JP2005342862A - robot - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a robot having various functions so that a user does not get bored.
A robot control unit 100 that controls a robot includes a news acquisition unit 102 that acquires news, a reading unit 106 that outputs the news by voice, and a voice recognition unit 110 that recognizes a re-output request from the user. And a read instruction unit 112 that causes the read unit 106 to re-output the news read by the read unit 106 in response to a news re-output request from the user. As a result, the user can read the news read by the robot, usually like BGM, and can read the news again by speaking to the robot when there is news of interest, and know the contents of the news. be able to.
[Selection] Figure 5

Description

  The present invention relates to a robot capable of outputting sound.

  In recent years, with the development of computer technology, robots using computers have been developed, and some of them have been commercialized. For example, AIBO (trademark) commercialized by Sony Corporation and ASIMO (trademark) under development by Honda Motor Co., Ltd. are known.

JP 2000-353012 A JP 2000-200090 A

  Robots for communicating with people (users) are also being actively developed. In such a robot, it is also necessary to give the robot various variations so that the user does not get bored.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a robot having various functions so that the user does not get bored.

  According to the present invention, the information acquisition means for acquiring information, the voice output means for outputting the information by voice, and the information output by the voice output means in response to the information re-output request from the user to the voice output means. And an interactive robot characterized in that the interactive robot is re-outputted.

  Here, the information is, for example, news. The information acquisition means can acquire information by various methods, but can acquire information from other terminals connected via a network, for example. In the interactive robot according to the present invention, the voice output means sequentially outputs the information acquired by the information acquisition means. When the user requests to re-output any information, the voice output means re-outputs the information. Accordingly, the user can listen to the information in detail by requesting re-output to the robot when there is interested information while listening to the information normally like BGM.

  The interactive robot according to the present invention may further include a storage unit that stores information output by the voice output unit, and the playback unit sends the information to the voice output unit from the storage unit in response to a re-output request for information from the user. Applicable information can be read out.

  The interactive robot of the present invention may further include an analysis unit that analyzes the content of information acquired by the information acquisition unit.

  Based on the keywords included in the information, the analysis means is whether the information is “happy content (joy)”, “is angry content (anger)”, “sad content (sad)”, “fun content (easy ) "Etc. are analyzed. The interactive robot can include a storage unit that associates the type of information content with a keyword corresponding to the type. The analysis unit analyzes which type of information content is classified based on the keyword included in the information and the keyword stored in the storage unit.

  In the interactive robot according to the present invention, the voice output means can output information in a voice that conveys the atmosphere of the content to the user according to the content of the information.

  The voice output means outputs, for example, information with a pleasant voice such as a high voice or a bouncy voice for pleasant content information and a low voice or a tearful voice for information with a sad content. In this way, the user can grasp the type of information from the tone of the robot's voice while listening to the information like BGM, and can easily notice the information of interest. This makes it possible to know the information in detail without missing the information of interest.

  The interactive robot of the present invention may further include a voice storage unit that stores information contents and voice information that conveys the atmosphere of the contents in association with each other. The voice output unit refers to the voice storage unit. The information can be output based on the voice information associated with the content of the information to be output. Here, the audio information is an audio tone, tone, rhythm, and the like.

  The interactive robot according to the present invention may further include an effect execution means for performing an effect to convey the atmosphere of the content to the user according to the content of the information.

  For example, the direction execution means may make the interactive robot dance when it is information of happy content, and light that makes tears flow on the face of the interactive robot when information is sad. An effect can be produced. In addition, the effect execution means can play music corresponding to the content according to the content of the information. In this way, the user can grasp the type of information from the movement of the robot and the music while listening to the information like BGM, and can easily notice the information of interest. This makes it possible to know the information in detail without missing the information of interest.

  The interactive robot of the present invention can further include an effect content storage means for storing the contents of information and the effect contents that convey the atmosphere of the content in association with each other, and the effect execution means refers to the effect content storage means Thus, it is possible to produce an effect with the production content associated with the content of the information output by the audio output means.

  The interactive robot of the present invention may further include a replacement unit that replaces a predetermined word included in the information with another word, and the voice output unit outputs a voice using the other word replaced by the replacement unit. be able to.

  The interactive robot according to the present invention may further include a storage unit that stores a word to be replaced. The storage unit may store information about the user such as the name of the user and the name of the user's family. it can. The replacement means can replace a word such as a proper noun included in the information with a word representing information about the user. In this way, since the original information is replaced with information including information about the user, a person who has heard the voice output by the interactive robot can feel happily.

  According to the present invention, there is provided an interactive robot characterized by including means for acquiring a user's voice and voice output means for imitating the user's voice and outputting the same words.

  As a result, the user can enjoy the conversation with the interactive robot and objectively know how he / she is speaking.

  According to the present invention, the voice output means for making an inquiry to the user, the storage means for storing the user's voice for the inquiry in association with the user, and analyzing the user's voice stored in the storage means, There is provided an interactive robot characterized by including parameter acquisition means for acquiring a parameter indicating the characteristics of the voice of the user.

  Here, the voice output means can perform various dialogs with the user with normal voice. The user makes various comments while having fun by interacting with the interactive robot. Thereby, it becomes easy to acquire a user's voice. Therefore, since various voices of the user are stored in the storage means, the parameter acquisition means can more accurately analyze the parameters indicating the characteristics of the user's voice.

  In the interactive robot according to the present invention, the voice output means can output the same word by imitating the voice of the user by using the voice generated based on the user parameter.

  As a result, the user can enjoy the conversation with the interactive robot and objectively know how he / she is speaking. Further, it is possible to further interact with the user and to acquire more user's voice. Based on this, the parameter acquisition means can re-acquire the parameter indicating the feature of the user's voice.

  In the interactive robot of the present invention, the features can include the pitch, speed, and accent of the user's voice.

  According to the present invention, there is provided an interactive robot comprising: a parameter acquisition unit that acquires a parameter indicating a voice characteristic of a specific person; and a voice output unit that outputs a voice generated based on the parameter. Provided.

  As a result, a user who interacts with an interactive robot can feel as if he / she is interacting with a desired specific person when interacting with the interactive robot, and enjoy interacting with the robot. Can do.

  The interactive robot according to the present invention includes a storage unit that stores a parameter indicating a voice characteristic of a specific person in association with the specific person, and a reception unit that receives a designation of a person who wants to perform a dialogue from the user. Further, the parameter acquisition means can acquire the parameter of the person received by the reception means from the storage means.

  In the interactive robot of the present invention, the features can include the pitch, speed, and accent of a particular person's voice.

  According to the present invention, a music playback means for playing back music, an information acquisition means for acquiring information related to music, and a voice output means for outputting information related to the music by voice when the music playback means plays back music. , A music playback robot characterized by including:

  As a result, the user can listen to the music with the robot and feel as if the DJ is introducing the music.

  In the music playback robot of the present invention, the information acquisition means can acquire information related to the music from another terminal connected via the network based on the identification information of the music included in the music. By doing in this way, the information acquisition means can acquire the latest information regarding the music, and the user can listen to the latest information.

  The music playback robot of the present invention may further include timing control means for controlling the timing at which the music playback means outputs music and the timing at which the voice output means outputs information related to music in voice.

  The control means can, for example, allow the audio output means to output information about music at the same time as the music starts, and to play the music after the audio output of the audio output means is finished. It is also possible to output the sound from the sound output means after the music ends.

  In the music playback robot of the present invention, the timing control means can control the sound output means so that information related to music is output only while the introduction is being played in the music.

  In the music playback robot of the present invention, the information acquisition means can acquire information related to the music or information related to the music to be reproduced next while the music playback means is reproducing music.

  According to the present invention, the character information acquisition means for acquiring the character information represented by the characters, the replacement means for replacing the character information with a sentence of a predetermined tone while maintaining the meaning of the information, and the replacement means replaced There is provided a voice output robot comprising voice output means for outputting a sentence as voice.

  Here, the predetermined tone is, for example, “lap tone”, “old sentence tone”, “period drama tone”, or the like. The character information is e-mail, for example. In this way, since the robot arranges character information such as an e-mail received by the user and outputs the voice, the user can enjoy it.

  The voice output robot of the present invention further includes music playback means for playing music that matches the tone, and the music playback means can play music when the voice output means outputs a sentence.

  According to the present invention, an interactive robot having language conversion means, which is an analysis means capable of analyzing at least two languages, and responds to a user's inquiry in a preset first language. In addition, an interactive robot is provided that includes voice output means that responds in a second language in response to a language conversion request from a user.

  Here, the language includes, for example, old languages and dialects in addition to a plurality of languages. In this way, the user can enjoy interacting with the robot in various languages and can also learn the language.

  According to the present invention, it is possible to prevent the user from getting bored by giving the robot various functions.

Next, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a block diagram showing a configuration of a robot used in the present embodiment.
The robot 20 includes a voice input unit 32, an image input unit 34, a voice recognition unit 36, an image recognition unit 38, an action determination unit 40, a storage unit 42, a voice output unit 44, and an operation unit 46. Have.

  The voice input means 32 is, for example, a microphone. The image input means 34 is, for example, a CCD camera. The audio output means 44 is, for example, a speaker. The operation means 46 is, for example, an actuator that moves the robot's head or limbs, or a monitor or lamp that expresses a facial expression.

  The voice recognition unit 36, the image recognition unit 38, the action determination unit 40, and the storage unit 42 are realized by the controller 10 described later.

  FIG. 2 is a diagram showing an appearance (front view) of the robot 20 in the present embodiment. FIG. 3 is a diagram showing an electrical configuration of the robot 20 shown in FIG. Hereinafter, a description will be given with reference to FIGS. 2 and 3.

  In the present embodiment, the robot 20 has a configuration in which the body 1 and the head 2 are connected. Two wheels 3 are attached to the lower part of the body part 1 on the left and right. These wheels 3 can rotate back and forth independently. The head 2 is provided so as to be rotatable with respect to the body 1.

  The body unit 1 houses a controller 10 that controls the entire robot 20, a battery 11 that is a power source of the robot 20, a speaker 12, an actuator 14 that moves the wheels 3, and the like.

  The head 2 houses a microphone 13, two CCD cameras 21, an actuator 22 for rotating the head 2, and the like.

  The microphone 13 provided in the head 2 collects surrounding sounds including the speech from the user, and sends the obtained sound signals to the controller 10. Here, the robot 20 is configured to include only one microphone 13, but the robot 20 includes a plurality of microphones 13 and performs noise suppression processing or the like using sound input from the plurality of microphones 13. You can also. Thereby, recognition of a user's voice can be performed easily.

  The two CCD cameras 21 provided on the head 2 image the surrounding situation and send the obtained image signals to the controller 10. Here, the two CCD cameras 21 can be arranged so as to be visible to the robot 20.

  The controller 10 includes a CPU 10A and a memory 10B. The memory 10B stores a control program. In the CPU 10A, various processes are executed by executing the control program stored in the memory 10B.

  Based on the audio signal obtained from the microphone 13 and the image signal given from the CCD camera 21, the controller 10 determines the surrounding situation and a command from the user.

  Further, the controller 10 determines the subsequent action of the robot 20 based on the determination result of the instruction from the user. Next, the controller 10 drives the actuator 22 and the like so that the robot 20 performs the determined action. Actions such as rotating the head 2 of the robot 20 up and down, left and right, and moving or rotating the robot 20 can be performed.

  Moreover, the controller 10 produces | generates a synthetic | combination sound as needed, supplies it to the speaker 12, and outputs an audio | voice.

  FIG. 4 is a functional block diagram showing the controller 10 of FIG. 3 in detail. Note that the functional configuration shown in FIG. 4 is realized by the CPU 10A executing the control program stored in the memory 10B.

  The controller 10 recognizes the external state based on the sensor input processing unit 51, the recognition result of the sensor input processing unit 51, the behavior determination unit 52 that determines the subsequent behavior, and the actuator 14 based on the determination result of the behavior determination unit 52. And a control unit 53 that controls the actuator 22, a speech synthesis unit 54 that generates a synthesized sound, an output unit 55 that controls the output of the synthesized sound synthesized by the speech synthesis unit 54, and a storage unit 56 that stores the behavior of the robot including.

  The sensor input processing unit 51 recognizes an external state, a specific action from the user, or the like based on an audio signal and an image signal obtained from the microphone 13 and the CCD camera 21, and represents state recognition information indicating the recognition result. Is notified to the action determination unit 52.

  The sensor input processing unit 51 includes an image recognition unit 51 </ b> A that performs image recognition processing using an image signal obtained from the CCD camera 21. 51 A of image recognition parts can detect the person who exists in an image, As a result of the process, "there is a person", "ID corresponding to the person", "the position on the person's image", etc. The action recognition unit 52 is notified of the image recognition result as state recognition information. When there are a plurality of persons in the image, the image recognition unit 51A can notify the action determination unit 52 of information regarding each of the plurality of persons. In the present embodiment, the robot 20 has the two CCD cameras 21, but the robot 20 may be configured to have one CCD camera 21.

  Further, the sensor input processing unit 51 includes a voice recognition unit 51B that performs voice recognition on the voice signal obtained from the microphone 13. Voice recognition unit 51B is, as a result of the voice recognition, for example, "Good morning", the words such as "Hello", as state recognition information, and notifies the action determining section 52.

  The behavior determination unit 52 refers to the storage unit 56 based on the state recognition information from the sensor input processing unit 51 and determines the next behavior. Then, the content of the determined action is sent to the control unit 53 as an action command and to the voice synthesis unit 54 as a synthesized utterance command.

  The action determining section 52, "Good morning" as the state recognition information, "Hello" voice recognition results and the like, "people are present one person", the image recognition result of "ID of the person is a K", image recognition Received from the unit 51A and the voice recognition unit 51B. When receiving the voice recognition result, the behavior determining unit 52 refers to the storage unit 56 and obtains the operation information of the robot 20 corresponding to the voice recognition result or the event recognition result. In addition, when receiving the image recognition result, the behavior determining unit 52 refers to the storage unit 56 and acquires information such as the name of a person included in the image recognition result.

  The storage unit 56 stores operation information of the robot 20 corresponding to the state recognition information from the sensor input processing unit 51. The robot motion information stored in the storage unit 56 includes a synthetic utterance command and a robot motion command. The synthetic utterance command includes content to be uttered by the robot, which is character string information to be uttered, an instruction to utter the name of the currently detected person, or Composed of a combination of them.

  The storage unit 56 stores information such as the name of the person corresponding to the ID obtained as the image recognition result, and information such as the name of the person can be obtained from the ID.

  As a method for identifying a person, a method of registering a face image and collating it can be considered, or a method of detecting a marker by attaching a marker unique to the person to the person. A wireless IC tag may be used for person / object identification. In this case, it is necessary to separately provide a means for putting a wireless IC tag in a name tag or the like and holding a person, attaching a wireless IC tag to an object, and recognizing information from the wireless IC tag. Although an example in which a person is identified by an image signal is shown here, it is also possible to identify a person by an audio signal.

  When the action determining unit 52 obtains the robot motion information from the storage unit 56, the behavior determining unit 52 interprets the synthesized utterance command, generates an uttered character string, sends it to the voice synthesizer 54, and sends the robot motion command to the control unit 53.

  For example, the robot motion command corresponding to the voice recognition result of “good morning” is the content that the head 2 is shaken up and down to return to the front, and the synthetic utterance command utters the person name first if the person name is known. Next, the content is that a synthetic utterance “Good morning” is performed.

  The behavior determination unit 52 sends the behavior command read from the storage unit 56 to the control unit 53 and the voice synthesis unit 54.

  The control unit 53 generates a control signal for driving the actuator 14 and the actuator 22 based on the behavior command given from the behavior determination unit 52, and sends this to the actuator 14 and the actuator 22. Thereby, the actuator 14 and the actuator 22 are driven according to the control signal, and the robot 20 behaves autonomously.

  The output unit 55 is supplied with digital data of the synthesized sound from the voice synthesizer 54. The output unit 55 performs D / A conversion of the digital data into an analog voice signal, and a speaker. 12 for output.

  Further, the robot 20 in the present embodiment can play music or sing a song.

  Next, an example in which various functions are further added to the robot 20 having the above basic configuration will be described. Various robots 20 shown below have the above-described configuration described with reference to FIGS. In the following description, only the characteristic structure in each embodiment is shown.

<Announcer robot>
(First embodiment)
In the present embodiment, the robot 20 reads the news aloud, answers questions from the user, and rereads the news as necessary. The robot 20 in the present embodiment is usually located at a certain distance from the user and reads out various news contents aloud. When the user talks to the robot 20 such as “Present news, tell me in detail”, the user approaches the user and informs the user of the news read aloud at that time.

  Thereby, the user can know the news by speaking to the robot 20 when there is news of interest while listening to the news like BGM.

FIG. 5 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 100 includes, for example, a news acquisition unit 102 that acquires news from a network 120 such as the Internet, a news storage unit 108 that stores news acquired by the news acquisition unit 102, and news acquired by the news acquisition unit 102. A classification processing unit 104 that performs classification. Here, the classification processing unit 104 classifies the news into, for example, “sports”, “entertainment”, “society”, “international” and the like. Note that, for example, when news is already classified on a site where the news acquisition unit 102 acquires news, the classification processing unit 104 may be omitted.

  The robot control unit 100 further reads out the news from the news storage unit 108 and causes the robot to read it aloud, the voice recognition unit 110 for recognizing the user's inquiry, and when there is a rereading request from the user And a reading instruction unit 112 that causes the reading unit 106 to read the news from the news storage unit 108 again.

FIG. 6 is a diagram showing the news storage unit 108 in detail.
The news storage unit 108 includes an acquired news storage unit 108 a that stores the news acquired by the news acquisition unit 102, a classified news storage unit 108 b that stores the news classified by the classification processing unit 104, and a reading unit 106 that reads the news storage unit 108. And a cache unit 108c for temporarily storing the news. As described above, when the news acquisition unit 102 acquires already classified news, the news is stored in the classified news storage unit 108b.

  The reading unit 106 reads news from the classified news storage unit 108b. When there is an instruction from the read instruction unit 112, the instruction is read from the head of the news read at that time from the cache unit 108c. The news read by the reading unit 106 from the classified news storage unit 108b is stored in the cache unit 108c.

FIG. 7 is a flowchart showing a processing procedure of the robot control unit 100 in the present embodiment.
First, the news acquisition unit 102 acquires news (S10). Subsequently, the classification processing unit 104 classifies the news (S12). The robot controller 100 waits until an instruction to start reading news is received (NO in S14). When there is an instruction to start reading the news aloud (YES in S14), the reading unit 106 reads the news from the classified news storage unit 108b (S16). Subsequently, the robot's voice output unit (not shown) reads the news aloud (S18). Until there is an inquiry from the user (NO in S20), the news stored in the classified news storage unit 108b is sequentially read (S16) and read aloud (S18). During this time, the news read from the classified news storage unit 108b and read aloud is stored in the cache unit 108c.

  If there is any question from the user (YES in S20), the voice recognition unit 110 determines whether the question is a request for rereading news (S22). If the request is a reread request (YES in S22), the read instruction unit 112 causes the read unit 106 to read the news stored in the cache unit 108c and read the news aloud (S24).

  After that, based on the user's instruction or the like, it is determined whether or not to read the continued news (S26). If the continuation is read (YES in S26), the process returns to step S16 and the same operation is repeated.

  On the other hand, if the continuation is not read in step S26 (NO in S26), it is determined whether or not to end the operation (S28). The case where the operation is not terminated (NO in S28) is, for example, when another operation is requested by the user, and another operation is performed (S30).

  In step S20, when the inquiry from the user is not a re-reading request (NO in S22), the process proceeds to step S28, and the operation is terminated or another operation is performed. Here, for example, when the user makes an inquiry such as “be quiet” in step S20, the end of the operation is determined in step S28, and the reading of news is ended. On the other hand, for example, in step S20, when the user makes an inquiry such as “Let me listen to music”, reading aloud is finished, and processing (other operations) such as music reproduction is performed (S30).

  Further, the reading unit 106 can also say a comment such as “Next is entertainment news” at the beginning of reading the news according to the items classified in the classified news storage unit 108b.

  By giving the above functions to the robot 20, the user listens to the news that the robot 20 reads aloud while doing something like BGM, and when the news of interest is heard in the ear, You can know the news in detail.

(Second embodiment)
The robot 20 in this embodiment basically reads the news aloud as in the above embodiment. Further, in the present embodiment, the robot 20 has a function of analyzing the type of the news based on a keyword or the like included in the news. The robot 20 according to the present embodiment performs a way of speaking and operation that matches the type of news according to the type of news. The robot 20 reads the news sadly when, for example, sad content is included in the news text. Also, if the news text contains happy content, read the news happily.

FIG. 8 is a block diagram showing a configuration of the robot control unit 100 in the present embodiment.
The robot control unit 100 further includes an analysis processing unit 114, a keyword storage unit 115, an operation control unit 116, and an action pattern storage unit 117 in addition to the configuration shown in FIG.

  The analysis processing unit 114 performs the semantic analysis of the news acquired by the news acquisition unit 102, and for example, whether the news is “happy content (joy)”, “why content (anger)”, “sad content ( "Sorrow"), "Is it fun (Easy)", etc. The keyword storage unit 115 stores keywords for each of joy, anger, sorrow, and comfort. The analysis processing unit 114 refers to the keyword storage unit 115 and analyzes whether the news corresponds to joy, anger, sadness, or comfort. For example, keywords such as “murder”, “murder”, and “death” are associated with “sorrow”. In addition, keywords such as “price increase”, “injustice”, and “crime concealment” are associated with “anger”. The result analyzed by the analysis processing unit 114 is stored in the classified news storage unit 108b.

FIG. 9 is a diagram showing the classified news storage unit 108b in detail.
The classified news storage unit 108b has items of “classification”, “news”, and “type (joy / anger / sorrow / easy)”. For example, the news “sport / 0518/001” is classified as a sport, and the type is “joy (joyful content)”. Here, each item is flagged in the news analyzed as being of any kind of “joy, anger, sorrow, comfort”.

  For example, when the news includes keywords such as “killing” and “children”, it can be determined that the news is that the child has been killed, and “sorrow” can be flagged. In addition, if the news contains words such as “consumption tax” and “price increase”, it can be determined that the consumption tax has been raised and the flag “angry” can be set. . If a particular keyword is not included, no item is flagged.

  Returning to FIG. 8, when reading the news from the news storage unit 108, the reading unit 106 refers to the flag to determine the type of the news. The operation control unit 116 controls the robot to perform an operation representing “joy / anger / sadness / easy” according to the type of news. The action pattern storage unit 117 stores a pattern indicating what action the robot 20 performs for each of joy, anger, sorrow, and comfort. The operation control unit 116 controls the operation of the robot with reference to the behavior pattern storage unit 117. For example, when the news is happy, the robot may dance, and when the news is sad, a light effect such as tears flowing on the face of the robot 20 may be produced. In addition, the behavior pattern storage unit 117 can also store voice information so that the way the robot 20 speaks changes for each of joy, anger, sorrow, and comfort. For example, in the case of sad news, the robot 20 can speak in tears, speak in a low voice, or speak in a way that makes the voice clogged.

  Further, although not shown here, the robot control unit 100 can also include a music playback unit. Depending on the type of news, the fun control may cause fun music to flow in the background or sad news. When you can control so that sad music flows in the background.

FIG. 10 is a flowchart showing a processing procedure of the robot control unit 100 in the present embodiment.
First, the news acquisition unit 102 acquires news (S40). Subsequently, the classification processing unit 104 classifies the news (S42). Thereafter, the analysis processing unit 114 refers to the keyword storage unit 115, analyzes the content of the news, and determines the type of the news (S44). If it is determined that the content of the news applies to any of joy, anger, sorrow, and ease, a flag is set at a location corresponding to the type.

  The robot controller 100 waits until an instruction to start reading news is received (NO in S46). When there is an instruction to start reading the news aloud (YES in S46), the reading unit 106 reads the news from the classified news storage unit 108b (S48). The reading unit 106 determines whether or not a flag is set for the news (S50). When the flag is set (YES in S50), the operation control unit 116 refers to the behavior pattern storage unit 117 and instructs the robot to perform an operation according to the flag (S52). Next, the robot's voice output unit (not shown) reads the news aloud (S54). At this time, depending on the type of news, you can read happily or sadly.

  If none of the flags are set in step S50, it is read aloud normally (S54). Until there is an inquiry from the user (NO in S56), the news stored in the classified news storage unit 108b is sequentially read (S48), and the processing from step S50 to step S54 is repeated.

  If there is any question from the user (YES in S56), the voice recognition unit 110 determines whether the question is a request for rereading news (S58). If the request is a reread request (YES in S58), the read instruction unit 112 causes the read unit 106 to read the news stored in the cache unit 108c and read the news aloud (S60).

  Thereafter, based on the user's instruction or the like, it is determined whether or not to read the continued news (S62). When reading the continued (YES in S62), the process returns to step S48 and the same operation is repeated.

  On the other hand, if the continuation is not read in step S62 (NO in S62), it is determined whether or not to end the operation (S64). The case where the operation is not terminated (NO in S64) is, for example, when another operation is requested by the user, and another operation is performed (S66).

  In step S58, when the inquiry from the user is not a re-reading request (NO in S58), the process proceeds to step S64, and the operation is terminated or another operation is performed.

  By giving the above functions to the robot 20, the user can grasp the type of news from the tone and operation of the voice of the robot 20 while listening to the news read by the robot 20 like BGM. , Make it easier to notice interesting news. This makes it possible to know the news in detail without missing the news of interest.

  In the above, while the robot 20 is reading the news like BGM, it refers to the flag associated with each news and reads the news expressing the emotions according to the type of news. Explained. However, the robot 20 normally reads all the news in the same manner regardless of the presence or absence of the flag, and is angry according to the flag associated with the news only when rereading any of the news at the request of the user. You can also read sorrow.

(Third embodiment)
In the present embodiment, the robot 20 reads the news aloud basically as in the above embodiment. However, the robot 20 does not transmit the news as it is, but reads the news aloud by replacing a specific word included in the news with another word. The specific word is, for example, a proper noun.

Hereinafter, a description will be given with reference to FIG.
Although not shown here, the robot control unit 100 includes a replacement processing unit that extracts proper nouns from news and replaces them with other words, and a storage unit that stores words to be replaced. The news whose word is replaced by the replacement processing unit is stored in the news storage unit 108, and the reading unit 106 reads the news stored in the news storage unit 108.

  Here, the memory | storage part which memorize | stored the word which should be substituted can memorize | store the information regarding a user, such as a user's name and a user's family name, for example. Since the robot 20 according to the present embodiment can recognize a nearby user, the information about the user can be appropriately replaced with proper nouns included in the real news, and lie news can be read aloud. This makes it possible to listen to the news read out by the robot 20 using the news as a theme.

<Imitation Robot>
(Fourth embodiment)
In the present embodiment, the robot 20 grasps the characteristics of the voice of the user by interacting with the user and speaks in the same manner as the user.

FIG. 11 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 200 is analyzed by the user recognition unit 210 that recognizes the user of the conversation partner, the voice acquisition unit 202 that acquires the user's voice, the voice analysis unit 204 that analyzes the user's voice, and the voice analysis unit 204. A parameter storage unit 206 that stores parameters and an audio output unit 208 that outputs audio based on the parameters stored in the parameter storage unit 206 are included.

  Here, the parameter is, for example, a numerical value of pitch information, speed, accent, and the like. The pitch information includes a pitch frequency (basic frequency), pitch intensity, and the like. Such pitch information can be extracted by, for example, a cepstrum method (Patent Document 2). The robot control unit 200 can acquire various voices of the user by repeating the dialogue with the specific user, and analyze these to grasp the characteristics of the voice of the user. Further, the robot control unit 200 can determine whether the user is male or female from the user's voice, and can use the male or female voice quality as a parameter.

  As a result, the user can talk to the user and imitate the user, and the user can enjoy and can objectively know how he / she is speaking.

  Further, here, the interaction with the user can be performed for the purpose of acquiring the user's voice. In this case, the robot 20 performs various dialogs with the user with normal voices and collects the user voices. At this time, since the user is identified by the user recognition unit 210, even if the robot 20 interacts with a plurality of users, it is possible to acquire voice for each user. The voice analysis unit 204 calculates, for each user, a parameter indicating the characteristics of the user's voice based on the user's voice. The parameters indicating the characteristics of the user's voice acquired in this way can be used as it is by the robot, but for example, transferred to another robot via a medium such as a recording medium or a network and used by the other robot. You can also.

  FIG. 12 is a flowchart showing a processing procedure of the robot controller 200 shown in FIG.

  First, the user recognition unit 210 recognizes a user who has spoken to the robot (S100). The robot interacts with the user (S102). During this time, the voice acquisition unit 202 acquires the voice of the user in association with the user (S104). The voice analysis unit 204 analyzes the voice acquired by the voice acquisition unit 202 and calculates parameters (S106). The voice analysis unit 204 stores the calculated parameter in the parameter storage unit 206 in association with the user (S108).

  Through the processing as described above, the user performs various dialogs with the robot 20, so that it becomes easy to acquire the user's voice. Further, in the above example, the voice imitating the user's voice based on parameters such as pitch, speed, and accent is output. However, the robot control unit 200 further includes a storage unit that stores words used frequently by the user. The audio output unit 208 can also imitate the user's wording and the like. Thus, in order to acquire the user's wording, it is necessary to acquire as many user conversations as possible, but by interacting with the robot 20, more user conversations can be acquired.

(Fifth embodiment)
In the present embodiment, the robot 20 interacts with the user by imitating how a proper person speaks using parameters such as those obtained by the robot controller 200 shown in FIG.

FIG. 13 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 220 selects a parameter in the parameter storage unit 226 that stores parameters indicating the characteristics of the voice of the unique person, a dialoger selection reception unit 222 that receives selection of a partner with whom the user interacts, and a dialoger selection reception unit 222. A parameter acquisition unit 224 that acquires the parameters of the accepted conversation person from the parameter storage unit 226, and an audio output unit 228 that outputs audio based on the parameters acquired by the parameter acquisition unit 224 are included.

  Here, as described with reference to FIG. 11, the parameters of the unique person can be obtained by analyzing the voice obtained through the dialogue with the robot, but the unique person parameters obtained by other methods are also available. It can also be obtained by analyzing the voice. In addition, for example, a site that can obtain parameters of celebrities on the Internet can be provided and downloaded from there. In the present embodiment, the parameters may be acquired by any method.

  In the present embodiment, the parameter storage unit 226 stores a plurality of voice parameters in association with each person. The user can select which person he / she wants to interact with, and the dialoger selection receiving unit 222 receives a selection from the user. For this selection, for example, the name of each person such as “Taro (eldest son)”, “Jiro (second son)”, “Hikari (grandchild)” is displayed on the robot display screen, and the user selects one of the buttons. For example, when the user speaks “Hikari-chan”, the voice parameter of “Hikari” can be selected.

  Thus, for example, when the grandparent who lives away from the grandchild is a user, the user can feel as if he / she is talking with his / her grandchild, and the attachment to the robot can be expected to be further enhanced.

  Also, by registering celebrity voice parameters, you can feel like you are talking to your favorite singer or actor.

  FIG. 14 is a flowchart showing a processing procedure of the robot controller 220 in the present embodiment.

  When the dialoger selection receiving unit 222 receives the selection of the dialoger from the user (S110), the parameter acquisition unit 224 reads the parameter of the voice of the dialoger from the parameter storage unit 226 (S112). After that, the voice output unit 228 performs a dialogue with the user using the voice generated based on the voice parameter acquired by the parameter acquisition unit 224 (S114).

  Furthermore, in the above example, the example in which the user imitates the sound of a proper person has been shown. However, the robot 20 may grasp the characteristics of the action of the proper person and perform the same operation as that of the proper person. it can. As a result, the user can feel as if he / she is in contact with a specific specific person.

<DJ Robot>
(Sixth embodiment)
In the present embodiment, the robot 20 is configured to be able to play music, and reads information related to the music like a DJ when playing the music.

FIG. 15 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 300 includes a selection receiving unit 302 that receives selection of music to be played back, a music storage unit 304 that stores music information, and a music title and album of the music from the music information stored in the music storage unit 304. And an identification information extraction unit 306 that extracts identification information such as a name and an artist name. The robot control unit 300 further includes an information acquisition unit 308 that accesses the network 120 such as the Internet based on the identification information read by the identification information extraction unit 306 and acquires information related to the music based on the identification information. Based on the amount of information acquired by the unit 308, the timing control unit 310 that controls the timing of reading out information about music and the timing of music playback, the music playback unit 314 that plays back music, and the audio output that outputs information about music Part 312.

  The music storage unit 304 stores music information, for example, in the MP3 format. The information acquisition unit 308 acquires the latest information on the music and artist based on the identification information extracted by the identification information extraction unit 306. For example, information such as “How much is this week in Oricon” or “This artist's debut song” is acquired.

  The timing control unit 310 considers the amount of information acquired by the information acquisition unit 308 and the length of the introduction portion of the music to be played, for example, at such a speed that the information can be read out during the introduction. The audio output unit 312 is controlled to read out information. Further, for example, the music output unit 312 may read the information acquired by the information acquisition unit 308 and then the music playback unit 314 may play back the music.

FIG. 16 is a timing chart showing music playback timing and timing for introducing information by voice.
For example, as shown in FIG. 16A, the timing control unit 310 can shorten the introduction sentence so that the voice introduction ends at the introduction part of the music, or can control the output speed of the voice.

  Further, for example, as shown in FIG. 16B, music can be started after the voice introduction is completed.

  For example, as shown in FIG. 16C, voice introduction and music can be started at the same time, and when the introduction ends and the song starts, the voice introduction fades out.

  In addition, as shown in FIG. 16D, after music is played, the music can be introduced to the voice. In this way, information related to the music can be acquired and voice introduction editing can be performed while the music is being played. Also, for example, in the case of music by foreign artists, the latest information on music may be written in a foreign language, so that translation processing is performed while the music is being played, and it is introduced in the user's native language. You can also

  In this case, it is also possible to introduce music only when the robot 20 makes an inquiry to the user such as “I want to hear introduction” and the user answers “I want to hear”. Also, the robot 20 can make an inquiry “There is new news. Want to hear?” Only when there is new news since the same music was played last time. This prevents a user who listens to the same song many times from listening to the same introduction every time.

  Also in the example shown in FIG. 16A to FIG. 16C, for example, while playing the previous song, it is possible to perform processing such as obtaining a music introduction regarding the next song. Thereby, when music is reproduced, the voice introduction of the music can be started quickly.

FIG. 17 is a flowchart showing a processing procedure of the robot controller 300 in the present embodiment.
First, the selection receiving unit 302 receives selection of music to be played back from the user (S200). For example, when a plurality of pieces of music information are stored in the music storage unit 304 and the “listen to listening mode” or “random listening mode” is set, music selection from the second song is automatically performed. Is called.

  The identification information extraction unit 306 extracts the identification information from the music information of the music for which the selection reception unit 302 has received the selection (S202). The information acquisition unit 308 acquires information related to the music based on the identification information (S204). The timing control unit 310 calculates timing based on the amount of information acquired by the information acquisition unit 308 and, for example, the length of an introduction portion of music (S206). At the timing controlled by the timing control unit 310, music reproduction and voice introduction are output (S208).

  By giving the above functions to the robot 20, the user can listen to information about the music while listening to the music, and the DJ introduces his favorite song. You can listen to music in the mood.

<Mail reading robot>
(Seventh embodiment)
In the present embodiment, when the robot 20 receives the e-mail, the robot 20 replaces the e-mail with, for example, “lap style”, “old tune style”, “period drama style”, etc., and matches the replaced e-mail to each tone. Read aloud with the rhythm. Further, the robot 20 is configured to be able to reproduce music, reads out an electronic mail, and plays music in accordance with each tone.

FIG. 18 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 400 includes a mail receiving unit 402 that receives an e-mail from the network 120 such as the Internet, a replacement processing unit 404 that replaces the e-mail received by the mail receiving unit 402 with each tone sentence, and a replacement processing unit 404 It has the word memory | storage part 406 which memorize | stores the word referred when replacing an electronic mail. The robot control unit 400 further includes a voice output unit 408 that outputs the email replaced by the replacement processing unit 404 as a voice, and a music selection unit that selects music to be played as BGM when the voice output unit 408 reads the email. 410, a music storage unit 412 that stores various music, and a music playback unit 414 that plays back the music selected by the music selection unit 410.

  Although not shown in the figure, the robot control unit 400 automatically determines a selection receiving unit that accepts a selection of which tone the robot 20 should read an e-mail and which tone the e-mail is read. It can have a determination part to do.

  The word storage unit 406 stores words to be replaced with normal words for each tone. For example, in the case of “historical drama”, the normal word “is” is associated with “dezazuru”. When “period drama” is selected, when the mail receiving unit 402 receives an e-mail “I went to school”, the replacement processing unit 404 changes “I” to “Seki”, “ “School” is replaced with “Terakoya”, “I went” is replaced with “Tandogo Gozaru”, and the original sentence is replaced with “Seksha went to Terakoya”. The audio output unit 408 outputs “She's gone to Terakoya”. At this time, the music selection unit 410 selects music that is often used in historical plays, the music playback unit 414 reads the music from the music storage unit 412, and the voice output unit 408 outputs the email as voice. To play that music.

  For example, when “wrapping” is selected, the replacement processing unit 404 divides each sentence into phrases and replaces the e-mail so that the word “YO!” Is added to the end of each phrase. When the “lap tone” is selected, when the mail receiving unit 402 receives an e-mail “What were you doing today?”, The replacement processing unit 404 reads this sentence as “Today”, “What? ”And“ I was doing ”, and replaced with“ Today is YO !, what was YO !, what was YO! ”. The audio output unit 408 outputs “today is YO !, what is YO !, what was YO!” At the lap tempo. At this time, the music selection unit 410 selects rap music, the music playback unit 414 reads the music from the music storage unit 412, and plays the music when the voice output unit 408 outputs the email as voice.

  Further, the robot control unit 400 can control the operation of the robot 20 in accordance with each tone, and can also cause the robot 20 to dance in accordance with music.

  By giving the above functions to the robot 20, the user can enjoy listening to the received e-mail.

<Multilingual robot>
(Eighth embodiment)
In the present embodiment, the robot 20 understands a plurality of languages and speaks a plurality of languages. Here, the language includes, for example, old languages and dialects in addition to a plurality of languages.

FIG. 19 is a block diagram showing a configuration of the robot control unit in the present embodiment.
The robot control unit 500 includes a voice input unit 502 for inputting a question from the user, a question language input by the voice input unit 502, a voice recognition unit 504 for recognizing the meaning, and a result of recognition by the voice recognition unit 504. Accordingly, a response unit 508 that reads a response to which the robot 20 responds is read from the response example database 510, and a sound output unit 512 that outputs the response read by the read unit 508 as a sound. The robot control unit 500 further includes a dictionary storage unit 506 that stores dictionaries of a plurality of languages. The voice recognition unit 504 refers to the dictionary storage unit 506 to recognize the meaning of the user's question.

Hereinafter, a case where the robot 20 speaks modern language and old language will be described as an example.
For example, when the user asks “this time” in an old language, the speech recognition unit 504 refers to the dictionary storage unit 506 to indicate that the user is speaking an old language and “the time in recent times” is a modern language. Knowing what time is it? As a response to this inquiry, the response example database 510 stores “currently XX time”. Although not shown, the robot control unit 500 has a timekeeping function, and the reading unit 508 puts the current time in the “OO” portion and responds, for example, “Now is 2 AM”. In addition, the robot 20 can also respond in old language to questions from the user in the old language. In this case, the reading unit 508 refers to the dictionary storage unit 506 and reads “now at 2 am”. You can also respond with the corresponding old word “The Three Times Now”. In this case, when the user asks “What does it mean?”, The voice recognition unit 504 recognizes that the user is speaking in a modern language, and reads the modern language of “Now at 2 am” to the reading unit 508. Response examples can be read out.

  Further, response examples in a plurality of languages may be stored in the response example database 510, and the reading unit 508 may read the response examples in the corresponding language from the response example database 510.

  By the same processing as described above, for example, when the user speaks in Japanese, the robot 20 can reply in English, or the user and the robot 20 can communicate in English. Thereby, language learning can also be performed.

  As mentioned above, although embodiment of this invention was described with reference to drawings, these are the illustrations of this invention, Various structures other than the above are also employable.

  In the third embodiment, the robot 20 has a function of extracting proper nouns from news and replacing them with other words. For example, in the seventh embodiment, It is also possible to give a function of extracting proper nouns from inside and replacing them with other words.

  In the eighth embodiment, the robot 20 has a function of understanding and speaking a plurality of languages. However, in another embodiment, the robot 20 can understand and speak a plurality of languages. Can be granted. For example, in the first embodiment and the second embodiment, if the robot has a function of understanding a plurality of languages, news in a foreign language can be translated and transmitted to the user.

It is a block diagram which shows the structure of the robot used by this Embodiment. It is a figure which shows the external appearance (front view) of the robot in this Embodiment. It is a figure which shows the electrical structure of the robot shown in FIG. FIG. 4 is a functional block diagram showing details of the controller shown in FIG. 3. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a figure which shows a news memory | storage part in detail. It is a flowchart which shows the process sequence of the robot control part in embodiment of this invention. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a figure which shows a classified news storage part in detail. It is a flowchart which shows the process sequence of the robot control part in embodiment of this invention. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a flowchart which shows the process sequence of the robot control part shown in FIG. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a flowchart which shows the process sequence of the robot control part in embodiment of this invention. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a timing chart which shows the reproduction timing of music, and the timing which introduces information by voice. It is a flowchart which shows the process sequence of the robot control part in embodiment of this invention. It is a block diagram which shows the structure of the robot control part in embodiment of this invention. It is a block diagram which shows the structure of the robot control part in embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Body part 2 Head 3 Wheel 12 Speaker 13 Microphone 14 Actuator 20 Robot 21 CCD camera 22 Actuator 32 Voice input means 34 Image input means 36 Voice recognition means 38 Image recognition means 40 Action determination means 42 Storage means 44 Voice output means 46 Operation Means 51 Sensor input processing unit 51A Image recognition unit 51B Speech recognition unit 52 Action determination unit 53 Control unit 54 Speech synthesis unit 55 Output unit 56 Storage unit 100 Robot control unit 102 News acquisition unit 104 Classification processing unit 106 Reading unit 108 News storage unit 108a Acquired news storage unit 108b Classified news storage unit 108c Cache unit 110 Speech recognition unit 112 Read instruction unit 114 Analysis processing unit 115 Keyword storage unit 116 Operation control unit 117 Action pattern storage unit 120 Network 200 Robot control unit 202 Audio acquisition unit 204 Audio analysis unit 206 Parameter storage unit 208 Audio output unit 220 Robot control unit 222 Dialogue person selection reception unit 224 Parameter acquisition unit 226 Parameter storage unit 228 Audio output unit 300 Robot control unit 302 Selection reception Unit 304 music storage unit 306 identification information extraction unit 308 information acquisition unit 310 timing control unit 312 voice output unit 314 music playback unit 400 robot control unit 402 mail reception unit 404 replacement processing unit 406 word storage unit 408 voice output unit 410 music selection unit 412 Music storage unit 414 Music playback unit 500 Robot control unit 502 Voice input unit 504 Voice recognition unit 506 Dictionary storage unit 508 Reading unit 510 Response example database 512 Voice output unit

Claims (23)

Information acquisition means for acquiring information;
Voice output means for outputting the information by voice;
In response to a request for re-outputting the information from the user, reproduction means for causing the sound output means to re-output the information output by the sound output means;
An interactive robot characterized by including: The interactive robot according to claim 1,
And further comprising storage means for storing the information output by the audio output means,
The interactive robot according to claim 1, wherein the reproduction unit causes the audio output unit to read out the corresponding information from the storage unit in response to a re-output request of the information from the user. The interactive robot according to claim 1 or 2,
The interactive robot characterized in that the voice output means outputs the information in a voice that conveys the atmosphere of the content to the user according to the content of the information. The interactive robot according to claim 3, wherein
A voice storage means for storing the contents of the information and voice information conveying the atmosphere of the contents in association with each other;
The interactive robot characterized in that the voice output means outputs the information based on voice information associated with the content of the information to be output with reference to the voice storage means. The interactive robot according to any one of claims 1 to 4,
An interactive robot characterized by further including an effect execution means for performing an effect to convey the atmosphere of the content to the user according to the content of the information. The interactive robot according to claim 5, wherein
Production content storage means for storing the content of the information and production content that conveys the atmosphere of the content in association with each other;
The interactive robot characterized in that the effect execution means refers to the effect content storage means and performs the effect with the effect contents associated with the content of the information output by the audio output means. The interactive robot according to any one of claims 1 to 6,
An interactive robot characterized by further comprising an analysis means for analyzing the content of the information acquired by the information acquisition means. The interactive robot according to any one of claims 1 to 7,
A replacement unit that replaces the predetermined word included in the information with another word;
The interactive robot characterized in that the voice output means outputs a voice using the other word replaced by the replacement means. Means for obtaining the user's voice;
Voice output means for imitating the user's voice and outputting the same words;
An interactive robot characterized by including: A voice output means for asking a user;
Storage means for storing the voice of the user in response to the inquiry in association with the user;
Analyzing the user's voice stored in the storage means and acquiring parameters indicating the characteristics of the user's voice;
An interactive robot characterized by including: The interactive robot according to claim 10, wherein
The interactive robot characterized in that the voice output means imitates the user's voice and outputs the same words using the voice generated based on the user's parameters. The interactive robot according to claim 10 or 11,
The interactive robot characterized in that the features include the pitch, speed, and accent of the user's voice. Parameter acquisition means for acquiring parameters indicating the characteristics of a specific person's voice;
Audio output means for outputting audio generated based on the parameters;
An interactive robot characterized by including: The interactive robot according to claim 13, wherein
Storage means for storing parameters indicating characteristics of a specific person's voice in association with the specific person;
An accepting means for accepting designation of a person who wants to interact with the user;
Further including
The interactive robot characterized in that the parameter acquisition means acquires the parameters of the person received by the reception means from the storage means. The interactive robot according to claim 13 or 14,
The interactive robot characterized in that the features include pitch, speed, and accent of the voice of the specific person. Music playback means for playing music,
Information acquisition means for acquiring information about the music;
An audio output means for outputting information related to the music by voice when the music is played by the music playback means;
A music playback robot characterized by including: The music playback robot according to claim 16, wherein
The said information acquisition means acquires the information regarding the said music from the other terminal connected via the network based on the identification information of the said music contained in the said music, The music reproduction robot characterized by the above-mentioned. The music playback robot according to claim 16 or 17,
A music reproducing robot, further comprising timing control means for controlling a timing at which the music reproducing means outputs the music and a timing at which the audio output means outputs information related to the music by voice. The music playback robot according to claim 18, wherein
The music reproduction robot according to claim 1, wherein the timing control means controls the sound output means so that information relating to the music is output only while the introduction is being reproduced in the music. The music playback robot according to any one of claims 16 to 19,
The information acquisition means acquires information relating to the music or information relating to music to be reproduced next while the music reproduction means is reproducing music. Character information acquisition means for acquiring character information represented by characters;
Replacement means for replacing the character information with a sentence of a predetermined tone while maintaining the meaning of the information;
Voice output means for outputting the sentence replaced by the replacement means by voice;
A voice output robot comprising: The voice output robot according to claim 21, wherein
Music reproduction means for reproducing music that matches the tone,
The music output robot according to claim 1, wherein the music playback means plays music when the voice output means outputs the text. An interactive robot having language conversion means,
An analysis means capable of analyzing at least two kinds of languages;
A voice output unit that responds to a user's inquiry in a preset first language and responds in a second language in response to a language conversion request from the user;
An interactive robot characterized by including:

Images