Information processing apparatus, information processing system, and information processing method

An information processing system, comprising:

• a user terminal that includes a microphone configured to receive a user speech;
• and
• a data processing server that includes at least one processor configured to:
• execute a voice recognition process on the user speech received from the user terminal to generate a plurality of user speech candidates associated with the user speech;
• update a degree of confidence of each user speech candidate of the plurality of user speech candidates based on an interaction between a user and an information processing apparatus, wherein
• the interaction between the user and the information processing apparatus is after the user speech,
• each user speech candidate of the plurality of user speech candidates is a voice recognition result of the voice recognition process, and
• the degree of confidence is an evaluation value that indicates reliability of the voice recognition result of the user speech;
• determine a misrecognition of the user speech based on the update of the degree of confidence of at least one user speech candidate of the plurality of user speech candidates;
• correct a specific part of a system response based on the determination of the misrecognition of the user speech and a degree of importance associated with the specific part, wherein the degree of importance associated with the specific part is with respect to the interaction between the user and the information processing apparatus;
• and
• output the system response which includes the corrected specific part.

An information processing method, comprising:

• executing, by a processor, a voice recognition process on a user speech to generate a plurality of user speech candidates associated with the user speech;
• updating, by the processor, a degree of confidence of each user speech candidate of the plurality of user speech candidates based on an interaction between a user and an information processing apparatus, wherein
• the interaction between the user and the information processing apparatus is after the user speech,
• each user speech candidate of the plurality of user speech candidates is a voice recognition result of the voice recognition process, and
• the degree of confidence is an evaluation value that indicates reliability of the voice recognition result of the user speech;
• determining, by the processor, a misrecognition of the user speech based on the updating of the degree of confidence of at least one user speech candidate of the plurality of user speech candidates;
• correcting, by the processor, a specific part of a system response based on the determination of the misrecognition of the user speech and a degree of importance associated with the specific part, wherein the degree of importance associated with the specific part is with respect to the interaction between the user and the information processing apparatus;
• and
• outputting, by the processor, the system response including the corrected specific part.

An information processing method which is executed by an information processing system including a user terminal and a data processing server, the information processing method comprising:

• receiving, by the user terminal, a voice input of a user speech;
• executing, by the data processing server, a voice recognition process on the user speech received from the user terminal to generate a plurality of user speech candidates associated with the user speech;
• updating, by the data processing server, a degree of confidence of each user speech candidate of the plurality of user speech candidates based on an interaction between a user and an information processing apparatus, wherein
• the interaction between the user and the information processing apparatus is after the user speech,
• each user speech candidate of the plurality of user speech candidates is a voice recognition result of the voice recognition process, and
• the degree of confidence is an evaluation value that indicates reliability of the voice recognition result of the user speech;
• determining, by the data processing server, a misrecognition of the user speech based on the updating of the degree of confidence of at least one user speech candidate of the plurality of user speech candidates;
• correcting, by the data processing server, a specific part of a system response based on the determination of the misrecognition of the user speech and a degree of importance associated with the specific part, wherein the degree of importance associated with the specific part is with respect to the interaction between the user and the information processing apparatus;
• and
• outputting, by the data processing server, the system response which includes the corrected specific part.

A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a processor, cause the processor to execute operations, the operations comprising:

• executing a voice recognition process on a user speech to generate a plurality of user speech candidates associated with the user speech;
• updating a degree of confidence of each user speech candidate of the plurality of user speech candidates based on an interaction between a user and an information processing apparatus, wherein
• the interaction between the user and the information processing apparatus is after the user speech,
• each user speech candidate of the plurality of user speech candidates is a voice recognition result of the voice recognition process, and
• the degree of confidence is an evaluation value that indicates reliability of the voice recognition result of the user speech;
• determining a misrecognition of the user speech based on the updating of the degree of confidence of at least one user speech candidate of the plurality of user speech candidates;
• correcting a specific part of a system response based on the determination of the misrecognition of the user speech and a degree of importance associated with the specific part, wherein the degree of importance associated with the specific part is with respect to the interaction between the user and the information processing apparatus;
• and
• outputting the system response which includes the corrected specific part.