Apparatus performing based on voice recognition and artificial intelligence and method for controlling thereof
AssigneeSamsung Electronics Co., Ltd.
InventorsTaekwang Um, Heeyoung Chung, Kyungtae Kim, Junesig Sung
Life of this patent
Estimating the term…
Abstract
An electronic device includes: a microphone; a speaker; a memory configured to store parameter information; and a processor configured to: perform speech recognition of a user's speech received by the microphone, control the speaker to output a first response message based on the speech recognition of the user's speech, detect a re-request for the first response message, recognize a text of the first response message, determine a second response message and a first speech signal based on a first parameter corresponding to the text, and generate the second response message comprising the determined first speech signal.
Claims20
An electronic device comprising:
- a microphone;
- a speaker;
- a processor;
- memory configured to store parameter information and instructions which, when executed by the processor, cause the processor to:
- receive, by the microphone, a user's speech as a request,
- perform speech recognition of the user's speech,
- control the speaker to output a first response message based on the speech recognition of the user's speech,
- receive, from the user, a re-request for the first response message,
- recognize a part of the first response message,
- determine a second response message comprising a first speech signal, based on a first parameter corresponding to the part, and
- output, to the user, the second response message.
A method performed by an electronic device, the method comprising:
- receiving a user's speech as a request;
- performing speech recognition of the user's speech;
- outputting a first response message based on the speech recognition of the user's speech;
- receiving, from the user, a re-request for the first response message;
- recognizing a part of the first response message;
- determining a second response message comprising a first speech signal, based on a first parameter corresponding to the part;
- and
- outputting, to the user, the second response message.
Dependencies are inferred from the claim text.