`
`to detect an
`
`in a
`
`object
`
`detecting
`
`area;
`
`1. Asound reproduction apparatus comprising:
`a detector configured
`a
`
`to output
`
`a sound; and
`
`5
`
`speaker configured
`a controller configured
`to control the speaker
`object based on an attribute of the object.
`
`to output the sound to the
`
`2. The sound reproducing apparatus of claim 1, wherein the controller is
`
`10
`
`configured
`
`to control
`
`the speaker
`
`to output different sounds for different
`
`attributes.
`
`3. The sound reproducing apparatus of claim 1, wherein the attribute of
`the object is determined based on information acquired by the detector.
`
`15
`
`4. The sound reproducing apparatus of claim 3, wherein:
`the object is a humanbeing, and
`the attribute comprises at least one of age or sex of the humanbeing.
`
`20
`
`5. The sound reproducing apparatusof claim 4, wherein:
`
`the information acquired by the detector comprises
`
`an
`
`imageof a face of
`
`the human being acquired using
`the at least one of the age or sex is determined based on the image of the
`
`a camera, and
`
`face.
`
`61
`
`
`
`6. The sound reproducing apparatus of claim 5, wherein the at least one of
`a
`age or sex is determined by using
`
`pattern matching process.
`
`7. The sound reproducing apparatusof claim 4, wherein:
`
`the information acquired by the detector comprises
`the humanbeing determined based on a
`
`plurality of images taken by
`
`a camera.
`
`movementof a face of
`
`10
`
`15
`
`8. The sound reproducing apparatus of claim 4, wherein:
`
`the information acquired by the detector comprises
`humanbeing determined based on an
`
`image taken by
`
`a camera.
`
`an eye direction of the
`
`9. The sound reproducing apparatus of claim 1, wherein the controller is
`
`configured
`
`to determinetheattribute of the object.
`
`10. The sound reproducing apparatus of claim 1, wherein the speakeris a
`
`directional speaker.
`
`11. The sound reproducing apparatus of claim 10, wherein an emission
`
`20
`
`angle of the directional speaker is between 0° to +30°, inclusive.
`
`12. Asound reproduction apparatus comprising:
`a detector configured
`a
`
`speaker configured
`
`to output
`
`a sound; and
`
`to detect an
`
`in a
`
`object
`
`detecting
`
`area;
`
`62
`
`
`
`a controller configured
`to control the speaker
`object based on an emotion of the object.
`
`to output the sound to the
`
`13. The sound reproducing apparatus of claim 12, wherein the controller is
`
`5
`
`configured
`
`to control the speaker
`
`to output different sounds for different emotions.
`
`14. The sound reproducing apparatus of claim 12, wherein the emotion of
`the object is determined based on information acquired by the detector.
`
`15. The sound reproducing apparatus of claim 14, wherein:
`the object is a humanbeing, and
`the information comprises at least one of
`
`information acquired from a
`
`facial image of the human being, voice sound of the humanbeing, linguistic
`
`expression of the humanbeing,
`
`or
`
`gesture of the humanbeing.
`
`10
`
`15
`
`microphone,
`
`a
`
`16. The sound reproducing apparatus of claim 15, wherein the detector
`comprises at least one of a camera, a
`time-of-flight sensor, a
`sensor.
`
`millimeter-wave sensor, a millimeter-wave radar,
`
`or a
`
`walking
`
`20
`
`17. The sound reproducing apparatus of claim 15, wherein the emotion is
`
`estimated from an arousal component and a valence component calculated from
`
`the information.
`
`18. The sound reproducing apparatus of claim 12, wherein the controller is
`
`63
`
`
`
`configured
`
`to determine the emotion of the object.
`
`19. The sound reproducing apparatus of claim 12, wherein the speakeris a
`
`directional speaker.
`
`20. The sound reproducing apparatus of claim 19, wherein an emission
`
`angle of the directional speaker is between 0° to +30°, inclusive.
`
`21. Amethod, comprising:
`acquiring information with respect to an
`object
`detecting
`an attribute or an emotion of the object based on the acquired
`
`in a
`
`area;
`
`acquiring
`
`information; and
`
`controlling
`
`a
`
`speaker
`
`to output sound to the object based on the attribute
`
`or the emotion.
`
`10
`
`15
`
`22. The methodof claim 21, wherein:
`
`the attribute is acquired and the speaker is controlled to output sound to
`the object based on the attribute, and
`
`the controlling the speaker comprises controlling the speaker
`
`to output
`
`20
`
`~=different sounds for different attributes.
`
`23. The methodof claim 21, wherein:
`
`the attribute is acquired and the speaker is controlled to output sound to
`
`the object based on the attribute,
`
`64
`
`
`
`the object is a humanbeing, and
`the attribute comprises at least one of age or sex of the humanbeing.
`
`24. The methodof claim 23, wherein:
`
`5
`
`the information comprises
`
`an
`
`image of a face of the human acquired by
`
`a
`
`camera, and
`
`the at least one of the age or sex is determined based on the image of the
`
`face.
`
`10
`
`25. The method of claim 24, wherein the at least one of age or sex is
`
`determined by using
`
`a
`
`pattern matching process.
`
`26. The methodof claim 23, wherein:
`
`the information comprises movement of a face of the human being
`a camera.
`determined based on a
`
`plurality of images taken by
`
`15
`
`27. The methodof claim 23, wherein:
`
`the information comprises
`
`an eye direction of the human being determined
`a camera.
`
`based on an
`
`image taken by
`
`20
`
`28. The methodof claim 21, wherein:
`
`the emotion is acquired and the speaker is controlled to output sound to
`the object based on the emotion, and
`
`the controlling the speaker comprises controlling the speaker
`
`to output
`
`65
`
`
`
`different soundsfor different emotions.
`
`29. The methodof claim 21, wherein:
`
`the emotion is acquired and the speaker is controlled to output sound to
`
`the object based on the emotion,
`the object is a humanbeing, and
`the information comprises at least one of
`
`information acquired from a
`
`facial image of the human being, voice sound of the humanbeing, linguistic
`
`expression of the humanbeing,
`
`or
`
`gesture of the humanbeing.
`
`10
`
`at least
`
`30. The method of claim 29, wherein the information is acquired by
`time-of-flight sensor, a millimeter-wave sensor,
`sensor.
`
`one of a camera, a
`
`microphone,
`
`a
`
`a millimeter-wave radar,
`
`or a
`
`walking
`
`15
`
`31. The method of claim 29, wherein the emotion is estimated from an
`
`arousal component and a valence componentcalculated from the information.
`
`32. The methodof claim 21, wherein the speakeris a directional speaker.
`
`20
`
`33. The method of claim 32, wherein an emission angle of the directional
`
`speakeris between 0° to +30°, inclusive.
`
`34. A sound control device comprising:
`a controller configured
`
`to acquire
`
`an attribute or an emotion of an
`
`object
`
`66
`
`
`
`based on information with respect to the object, and cause a
`speaker
`sound to the object based on the attribute or the emotion of the object.
`
`to output
`
`35. The sound control device of claim 34, wherein the controller is
`
`5
`
`configured
`
`to cause the speaker
`
`to output different soundsfor different attributes
`
`or to output different sounds for different emotions.
`
`36. The sound control device of claim 34, wherein:
`
`the object is a humanbeing,
`to acquire the attribute of the object, and cause
`the controller is configured
`to output sound to the object based on the attribute of the object, and
`the speaker
`the attribute comprises at least one of age or sex of the humanbeing.
`
`37. The sound control device of claim 36, wherein:
`
`the information comprises
`
`imageof a face of the human, and
`the at least one of the age or sex is determined based on the image of the
`
`an
`
`10
`
`15
`
`face.
`
`38. The sound control device of claim 37, wherein the at least one of age or
`
`20
`
`sex is determined by using
`
`a
`
`pattern matching process.
`
`39. The sound control device of claim 37, wherein:
`
`the information comprises movement of a face of the human being
`determined based on a
`
`plurality of images.
`
`67
`
`
`
`40. The sound control device of claim 37, wherein:
`
`the information comprises
`
`an eye direction of the human being determined
`
`based on an
`
`image.
`
`41. The sound control device of claim 34, wherein:
`
`the object is a humanbeing,
`
`the speaker
`
`to acquire the emotion of the object, and cause
`the controller is configured
`to output sound to the object based on the emotion of the object, and
`the information comprises at least one of information acquired from a
`
`10
`
`facial image of the human being, voice sound of the humanbeing, linguistic
`
`expression of the humanbeing,
`
`or
`
`gesture of the humanbeing.
`
`42. The sound control device of claim 41, wherein the emotion is estimated
`
`15
`
`from an arousal component and a valence component calculated from the
`
`information.
`
`43. The sound control device of claim 34, wherein the controller is
`
`configured
`
`to determinethe attribute or the emotion of the object.
`
`20
`
`44. The sound control device of claim 34, wherein the controller is further
`
`configured
`
`to acquire the information with respect to the object.
`
`45. The sound control device of claim 34, wherein:
`
`68
`
`
`
`the controller includes:
`
`a
`
`processor; and
`
`a
`
`non-transitory computer readable medium storing
`the program, when executed by the processor, causes the processor to
`acquire the attribute or the emotion of then object based on the information with
`respect to the object, and cause the speaker
`to output the sound to the object
`based on theattribute or the emotion of the object.
`
`a program,
`
`69
`
`