Question answering device, question answering method, and program
AssigneeToyota Jidosha Kabushiki Kaisha
InventorKeiko Nakano
Life of this patent
Estimating the term…
Abstract
A question answering device includes: a reception unit configured to receive speech which is uttered in a vehicle; a generation unit configured to generate a character string which is indicated by the speech based on speech recognition; a first acquisition unit configured to acquire an answer to a question indicated by the character string; a second acquisition unit configured to acquire control information for localizing speech of the answer at a position associated with the answer in the vehicle; and an output unit configured to output the control information.
Claims5
A question answering device comprising:
- a speaker that receives speech which is uttered in a vehicle;
- a generation processor that generates a character string which is indicated by the speech based on speech recognition;
- a first acquisition processor that acquires a target answer to a question indicated by the character string;
- a second acquisition processor that acquires control information for localizing speech of the target answer at a coordinate value indicating a specific position of an onboard device in the vehicle that corresponds with the target answer;
- and
- a speaker that outputs the target answer by stereophonic sound using the control information.
A question answering method causing a computer to perform:
- a reception process of receiving speech which is uttered in a vehicle;
- a generation process of generating a character string which is indicated by the speech based on speech recognition;
- a first acquisition process of acquiring a target answer to a question indicated by the character string;
- a second acquisition process of acquiring control information for localizing speech of the target answer at a coordinate value indicating a specific position of an onboard device in the vehicle that corresponds with the target answer;
- and
- an output process of outputting the target answer by stereophonic sound using the control information.
A non-transitory computer-readable storage medium storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
- a reception process of receiving speech which is uttered in a vehicle;
- a generation process of generating a character string which is indicated by the speech based on speech recognition;
- a first acquisition process of acquiring a target answer to a question indicated by the character string;
- a second acquisition process of acquiring control information for localizing speech of the target answer at a coordinate value indicating a specific position of an onboard device in the vehicle that corresponds with the target answer;
- and
- an output process of outputting the target answer by stereophonic sound using the control information.
Dependencies are inferred from the claim text.