JP2009178783A - Communication robot and control method thereof - Google Patents

Abstract

A communication robot capable of appropriately speaking depending on a target person is provided.
A communication robot that communicates with a subject through conversation, and controls the volume and / or frequency of an utterance signal according to the age and reaction of the subject. The communication robot includes an age determination unit that determines the age of the subject, an age input unit that inputs the age of the subject determined by the age determination unit, a reaction determination unit that determines the response of the subject, and a reaction determination A response input unit that inputs the response of the subject determined by the unit, the age of the subject input to the age input unit, and the volume of the speech signal according to the response of the subject input to the response input unit, and And / or an utterance control unit that controls the frequency.
[Selection] Figure 2

Description

  The present invention relates to a communication robot that communicates with a target person through conversation and a control method thereof.

  In recent years, a communication robot that communicates with a target person through conversation has been developed and attracted attention as a robot that coexists with humans.

  Patent Document 1 discloses that external information including information related to the age group of the subject is acquired, and the utterance of the robot is controlled based on the acquired external information.

Patent Document 2 discloses a notification sound conversion device that detects a notification sound emitted by an electrical device located at a location away from a subject and utters information corresponding to the notification sound detected for the subject. . Patent Document 2 discloses that when the target person who notifies the notification sound is an elderly person, the utterance is made in a frequency band and volume that are easy for the elderly person to hear.
JP-A-2005-313308 JP 2004-020817 A

  However, with the robot control method described in Patent Document 1, it is not possible to perform utterance control according to the hearing ability of an unspecified subject who has different hearing abilities depending on age and individual differences. Moreover, in the notification conversion device described in Patent Document 2, utterance control for the elderly is uniformly performed on the elderly. Therefore, even if the subject is an elderly person and the hearing ability has not deteriorated, the robot speaks at a high volume, which may give an unpleasant feeling to the subject. An object of this invention is to provide the communication robot which can perform an appropriate speech by performing speech control according to a subject in such a communication robot.

  The communication robot according to the first aspect of the present invention is a communication robot that communicates with a target person through conversation, and controls the volume and / or frequency of an utterance signal according to the age and reaction of the target person. By controlling the speech signal according to the age and reaction of the target person, even when talking to an unspecified target person having different hearing abilities depending on the age and individual differences, the volume and range corresponding to each target person You can speak.

  A communication robot according to a second aspect of the present invention includes an age determination unit that determines the age of the subject, a reaction determination unit that determines a response of the subject, and the subject determined by the age determination unit. An utterance control unit that controls the volume and / or frequency of the utterance signal according to the age and the response of the subject determined by the response determination unit. While determining the age of the subject by the age determination unit and determining the response of the subject by the reaction determination unit, even when talking with an unspecified subject having different hearing abilities depending on age and individual differences, It is possible to speak at a volume and range corresponding to each target person.

  In the communication robot according to the third aspect of the present invention, the age determination unit and the reaction determination unit may be configured so that the target person's voice information and / or image information is acquired based on the target person's voice information and / or image information. Determine age and response. By analyzing audio information and / or image information acquired by either one of the microphone and the camera, the age and reaction of the subject can be detected.

  In the communication robot according to the fourth aspect of the present invention, the age determination unit determines that the target person is an elderly person and / or the reaction determination unit determines that the target person has not heard the utterance signal. In this case, the utterance control unit raises the volume of the utterance signal from the normal volume. By raising the volume of the utterance signal, it is possible to utter at a volume that is easy for a subject who cannot hear the utterance signal or an elderly subject to hear.

  In the communication robot according to the fifth aspect of the present invention, the age determination unit determines that the target person is an elderly person and / or the reaction determination unit determines that the target person cannot hear the speech signal. In this case, the speech control unit lowers the frequency of the speech signal from the frequency of the normal speech signal. By lowering the frequency of the utterance signal, it is possible to utter with low-frequency sound that can be easily heard by subjects who cannot hear the utterance signal or elderly subjects.

  In the communication robot according to the sixth aspect of the present invention, the age determination unit determines that the target person is an elderly person and / or the reaction determination unit determines that the target person has not heard the speech signal. In this case, the volume of the high-tone phoneme is increased in the speech signal. By increasing the volume of the phoneme in the high sound range of the speech signal that is difficult to hear, it is possible to utter at a volume that is easy for a subject who cannot hear the speech signal or an elderly subject to hear.

  A communication robot control method according to a seventh aspect of the present invention is a communication robot control method for communicating with a target person through conversation, and according to the age and reaction of the target person, the volume of the speech signal and / or Control the frequency. By controlling the speech signal according to the age and reaction of the target person, even when talking to an unspecified target person having different hearing abilities depending on the age and individual differences, the volume and range corresponding to each target person You can speak.

  According to the communication robot and the control method thereof according to the present invention, speech control can be performed according to the target person.

  Hereinafter, a communication robot and a control method thereof according to embodiments of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a diagram showing an overall configuration of a communication robot 10 according to an embodiment of the present invention. The communication robot 10 has a function of talking with the target person 30. The communication robot 10 includes a speaker 11, a control unit 12, a camera 13, and a microphone 14. The speaker 11 is configured to output an utterance signal whose volume and range are controlled by the control unit 12 to the subject 30. The speaker 11 is installed, for example, around the mouth of the communication robot 10. The control unit 12 adjusts the volume and range of the utterance of the communication robot 10 by controlling the volume and frequency of the utterance signal output from the speaker 11.

  The camera 13 acquires an external environment of the communication robot as image information by capturing an image around the communication robot 10. The control unit 12 can recognize the facial expression and emotion of the subject 30 based on the facial expression and gesture of the subject 30 captured by the camera 13. The camera 13 can be constituted by, for example, a CCD (Charge Coupled Device) camera. The microphone 14 acquires the external environment of the communication robot 10 as voice information. The control unit 12 can recognize the voice uttered by the target person 30 and the content of the conversation by analyzing the voice information acquired by the microphone 14. The microphone 14 is installed, for example, on the ears on both sides of the communication robot 10.

  FIG. 2 is a block diagram showing a configuration of the control unit 12 of the communication robot 10 according to the embodiment of the present invention. The control unit 12 includes an age determination unit 15, an age input unit 16, a reaction determination unit 17, a reaction input unit 18, and an utterance control unit 19.

  Image information captured by the camera 13 is input to the age determination unit 15. The age determination unit 15 determines the age of the target person 30 by analyzing the image information input from the camera 13. For example, the age can be estimated by extracting feature points from the input image information. In addition, voice information acquired by the microphone 14 is input to the age determination unit 15. The age determination unit 15 determines the age of the target person by analyzing the voice information acquired by the microphone 14. For example, it is possible to determine the age of the target person by extracting feature points of the acquired audio signal and analyzing the extracted feature points.

  In addition, in this embodiment, although comprised so that the age of the subject 30 may be determined based on the information of both image information and audio | voice information, this invention is not limited to this. For example, the age of the target person 30 can be determined based on only one of image information and audio information. The age determined by the age determination unit 15 may be a specific age such as 10 years old, 41 years old, 75 years old, or the like, or may be an age group such as teens, 40s, or 70s.

  The age of the subject 30 determined by the age determination unit 15 in this way is input to the age input unit 16. The age of the subject 30 input to the age input unit 16 is output to the utterance control unit 19.

  Image information captured by the camera 13 is input to the reaction determination unit 17. The reaction determination unit 17 determines the reaction of the target person 30 by analyzing the image information input from the camera 13. In addition, voice information acquired by the microphone 14 is input to the reaction determination unit 17. The reaction determination unit 17 determines the reaction of the target person 30 by analyzing the voice information acquired by the microphone 14.

  Here, the reaction of the subject 30 is the facial expression or words of the subject 30 immediately after the communication robot 10 speaks. Specifically, the reaction of the target person 30 is that the target person 30 responds to the communication robot 10 when he / she cannot hear the utterance signal uttered by the communication robot 10. It is a word that was uttered. Further, the reaction of the other subject 30 was sent to the communication robot 10 from the subject 30 such as an uncomfortable expression of the subject 30 when the volume of the speech signal is too high or “too noisy”. Words. The reaction determination unit 17 detects the facial expression and words of the subject person 30 to determine whether the subject person 30 can hear the immediately preceding utterance signal, and the subject person 30 increases the volume of the immediately preceding utterance signal. Determine if you feel too much.

  In addition, in this embodiment, although comprised so that the reaction of the subject 30 may be determined based on the information of both image information and audio | voice information, this invention is not limited to this. For example, the reaction of the target person 30 may be determined by determining only one of image information and audio information.

  The age of the subject 30 is input to the speech control unit 19 via the age input unit 16. Similarly, the reaction of the subject 30 is input to the utterance control unit 19 via the reaction input unit 18. Specifically, information such as whether or not the subject 30 has heard the previous utterance signal from the reaction input unit 18 and whether or not the subject 30 feels that the volume of the previous utterance signal is too high. Entered. The utterance control unit 19 controls the volume and range of the utterance signal based on the age of the subject 30 input from the age input unit 16 and the response of the subject 30 input from the reaction input unit 18. The utterance control unit 19 extracts the output information selected from the content 20.

  The utterance control unit 19 adjusts the volume and frequency of the utterance signal corresponding to the selected content 20 according to the age and reaction of the input target person 30. The utterance control unit 19 is connected to an utterance adjustment device such as a mixer 21, an amplifier (not shown), and an equalizer (not shown). The mixer 21 converts the frequency of the speech signal. The amplifier adjusts the volume of the speech signal. The equalizer adjusts the volume of phonemes in a specific range of the speech signal. The utterance control unit 19 controls the mixer 21, the amplifier, and the equalizer to generate an utterance signal corresponding to the age and reaction of the target person 30 and output it from the speaker 11.

  In the above description, the speech signal is adjusted using the mixer 21, the amplifier, and the equalizer. However, the volume and frequency of the speech signal can be adjusted by using, for example, a speech synthesizer. . The speech synthesizer includes a front end and a back end. At the front end, the content uttered by the communication robot 10 is converted into phonetic symbols. In the back end, when the communication robot 10 utters based on the utterance symbol generated by the front end, adjustment is performed so that the utterance is naturally spoken to the prosody, the emphasized word, the phoneme, and the target person. By using the determined age of the subject as a back-end adjustment parameter of the speech synthesizer, speech control according to the age of the subject can be easily performed.

  Next, a flowchart of the communication robot 10 configured as described above will be described. FIG. 3 is a flowchart of the communication robot 10 according to the embodiment of the present invention. First, when the subject 30 and the communication robot 10 have a conversation, the age of the subject 30 determined by the age determination unit 15 is input to the utterance control unit 19 (S1). The utterance control unit 19 determines whether the target person 30 is an elderly person based on the age input from the age input unit 16 (S2). Specifically, if the input age is equal to or greater than a threshold age, it is determined that the person is an elderly person. If the input age is lower than the threshold age, it is determined that the person is not an elderly person.

  If it is determined in step S2 that the target person 30 is not an elderly person (N), the utterance control unit 19 controls the mixer 21, the amplifier, and the equalizer to set the normal volume and sound range. Then, the user speaks by outputting a speech signal corresponding to the content 20 selected in the set volume and range (S3). Thereby, the communication robot 10 speaks with the normal sound volume and a sound range with respect to the target person 30 who is not elderly. Note that, as described above, the speech control may be configured such that the volume and frequency of the speech signal are adjusted by the speech synthesizer.

  Next, as illustrated in FIG. 4, a case where the target person 40 is an elderly person will be described. If the target person 40 is an elderly person, it is determined in step S2 that the subject person 40 is an elderly person in the flowchart of FIG. When the target person 40 is an elderly person (Y), the utterance control unit 19 executes utterance control for the elderly person (S100) surrounded by a dotted line. Specifically, the volume of the speech signal is increased by controlling the amplifier (S12). Then, the mixer 21 is controlled to lower the frequency of the speech signal (S13). Further, the equalizer is controlled to increase the volume of the phoneme in the high range of the speech signal (S14).

  In this way, by controlling the mixer 21, the amplifier, and the equalizer, the volume, the frequency, and the volume of the phoneme in the high range are set for the elderly. When the setting is completed in steps S12 to S14, the process proceeds to step S3, where the utterance is made with the set volume and range. As a result, the communication robot 10 utters a voice that is easy for the elderly subject 40 to hear. Note that the utterance control for the elderly (S100) does not have to include all steps S12 to S14. If at least one utterance control is executed in steps S12 to S14, it is possible to output a voice that is easier for an elderly person to hear than a normal utterance signal.

  Then, the facial expression and words of the subject 30 immediately after outputting the speech signal are acquired by the camera 13 and the microphone 14. The reaction determination unit 17 analyzes the image information and sound information acquired by the camera 13 and the microphone 14 and determines whether the volume and range of the utterance signal are appropriate for the target person 30 (S4). For example, it is determined whether or not the volume and range of the speech signal are appropriate for the target person 30 by recognizing the confused facial expressions of the target persons 30 and 40 when the volume is too low and the voice such as “I cannot hear”. . On the other hand, when the volume is too high, by recognizing an unpleasant expression of the subjects 30 and 40 and a voice such as “too loud”, whether the volume and range of the utterance signal are appropriate for the subject 30 or not. Judge.

  In step S4, when it is determined that the output audio signal is appropriate for the target person 30 (Y), it is determined whether there is content 20 to be output next, thereby determining the target persons 30, 40 and It is determined whether or not to end the conversation (S5). If there is no content 20 to be output next and a conversation is made (Y), the control of voice and the like is terminated. On the other hand, if there is content to be output next and the conversation continues (N), the process returns to step S3 to output an utterance signal corresponding to the content 20 to be output next in the previously set volume and range. Thereafter, steps S3 to S5 are repeated until the conversation is finished.

  On the other hand, if it is determined in step S4 that the output audio signal does not have an appropriate volume and range (N), it is then determined whether the volume is too high for the target persons 30 and 40 (S6). If the volume is too high (Y), the control (S200) opposite to steps S12-14 is performed. Specifically, the volume of the speech signal is decreased by controlling the amplifier (S7). Then, the mixer 21 is controlled to lower the frequency of the speech signal (S8). Further, the equalizer is controlled to lower the volume of the high-tone phoneme in the speech signal (S9). Note that the control when it is determined that the volume is high for the target persons 30 and 40 is not limited to this. For example, it can also be configured to execute any one utterance control among steps S12 to S14. When the setting is completed, the process returns to step S3, and an utterance signal corresponding to the content 20 is output with the set volume and sound range.

  If it is determined in step S6 that the volume of the utterance signal does not feel too high based on the reaction of the subjects 30 and 40 (N), the same content that was spoken immediately before at the same volume and range is again displayed. An utterance signal is output (S10). This is because even if the volume or range of the speech signal is suitable for the target person 30 or 40, the target person 30 or 40 may miss it. In such a case, the volume or range is changed. This is because the subjects 30 and 40 feel uncomfortable. Then, the camera 13 and the microphone 14 detect the reaction of the subjects 30 and 40 immediately after outputting the speech signal again with the same volume and range. Based on the image information and audio information acquired by the camera 13 and the microphone 14, it is determined whether or not the target persons 30 and 40 can hear the speech signal (S11). In step S11, when the target persons 30 and 40 can hear the speech signal (Y), the process proceeds to step S5, and steps S3 to S5 are repeated until the conversation ends.

  On the other hand, if it is determined in step S11 that the target persons 30 and 40 cannot hear the speech signal (N), the process proceeds to step S12, and the same control as the voice control for the elderly is executed. That is, in step S12, the volume is set higher than the volume of the speech signal set last time. In step S13, the frequency is made lower than the frequency of the speech signal set last time. In step S14, the volume of the phoneme in the high range set last time is further increased. In step S3, the utterance is performed with the reset volume and range.

  As described above, according to the communication robot 10 according to the present embodiment, the sound volume and frequency appropriate for an elderly person whose hearing has declined by performing utterance control according to the age of the target persons 30 and 40 having conversation. Can output an utterance signal. Further, by determining the reaction of the target persons 30 and 40 immediately after the output of the utterance signal by the reaction determination unit 17, the utterance control can be performed according to the reaction of the target persons 30 and 40. For example, even elderly people of the same age have individual differences in hearing loss, and some elderly people feel uncomfortable with a large volume. Even if the subject is not an elderly person, there is a possibility that the speech signal cannot be heard at a normal volume if the ambient noise is large. In this embodiment, even in such a case, by detecting not only the age of the subject but also the reactions of the subjects 30 and 40, an utterance signal is output at a volume and frequency according to the situation and individual differences. be able to. As described above, according to the communication robot 10 according to the present embodiment, it is possible to have a conversation at a volume and a sound range appropriate for the target person by controlling the utterance signal while listening to the age of the target person and the reaction of the target person. it can.

  FIG. 5 is a block diagram showing a modification of part of the communication robot 10 according to the embodiment of the present invention. In the communication robot described above, the age of the target person is determined by analyzing the image captured by the camera 13 and the voice information collected by the microphone 14, but in this modification, the identification information of the target person is used. The subject is provided with a stored RFID (Radio Frequency IDentification) tag, and the identification information stored in the RFID tag is read by an RFID reader installed in the communication robot 10 to acquire the age of the subject. .

  As shown in FIG. 5, the target person holds the RFID tag 50 in which the identification information is stored in advance. The communication robot 10 is provided with an RFID reader 51 for reading identification information from the RFID tag 50. The RFID reader 51 acquires the identification information of the target person by analyzing the wireless data received from the RFID tag 50. The communication robot 10 acquires the age of the target person from the identification information of the target person acquired by the RFID reader 51.

  For example, the communication robot 10 is provided with a table (not shown) in which the identification information of the subject and the age information of the subject are associated, and the age information of the subject is acquired by referring to this table. Can be configured. The table in which the identification information of the target person and the age information of the target person are associated may be provided outside the communication robot 10. In this case, when the communication robot 10 acquires the identification information of the target person, the communication robot 10 accesses an external database in which the identification information of the target person and the age information of the target person are associated, and acquires the age of the target person. do it. The age input unit 16 executes the utterance control as described above based on the age information acquired based on the identification information. As described above, the age information of the target person can be acquired using the RFID tag, and the speech control according to the age of the target person can be performed.

  The present invention is not limited to the configuration of the present embodiment, and various design changes can be made by those skilled in the art.

1 is a diagram showing an overall structure of a communication robot 10 according to an embodiment of the present invention. It is a block diagram which shows the structure of the control part 12 of the communication robot 10 which concerns on embodiment of this invention. It is a flowchart of the communication robot 10 which concerns on embodiment of this invention. It is a figure which shows the other control state of the communication robot 10 which concerns on embodiment of this invention. It is a block diagram which shows the modification of the communication robot 10 which concerns on embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Communication robot 11 Speaker 12 Control part 13 Camera 14 Microphone 15 Age determination part 16 Age input part 17 Reaction determination part 18 Reaction input part 19 Speech control part 20 Content 21 Mixer 30 Target person 40 Target person 50 RFID tag 51 RFID reader

Claims (10)

A communication robot that communicates with a target person through conversation,
A communication robot that controls the volume and / or frequency of an utterance signal according to the age and response of the subject. An age determination unit for determining the age of the subject;
A reaction determination unit for determining the reaction of the subject;
An utterance control unit that controls the volume and / or frequency of the utterance signal according to the age of the subject determined by the age determination unit and the response of the subject determined by the response determination unit. Item 1. The communication robot according to item 1. The said age determination part and the said reaction determination part determine the age and reaction of the said subject based on the audio | voice information and / or image information of the said subject acquired with the microphone and / or the camera. Communication robot. When the age determination unit determines that the subject is an elderly person and / or when the response determination unit determines that the subject has not heard the speech signal,
The communication robot according to any one of claims 1 to 3, wherein the utterance control unit raises a volume of the utterance signal from a normal volume. When the age determination unit determines that the subject is an elderly person and / or when the response determination unit determines that the subject has not heard the speech signal,
The communication robot according to any one of claims 1 to 4, wherein the utterance control unit lowers the frequency of the utterance signal from a frequency of a normal utterance signal. When the age determination unit determines that the subject is an elderly person and / or when the response determination unit determines that the subject has not heard the speech signal,
The communication robot according to any one of claims 1 to 5, wherein a volume of a high-tone phoneme is increased in the utterance signal. A communication robot control method for communicating with a target person through conversation,
A communication robot control method for controlling the volume and / or frequency of an utterance signal according to the age and response of the subject. The communication robot control method according to claim 7, wherein when the target person is an elderly person and / or when the target person does not hear the speech signal, the volume of the speech signal is increased from a normal volume. The communication robot control according to claim 7 or 8, wherein when the subject is an elderly person and / or when the subject cannot hear the speech signal, the frequency of the speech signal is lowered from a normal frequency. Method. 10. The device according to claim 7, wherein when the subject is an elderly person and / or when the subject cannot hear the utterance signal, the volume of a high-frequency phoneme in the utterance signal is increased. The communication robot control method according to the item.

Images