Electronic device and operation method for performing speech recognition

Patent metadata

Field	Value
Publication number	US-11830501-B2
Application number	US-202217750860-A
Country	US
Kind code	B2
Filing date	May 23, 2022
Priority date	Aug 20, 2018
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

An electronic device for performing speech recognition and a method therefor are provided. The method includes detecting a first text, which is preset for performing speaker recognition, by performing speech recognition on a first speech signal, performing speaker recognition on a second speech signal acquired after the first speech signal, based on the first text being detected, and executing a voice command obtained from the second speech signal, based on a result of performing the speaker recognition on the second speech signal indicating that a speaker of the second speech signal corresponds to a first speaker who registered the first text.

First claim

What is claimed is:

1. A method of performing speech recognition by an electronic device, the method comprising:
registering a user by storing characteristic information of voice signals of the user as registration information of the user for executing at least one voice command;
receiving a speech signal including a first text and a voice command uttered subsequently to the first text;
determining whether the first text is detected in the received speech signal;
determining characteristic information of the received speech signal, based on determining that the first text is detected in the speech signal;
determining whether a speaker who uttered the first text and the voice command corresponds to the registered user by comparing the characteristic information of the received speech signal with the characteristic information stored as the registration information of the registered user;
executing the voice command and outputting a result of executing the voice command, based on determining that the speaker who uttered the first text and the voice command corresponds to the registered user; and
ignoring the voice command, based on determining that the speaker who uttered the first text and the voice command does not correspond to the registered user.

2. The method of claim 1 , wherein the at least one voice command includes at least one of Internet shopping, financial transaction, call connection, message transmission and alarm setting.

3. The method of claim 1 , wherein the outputting of the result of executing the voice command comprises:
outputting a synthetic speech signal generated by executing the voice command; and
displaying an image generated by executing the voice command.

4. An electronic device for performing speech recognition, the electronic device comprising:
a microphone;
at least one memory storing one or more instructions; and
at least one processor configured to, by executing the one or more instructions, to:
control the memory to register a user by store characteristic information of voice signals of the user as registration information of the user for executing at least one voice command,
receive, through the microphone, a speech signal including a first text and a voice command uttered subsequently to the first text,
determine whether a first text is detected in the received speech signal,
determine characteristic information of the received speech signal, based on determining that the first text is detected in the speech signal,
determine whether a speaker who uttered the first text and the voice command corresponds to the registered user by comparing the characteristic information of the received speech signal with the characteristic information stored as the registration information of the registered user,
execute the voice command and output a result of executing the voice command, based on determining that the speaker who uttered the first text and the voice command corresponds to the registered user, and
ignore the voice command, based on determining that the speaker who uttered the first text and the voice command does not correspond to the registered user.

5. The electronic device of claim 4 , wherein the at least one voice command includes at least one of Internet shopping, financial transaction, call connection, message transmission and alarm setting.

6. The electronic device of claim 4 , the at least one processor is further configured, by executing the one or more instructions, to:
output a synthetic speech signal generated by executing the voice command and
display an image generated by executing the voice command.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choi Wonjong
• Kim Soofeel
• Ham Jina

Classifications

• G10L17/00 Primary

  Speaker identification or verification techniques · CPC title

• G06F40/295

  Named entity recognition · CPC title

• G10L17/06

  Decision making techniques; Pattern matching strategies · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L17/22 Primary

  Interactive procedures; Man-machine interfaces · CPC title