “current time”, “conversation type”, “robot emotion” may be added, and the utterance generation unit 23 may further generate an utterance sentence based on these pieces of information.
Also, in the description of the embodiment, the robot identifier is included in the utterance data set, but this is omitted when the robot that is the conversation partner can be uniquely identified, for example, when the robot that performs the conversation is one-to-one. Also good.

DESCRIPTION OF SYMBOLS 10 ... Robot 11, 21 ... Communication part 12 ... Voice output part 13 ... Voice input part 14 ... Voice recognition part 15 ... Short-range communication part 16 ... Control part 20 .. Dialog server 22 ... Utterance generator

Claims (7)

A robot constituting an interactive system in which robots interact with each other,
Communication means for performing wireless communication with other robots;
An utterance sentence acquisition means for acquiring an utterance sentence for the other robot;
Voice output means for outputting the utterance sentence by synthesized voice;
Speech transmission means for transmitting speech data, which is data related to a speech sentence output by the voice output means, to another robot by wireless communication;
Utterance receiving means for acquiring the content of the utterances uttered by the robot by receiving the utterance data transmitted by the robot of the conversation partner;
Robot with The utterance sentence acquisition means acquires an utterance sentence that becomes a response to the robot using the utterance data transmitted by the robot of the conversation partner.
The robot according to claim 1. The speech data includes information for identifying a robot that performs speech.
The robot according to claim 1 or 2. The utterance data includes information for identifying a robot of a conversation partner.
The robot according to claim 3. The utterance data includes information for identifying the owner of the robot that performs the utterance and the owner of the robot of the conversation partner,
The utterance sentence acquisition means acquires the utterance sentence by further using information about the owner.
The robot according to any one of claims 1 to 4. A voice dialogue method performed by robots that constitute a dialogue system in which robots interact with each other,
An utterance acquisition step for acquiring an utterance for another robot;
A voice output step of outputting the spoken sentence by synthesized voice;
A speech transmission step of transmitting speech data, which is data related to the speech sentence, to another robot by wireless communication;
An utterance receiving step of receiving utterance data from another robot;
Including
Using the utterance data sent by the robot of the conversation partner, acquire the content of the utterance uttered by the robot,
Voice interaction method.   A program for causing a computer to execute the voice interaction method according to claim 6.

Images