Call system, call apparatus, call method, and non-transitory computer-readable medium storing program

A call apparatus comprising:

• at least one memory storing instructions;
• and
• at least one processor configured to execute the instructions to:
• detect a motion of a user;
• store unique information different for each user in a user profile;
• generate non-vocalization data based on the motion of the user and generate a plurality of word candidates predicted according to the non-vocalization data;
• generate a voice to be output to a talk partner according to a word selected by the user from among the plurality of word candidates;
• and
• transmit a signal generated from the voice, to an apparatus used by the talk partner, wherein
• generating the plurality of the word candidates comprises changing a candidate of a word to be predicted according to the unique information stored in the user profile, and
• detecting the motion comprises:
• acquiring a movement of a mouth of the user for each of the patterns of mouth opening to utter a word;
• creating reference pattern data for each of the patterns according to the movement of the mouth;
• determining, for each instance of the mouth opening, a corresponding patter of the patterns in the reference pattern data for the movement of the mouth;
• and
• replacing a determination result with words as the non-vocalization data.

A call method comprising:

• storing unique information different for each user in a user profile;
• detecting a motion of the user;
• generating non-vocalization data based on the motion of the user;
• generating a plurality of word candidates predicted according to the non-vocalization data and the unique information different for each user stored in the user profile;
• and
• generating a voice to be output to a talk partner according to a word selected by the user from among the plurality of word candidates;
• and
• transmitting a signal generated from the voice, to an apparatus used by the talk partner, wherein
• generating the plurality of the word candidates comprises changing a candidate of a word to be predicted according to the unique information stored in the user profile,
• detecting the motion comprises:
• acquiring a movement of a mouth of the user for each of the patterns of mouth opening to utter a word;
• creating reference pattern data for each of the patterns according to the movement of the mouth;
• determining, for each instance of the mouth opening, a corresponding pattern of the patterns in the reference pattern data for the movement of the mouth corresponds to;
• and
• replacing a determination result with words as the non-vocalization data.