Information processing apparatus and information processing method

1. An information processing apparatus, comprising:

at least one processor configured to:

detect a first speech of a user based on first voice information associated with the first speech of the user;

set a weight associated with a summary of the first speech of the user, wherein the weight is set based on information related to an application for execution by the user;

summarize first content of the first speech indicated by the first voice information to generate the summary of the first speech, wherein the summarization of the first content is based on the set weight associated with the summary;

detect a first language of the first speech of the user;

translate the first content of the first speech into a second language via a translation process, wherein the second language is different from the first language;

retranslate the first content, which is translated into the second language via the translation process, into the first language;

acquire second voice information, after the retranslation of the first content; and

include a first word in the first content of the first speech associated with the first voice information, based on the first word which is present in each of the retranslated first content and second content of a second speech associated with the second voice information.

2. The information processing apparatus according to claim 1 , wherein the summarization of the first content is further based on a start condition being satisfied.

3. The information processing apparatus according to claim 2 , wherein

the start condition is related to a non-speaking period in which the first speech is not performed by the user, and

the at least one processor is further configured to determine that the start condition is satisfied based on the non-speaking period which is one of equal to or larger than a specific period.

4. The information processing apparatus according to claim 2 , wherein

the start condition is related to a state of a voice recognition operation to acquire the first content of the first speech from the first voice information, and

the at least one processor is further configured to determine that the start condition is satisfied based on a stop request for the voice recognition operation.

5. The information processing apparatus according to claim 2 , wherein

the start condition is related to a state of a voice recognition operation to acquire the first content of the first speech from the first voice information, and

the at least one processor is further configured to determine that the start condition is satisfied based on completion of the voice recognition operation.

6. The information processing apparatus according to claim 2 , wherein

the start condition is related to the first content of the first speech, and

the at least one processor is further configured to determine that the start condition is satisfied based on a second word in the first content of the first speech indicated by the first voice information.

7. The information processing apparatus according to claim 2 , wherein

the start condition is related to the first content of the first speech, and

the at least one processor is further configured to:

detect a hesitation of the user to speak, based on the first voice information; and

determine that the start condition is satisfied based on the detection of the hesitation to speak.

8. The information processing apparatus according to claim 2 , wherein

the start condition is related to an elapsed time since the first voice information is obtained, and

the at least one processor is further configured to determine that the start condition is satisfied based on the elapsed time which is one of equal to or larger than a specific period.

9. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to abort the summarization, based on a summarization exclusion condition is satisfied.

10. The information processing apparatus according to claim 9 , wherein

the summarization exclusion condition is related to detection of a gesture, and

the at least one processor is further configured to determine that the summarization exclusion condition is satisfied based on the detection of the gesture.

11. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to change a summarization level of the first content of the first speech based on at least one of a speaking period specified by the first voice information and a number of characters specified by the first voice information.

12. The information processing apparatus according to claim 11 , wherein the at least one processor is further configured to limit the number of characters in the summary of the first speech to change the summarization level of the first content of the first speech.

13. The information processing apparatus according to claim 1 , wherein

the at least one processor is further configured to set the weight associated with the summary, based on at least one of information related to the user, information related to an environment associated with the user, or information related to a device, and

the information related to the device includes at least one of a type of the device or a state of the device.

14. The information processing apparatus according to claim 13 , wherein the information related to the user includes at least one of state information of the user or manipulation information of the user.

15. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to abort the translation based on a translation exclusion condition being satisfied.

16. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to control notification of the first content of the first speech.

17. An information processing method, comprising:

detecting a first speech of a user based on first voice information associated with the first speech of the user;

setting a weight associated with a summary of the first speech of the user, wherein the weight is set based on information related to an application for execution by the user;

summarizing first content of the first speech indicated by the first voice information to generate the summary of the first speech, wherein the summarization of the first content is based on the set weight associated with the summary;

detecting a first language of the first speech of the user;

translating the first content of the first speech into a second language via a translation process, wherein the second language is different from the first language;

retranslating the first content, which is translated into the second language via the translation process, into the first language;

acquiring second voice information, after the retranslation of the first content; and

including a word in the first content of the first speech associated with the first voice information, based on the word which is present in each of the retranslated first content and second content of a second speech associated with the second voice information.

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

detecting a first speech of a user based on first voice information associated with the first speech of the user;

setting a weight associated with a summary of the first speech of the user, wherein the weight is set based on information related to an application for execution by the user;

summarizing first content of the first speech indicated by the first voice information for generation of the summary of the first speech, wherein the summarization of the first content is based on the set weight associated with the summary;

detecting a first language of the first speech of the user;

translating the first content of the first speech into a second language via a translation process, wherein the second language is different from the first language;

retranslating the first content, which is translated into the second language via the translation process, into the first language;

acquiring second voice information, after the retranslation of the first content; and

including a word in the first content of the first speech associated with the first voice information, based on the word which is present in each of the retranslated first content and second content of a second speech associated with the second voice information.