JP2015102851A - Voice output device, control method for voice output device, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a voice output device, the control method of the voice output device and a program capable of developing relaxation effects or stress reduction effects optimal to a person who listens to a musical piece under the consideration of a personal difference.SOLUTION: A reproduction device 1 includes: a voice output part 12 for outputting a test sound as the reference of voice control; a monitoring part 11 for monitoring the change of the crying voice of an infant; and a voice control part 14 for performing voice control in accordance with the change of the crying voice after the output of the test sound. The voice control content includes: varying the BPM of the test sound; varying the frequency characteristics of a filter circuit; varying a sound volume; and adding a pseudo sound or the like.

Description

  The present invention relates to an audio output device for controlling a mental state of a person, a control method for the audio output device, and a program.

  For example, Patent Document 1 is known as this type of technology. Patent Document 1 describes that an infant's appearance is detected by voice, and music is selected and reproduced according to the detected voice. As described above, by reproducing the music suitable for the infant's situation, it is possible to watch the infant on behalf of the mother.

  On the other hand, as a method for stopping infants from crying, proof results have been known that it is effective to hear the mother's heart sound (internal womb sound). In recent years, an “in womb sound CD” for supporting infants falling asleep has also been released.

JP 2003-337591 A

  However, since the invention of Patent Document 1 detects the state of an infant by voice and selects music according to the detected voice, the music that the mother likes cannot be reproduced. Moreover, although it is thought that a favorite music and the music with a high effect which stops crying differ also with infants, in patent document 1, the point is not considered.

  Also, from the above demonstration results, it is considered that selecting and playing music that has a similar tempo (BPM) to the mother's heart sound will have the effect of making infants stop crying. There should be individual differences. That is, it is considered that there are subtle differences in the tempo (BPM), volume, and frequency of heart sounds depending on the person. However, the existing “in utero sound CD” cannot cover such individual differences.

  In view of the above problems, the present invention provides an audio output device, a control method for an audio output device, and a program capable of exhibiting an optimal relaxation effect or stress down effect for a person who listens to music while considering individual differences. Is an issue.

  An audio output device of the present invention includes an audio output unit that outputs a test sound that is a reference for audio control, a monitoring unit that monitors a change in sound for predetermined biological information, an output state of the test sound, and a monitoring unit And a voice control unit that performs voice control of the voice output unit according to the monitoring result.

  In the audio output device, the predetermined biological information is a cry, and the audio control unit performs audio control of the audio output unit according to a change in the cry after the test sound is output.

  In the audio output device, the audio control unit varies the BPM (beats per minute) of the test sound or a sound source other than the test sound as the audio control of the audio output unit.

  In the audio output device, the audio control unit varies the frequency characteristic and volume of a filter circuit that performs audio processing of a test sound or a sound source other than the test sound as audio control of the audio output unit. .

  In the audio output device, the audio control unit adds a pseudo sound to the test sound or a sound source other than the test sound as audio control of the audio output unit.

  In the audio output device described above, when there is a predetermined change in the cry monitored by the monitoring unit after starting the audio control by the audio control unit, the audio output device further includes a storage unit that stores the audio control content at that time, The voice control unit performs voice control of the voice output unit in accordance with past voice control contents stored in the storage unit.

  In the voice output device, the storage unit further stores the feature amount of the cry and the voice control content for each individual, the feature amount of the individual cry stored in the storage unit, and the monitoring result of the monitoring unit And a voice control unit that performs voice control of the voice output unit according to past voice control contents of the individual specified by the personal specification unit. And

  In the above sound output device, a heart sound measuring unit that measures the frequency and BPM of another person's heart sound related to an individual who is a control target of the sound control unit, and a storage unit that stores a measurement result of the heart sound measuring unit The voice control unit performs voice control of the voice output unit according to the measurement result of the heart sound measurement unit stored in the storage unit.

  In the voice output device, the storage unit further stores the feature amount of the cry and the measurement result of the heart sound measurement unit for each individual, and the feature amount of the individual cry stored in the storage unit and the monitoring unit A personal identification unit that identifies the individual by comparing the monitoring results of the voice, and the voice control unit is configured to generate a voice output unit according to a measurement result of another person's heart sound measurement unit associated with the individual identified by the personal identification unit. The voice control is performed.

  In the audio output device described above, after starting the audio control by the audio control unit, after changing the audio control content a predetermined number of times, or when a predetermined change in the cry monitored by the monitoring unit even after a predetermined time has elapsed, The information processing device further includes a notification unit that notifies the fact.

  The control method of the sound output device of the present invention includes a sound output step for outputting a test sound serving as a reference for sound control, a monitoring step for monitoring a change in sound for predetermined biological information, an output state of the test sound, A voice control step for performing voice control is executed according to the monitoring result of the monitoring step.

  A program according to the present invention causes a computer to execute each step in the above-described method for controlling an audio output device.

1 is a system configuration diagram of a playback system according to a first embodiment. It is a figure which shows the example of a screen display of a portable terminal. It is a flowchart which shows the reproduction | regeneration processing which concerns on 1st Embodiment. It is a block diagram of the reproducing | regenerating apparatus concerning 2nd Embodiment. It is a flowchart which shows the reproduction | regeneration processing which concerns on 2nd Embodiment. It is a block diagram of the reproducing | regenerating apparatus concerning 3rd Embodiment. It is a system block diagram of the reproduction | regeneration system which concerns on 4th Embodiment.

[First Embodiment]
Hereinafter, an audio output device, a control method for an audio output device, and a program according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In this embodiment, the case where the audio output device of the present invention is applied to a reproduction system SY for controlling the mental state of an infant (individual) will be exemplified.

  FIG. 1 is a system configuration diagram of a reproduction system SY according to the first embodiment. The playback system SY includes a playback device 1 and a mobile terminal 2. The playback device 1 is a playback unit formed integrally with a speaker SP and a battery (not shown), and is configured to be housed inside a stuffed toy or covered with a stuffed toy cover. In addition, the playback device 1 is covered with a rubber case inside the stuffed toy, and has a structure that is resistant to impacts and water and takes into account infant safety.

  In addition, the playback device 1 includes a monitoring unit 11, an audio output unit 12, a control program storage unit 13, an audio control unit 14, and a communication unit 15 as main functional configurations.

  The monitoring unit 11 is composed of a microphone and monitors changes in the infant's cry. The sound output unit 12 outputs a test sound serving as a reference for sound control or a control sound that is a sound obtained by controlling the test sound by the sound control unit 14 to the speaker SP. The control program storage unit 13 stores a control program for the voice control unit 14 to perform voice control.

  The voice control unit 14 performs voice control of the voice output unit 12 according to the output state of the test sound and the monitoring result of the monitoring unit 11. Specifically, the BPM (beats per minute) of the test sound and the frequency characteristics and volume of the filter circuit that performs sound processing are varied according to the change in the cry after the test sound is output. In the present embodiment, a bandpass filter is used as the filter circuit, and the center frequency thereof is varied. In addition, the bandwidth of the bandpass filter may be varied, or the cutoff frequency of a filter circuit (a highpass filter or a lowpass filter) other than the bandpass filter may be varied. As a method for changing the BPM, frequency characteristics, and volume, it is conceivable to gradually approach the predetermined value every time the audio control content is switched, increase or decrease by a predetermined number, and the like.

  The communication unit 15 performs wireless communication with the mobile terminal 2. In particular, in this embodiment, when an infant does not stop crying easily, it is used to notify the guardian (mother) to that effect. The “notification unit” in the claims includes the communication unit 15, a display unit 23, an audio output unit 24, and a communication unit 25 of the mobile terminal 2 described later. As the wireless communication, Bluetooth communication (registered trademark) or wireless LAN communication can be employed.

  On the other hand, the portable terminal 2 is owned by a guardian, and is realized by a tablet terminal such as a smartphone or an information processing terminal such as a cellular phone. Moreover, the portable terminal 2 is provided with the operation part 21, the music data storage part 22, the display part 23, the audio | voice output part 24, and the communication part 25 as main function structures. Each unit of the portable terminal 2 is a function of a support application (not shown) that supports the care of the infant. That is, by installing a support application on the information processing terminal (downloading from a predetermined server), the information processing terminal can function as the mobile terminal 2 of the present embodiment. However, for the music data storage unit 22, the function of an application (such as a music playback application) other than the support application may be used.

  The operation unit 21 is used by a guardian to perform various operations of the playback device 1. In the present embodiment, it is used for setting the audio control content by the audio control unit 14 and setting the music selection mode (“automatic” or “manual”) (details will be described later). The music data storage unit 22 stores one or more music data.

  The display unit 23 displays a setting screen D1, a message screen D2, and the like (see FIG. 2). The audio output unit 24 outputs the music (test sound or control sound controlled by the audio control unit 14) being played back by the playback device 1, or the output of the music played by the playback function of the mobile terminal 2. Do. The communication unit 25 communicates with the communication unit 15 of the playback device 1.

  Next, the setting screen D1 and the message screen D2 displayed on the display unit 23 of the mobile terminal 2 will be described with reference to FIG. FIG. 2A shows a display example of the setting screen D1. In addition to the name of the support application and the title of the setting screen D1, the setting screen D1 includes an audio control content setting area E1 and a music selection area E2. In the voice control content setting area E1, selection / non-selection can be set for the three items “BPM”, “frequency”, and “volume”. Here, the selected item is an item to be controlled by the voice control unit 14. In the case of the example in the figure, since the item “volume” is not selected, the volume control is not performed (in this case, the volume of the test sound and the control sound is the same).

  In the music selection area E2, either “automatic” or “manual” can be selected as the music selection mode. For example, when “automatic” is selected as the music selection mode, one of the music stored in the mobile terminal 2 (for example, the first music in the playlist or a music randomly selected from the playlist) is selected. Used as a test sound. When “manual” is selected, a music selection screen (not shown) is displayed, and the music selected by the guardian is used as a test sound.

  FIG. 2B is a diagram illustrating a display example of the message screen D2. The message screen D2 includes a message area E3 and a time display area E4 in addition to the name of the support application and the title of the message screen D2. In the message area E3, a text document indicating that the infant does not stop crying is displayed. Of course, an image or illustration may indicate that the infant does not stop crying. In the time display area E4, the time when the playback device 1 (monitoring unit 11) detects a cry and the time when the message screen D2 is displayed (the time when the playback device 1 is notified) are displayed.

  Next, the reproduction process according to the first embodiment will be described with reference to the flowchart of FIG. When the playback device 1 detects a cry by monitoring by the monitoring unit 11 (S01: Yes), the test sound selected by the mobile terminal 2 (music data acquired from the mobile terminal 2 itself, hereinafter referred to as “specified test sound”). ) Is output to the speaker SP (S02). The test sound output here is based on the music selection mode selected in the music selection area E2 (see FIG. 2A). When crying is detected after a predetermined time (several tens of seconds to several minutes) from the start of test sound output (S03: Yes), the audio output is performed for a predetermined time (several minutes to several tens of minutes) without changing the audio control content. Minutes)) (S04) and return to S01.

  If no crying is detected (S03: No), it is determined whether or not the number of retries in the reproduction process is N or more (where N is an integer satisfying N ≧ 2) (S05). When the number of retries is less than N (S05: No), the audio control content is changed and the retry is performed (the audio control content is switched and reproduction is performed for a predetermined time, S06), and the process returns to S03. Note that the retry in S06 means that the test sound is not replayed from the beginning, but only the audio control content is switched while the playback position continues. If the number of retries is N or more (S05: Yes), the mobile terminal 2 is notified that it will not cry (S07), and the process returns to S01. The portable terminal 2 notified that the crying is not stopped displays a message screen D2 (see FIG. 2B) on the display unit 23.

  As described above, according to the first embodiment, the test sound is once output to monitor the change of the infant's cry, and according to the monitoring result, the BPM, the frequency characteristic and the volume of the test sound are varied. Can effectively stop infants from crying. In other words, if the infant stops crying by outputting a test sound with any voice control content, it is determined that the voice control content is optimal, the voice control is continued, and if the infant does not stop crying, Variable voice control content. Thus, according to the first embodiment, since voice control is performed based on the actual reaction of the infant, the effect can be exerted on all infants regardless of individual differences. Further, since the test sound can be selected according to the preference of the guardian, the relaxation effect or the stress-down effect of the guardian can be expected.

  Further, as shown in FIG. 3, since the reproduction process is started when the cry is detected, there is no need to perform useless music reproduction. Furthermore, when the infant does not stop crying easily, the guardian is notified, so that the guardian can take an appropriate action according to the infant's condition.

  In the first embodiment, the example of changing the BPM of the test sound, the frequency characteristic of the filter circuit, and the volume is shown as the sound control content by the sound control unit 14, but in addition, a pseudo sound is added to the test sound. You may do it. The pseudo sound refers to a sound source created by imitating real sound or a sound source that records actual sound. In order to obtain the effect of stopping crying, it is preferable to add pseudo sounds such as white noise and mother's heart sounds.

  Also, instead of performing sound control on the test sound to generate control sound, sound control may be performed on a sound source other than the test sound. In this case, the sound source other than the test sound (the sound source that is the source of the control sound) is preferably the music selected by the mobile terminal 2. Further, the test sound in this case may be a music stored in advance in the playback device 1 or the portable terminal 2 or a simple loop sound source.

  In the first embodiment, a message is displayed as a method for notifying the guardian (see FIG. 2B), but instead of this, a sound (control sound) reproduced by the reproducing apparatus 1 is used. May be output by the audio output unit 24 of the mobile terminal 2.

  In the first embodiment, when the number of retries is N or more (S05: Yes in FIG. 3), the mobile terminal 2 is notified that it will not stop crying (S07). Instead of this, the determination may be made with the passage of time from the start of the voice control. That is, after the voice control by the voice control unit 14 is started, if there is no predetermined change in the cry after a predetermined time has elapsed, the mobile terminal 2 may be notified of this.

  In the first embodiment, when the infant does not stop crying, the mobile terminal 2 is notified (S07 in FIG. 3), and the detection of the crying is resumed by returning to S01, but the mobile terminal 2 is notified. After that, the reproduction process may be terminated. In S04, when crying is detected while the audio output for a predetermined time is continued, the output of the control sound may be retried by changing the audio control content without waiting for the end of the predetermined time (S06). .

[Second Embodiment]
Next, a second embodiment of the present invention will be described with reference to FIGS. The present embodiment is characterized by a so-called learning function that identifies an individual from the feature amount of an infant's cry and stores voice control contents effective for each individual and uses them for the next voice control. And Only differences from the first embodiment will be described below. In the present embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and detailed description thereof is omitted. Moreover, the modification applied about the component similar to 1st Embodiment is applied similarly about this embodiment.

  FIG. 4 is a configuration diagram of the playback device 1 according to the second embodiment. Note that the functional configuration of the mobile terminal 2 is the same as that of the first embodiment, and thus illustration and description thereof are omitted. The playback device 1 according to the second embodiment has a configuration in which an individual identification unit 16 is added as compared with the first embodiment. Moreover, the point from which a control table is memorize | stored in the control program memory | storage part 13 also differs from 1st Embodiment.

  In the control table, after the voice control by the voice control unit 14 is started, when there is a predetermined change in the cry monitored by the monitoring unit 11 (for example, when the cry stops or the cry is reduced), It is determined that the voice control content at that time is effective, and the voice control content is stored. Specifically, for each individual, the feature amount of the cry and the voice control content (learning data) are stored in association with each other. Here, the feature amount of the cry refers to the frequency, volume, and breath interval of the cry. The voice control content refers to the music ID for specifying the test sound, the BPM of the test sound, the frequency characteristics of the filter circuit, the absolute values of the sound volume, the added pseudo sound, and the like. In the example shown in the figure, the music ID, BPM, and center frequency of the bandpass filter are stored as the audio control content.

  The individual specifying unit 16 specifies an individual (individual infant) by comparing the individual cry characteristic amount stored in the control program storage unit 13 with the monitoring result of the monitoring unit 11. That is, the cry feature value of the cry that is the monitoring result is compared with the stored cry feature value of an arbitrary infant, and if the degree of match is high, it is determined that the individual to be monitored is an arbitrary infant.

  Further, the voice control unit 14 of the present embodiment performs voice control of the voice output unit 12 according to the past voice control contents stored in the control table of the individual specified by the individual specifying unit 16. That is, the sound control of the test sound is performed with the sound control content determined to be effective in the past from the playback start time.

  Next, the reproduction process according to the second embodiment will be described with reference to the flowchart of FIG. When the playback device 1 detects crying by monitoring by the monitoring unit 11 (S11: Yes), by comparing the feature amount of the cry contained in the monitoring result with the feature amount of the cry stored in the control table, An individual is specified (S12). Here, it is determined whether or not it has been specified (S13), and if it can be specified (S13: Yes), the voice control of the test sound is performed using the past voice control content of the individual, and the control sound is obtained. Output (S14). In addition, when it cannot be specified (when the voice control content of the individual is not stored in the control table, or when the crying voice has changed greatly from before, it is determined that the person is different) (S13: No), A prescribed test sound is output as in the first embodiment (S15). Thereafter, S16 to S20 are the same as S03 to S07 of the first embodiment.

  As described above, according to the second embodiment, since an individual is identified from the monitoring result of the monitoring unit 11 and voice control is performed using the voice control content based on the past performance of the individual, the infant can be more quickly Can be expected to stop crying.

  In the second embodiment, the music ID, the absolute value of the BPM, and the absolute value of the center frequency of the bandpass filter are stored in the control table as the audio control contents. As for the center frequency, a relative value from a prescribed test sound value may be stored. In addition, when there is one type of test sound, the storage of the music ID may be omitted. Moreover, when storing the pseudo sound as the audio control content, the BPM, the frequency characteristic, and the volume of the pseudo sound may be stored in addition to the pseudo sound ID.

[Third Embodiment]
Next, a third embodiment of the present invention will be described with reference to FIG. This embodiment is characterized by measuring a mother's heart sound and performing voice control based on the measurement result. Only differences from the second embodiment will be described below. Also in the present embodiment, the same components as those in the first and second embodiments are denoted by the same reference numerals, and detailed description thereof is omitted. The modification applied to the same components as those in the first and second embodiments is also applied to the present embodiment.

  FIG. 6 is a configuration diagram of the playback apparatus 1 according to the third embodiment. The playback device 1 according to the third embodiment has a configuration in which a heart sound measurement unit 17 is added as compared with the second embodiment. The contents of the control table stored in the control program storage unit 13 are also different from those in the second embodiment. The control table of the third embodiment stores the heart sound feature amount of the mother as the voice control content.

  The heart sound measuring unit 17 includes a microphone, and measures a heart sound feature quantity of an infant (individual) mother (another person) to be controlled by the voice control unit 14. As the heart sound feature quantity, the frequency (for example, center frequency) and BPM of the heart sound are measured. As a measuring method, for example, it is conceivable that the measurement is performed while the mother is holding the stuffed animal (reproducing apparatus 1) for several tens of seconds to several minutes. In addition, by holding a stuffed animal while the infant is crying, it is possible to associate the feature amount of the infant's cry and the heart sound feature amount of the mother.

  In addition, the voice control unit 14 according to the present embodiment performs the voice output of the voice output unit 12 according to the voice control contents (features of mother's heart sounds) stored in the control table of the individual specified by the individual specifying unit 16. Perform voice control. That is, the voice control of the test sound is performed with the feature amount of the mother's heart sound measured by the heart sound measuring unit 17 from the playback start time. Note that the flow of the reproduction process is the same as that in the second embodiment (see FIG. 5), and thus description thereof is omitted.

  As described above, according to the third embodiment, by measuring the mother's heart sound feature quantity and performing voice control so as to approach the heart sound feature quantity, it is possible to approach the infant's in womb environment, and more It can effectively stop infants from crying.

  In the third embodiment, the heart sound feature amount of the mother is measured, but the heart sound itself may be recorded. Then, as a voice control, the recorded heart sound may be added to the test sound.

  Further, the second embodiment and the third embodiment may be combined, and the voice control unit 14 may perform voice control based on the mother's heart sound feature amount and past voice control contents (learning data). In the second and third embodiments, it is not always necessary to specify an individual, and the individual specifying unit 16 may be omitted on the assumption that one infant uses a stuffed toy.

[Fourth Embodiment]
Next, a fourth embodiment of the present invention will be described with reference to FIG. The present embodiment is characterized in that voice control is performed on the mobile terminal 2 side. Only differences from the first embodiment will be described below. Note that this embodiment is also applicable to the second and third embodiments.

  FIG. 7 is a system configuration diagram of the reproduction system SY according to the fourth embodiment. The playback system SY according to the present embodiment includes the playback device 1 and the mobile terminal 2 as in the first embodiment. However, the playback device 1 has a simple configuration including only the monitoring unit 11, the audio output unit 12, the communication unit 15, and the speaker SP. On the other hand, the portable terminal 2 has a configuration including an operation unit 21, a storage unit 26, a communication unit 25, a voice control unit 27, a display unit 23, and a voice output unit 24. That is, as a configuration requirement, compared to the first embodiment, the music data storage unit 22 is changed to a storage unit 26 for storing the control program and music data, and a voice control unit 27 is added. The point is different. The voice control unit 27 functions in the same manner as the voice control unit 14 of the first embodiment. Note that the voice control unit 27 is a function of a support application installed in the mobile terminal 2.

  In this embodiment, when a cry is detected by the monitoring unit 11 of the playback device 1, information to that effect is transmitted to the mobile terminal 2, and a test sound selected by the mobile terminal 2 is output from the playback device 1. . The monitoring unit 11 continues to periodically transmit the monitoring result to the mobile terminal 2 after detecting the cry. The voice control unit 27 of the portable terminal 2 instructs the playback device 1 to continue the output of the test sound when detecting the crying stop from the monitoring result. If the crying stop is not detected, the voice control unit 27 changes the voice control content and controls the control sound. And the control sound is output to the playback device 1.

  As described above, according to the fourth embodiment, since voice control is performed on the mobile terminal 2 side, the hardware configuration of the playback device 1 can be simplified, and as a result, the cost of the stuffed toy can be reduced. Further, by providing the voice control unit 27 with a support application, it is possible to easily add functions, correct bugs, and the like.

  As mentioned above, although four embodiment was illustrated, it is possible to provide each component of the reproducing | regenerating apparatus 1 and the portable terminal 2 which were shown in each embodiment as a program. Further, the program can be provided by being stored in various recording media (CD-ROM, flash memory, etc.). That is, a program for causing a computer to function as each component of the playback device 1 and the portable terminal 2 and a recording medium on which the program is recorded are also included in the scope of rights of the present invention.

  Further, in each of the above embodiments, the audio output device of the present invention is configured by the playback device 1 and the portable terminal 2, but may be realized by only the playback device 1. Further, the audio output device of the present invention may be configured by the playback device 1, the portable terminal 2, and the cloud server, such as realizing the music data storage unit 22 in the cloud.

  Moreover, in each said embodiment, although the monitoring part 11 monitored the infant's cry, you may monitor also including audio | voices (breathing sound, speech, cry) other than a cry. Moreover, you may monitor the audio | voice emitted from children other than infants and adults. When a subject other than an infant is targeted, a relaxation effect or a stress-down effect can be expected instead of a cry-stopping effect. Other modifications can be made as appropriate without departing from the scope of the present invention.

  1: Playback device 2: Mobile terminal 11: Monitoring unit 12: Audio output unit 13: Control program storage unit 14: Audio control unit 15: Communication unit 16: Individual identification unit 17: Heart sound measurement unit 21: Operation unit 22: Music data Storage unit 23: Display unit 24: Audio output unit 25: Communication unit 26: Storage unit 27: Audio control unit SP: Speaker SY: Playback system

Claims (12)

A voice output unit that outputs a test sound that is a reference for voice control;
A monitoring unit that monitors changes in sound for predetermined biological information;
An audio output device comprising: an output state of the test sound; and an audio control unit that performs audio control of the audio output unit according to a monitoring result of the monitoring unit. The predetermined biological information is a crying voice,
The voice output device according to claim 1, wherein the voice control unit performs voice control of the voice output unit in accordance with a change in a cry after the test sound is output.   The sound output apparatus according to claim 2, wherein the sound control unit varies BPM (beats per minute) of the test sound or a sound source other than the test sound as sound control of the sound output unit.   The sound control unit varies the frequency characteristic and volume of a filter circuit that performs sound processing of the test sound or a sound source other than the test sound as sound control of the sound output unit. 4. The audio output device according to 3.   5. The sound control unit according to claim 2, wherein the sound control unit adds a pseudo sound to the test sound or a sound source other than the test sound as sound control of the sound output unit. 6. Audio output device. After starting voice control by the voice control unit, if there is a predetermined change in the cry monitored by the monitoring unit, further comprising a storage unit for storing the voice control content at that time,
The said audio | voice control part performs the audio | voice control of the said audio | voice output part according to the said said audio | voice control content memorize | stored in the said memory | storage part, The any one of Claim 2 thru | or 5 characterized by the above-mentioned. Audio output device. The storage unit further stores the feature amount of the cry and the voice control content for each individual,
Further comprising a personal identification unit for identifying the individual by comparing the individual cry characteristic stored in the storage unit with the monitoring result of the monitoring unit;
The voice output device according to claim 6, wherein the voice control unit performs voice control of the voice output unit in accordance with the past voice control contents of the individual specified by the individual specifying unit. . A heart sound measurement unit that measures the frequency and BPM of another person's heart sound related to the individual to be controlled by the voice control unit;
A storage unit for storing the measurement result of the heart sound measurement unit,
6. The voice control unit according to claim 2, wherein the voice control unit performs voice control of the voice output unit according to a measurement result of the heart sound measurement unit stored in the storage unit. Voice output device. The storage unit further stores, for each individual, the feature amount of the cry and the measurement result of the heart sound measurement unit,
Further comprising a personal identification unit for identifying the individual by comparing the individual cry characteristic stored in the storage unit with the monitoring result of the monitoring unit;
9. The voice control unit according to claim 8, wherein the voice control unit performs voice control of the voice output unit in accordance with a measurement result of the heart sound measurement unit of another person associated with the individual specified by the individual specifying unit. The audio output device described.   After starting the voice control by the voice control unit, after a predetermined number of changes in the voice control content, or after a predetermined time has passed, if there is no predetermined change in the cry monitored by the monitoring unit, a notification to that effect The audio output device according to claim 2, further comprising a notification unit that performs the operation. An audio output step for outputting a test sound as a reference for audio control;
A monitoring step for monitoring changes in sound for predetermined biological information;
An audio output device control method, comprising: executing an audio control step of performing audio control according to an output state of the test sound and a monitoring result of the monitoring step.   The program for making a computer perform each step in the control method of the audio | voice output apparatus of Claim 11.

Images