Electronic apparatus and method for recognizing speech thereof

Patent metadata

Field	Value
Publication number	US-11978458-B2
Application number	US-202017290873-A
Country	US
Kind code	B2
Filing date	Apr 24, 2020
Priority date	Jul 15, 2019
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

An electronic apparatus is provided. The electronic apparatus according to an embodiment includes a communication interface, a memory configured to store identification information of a plurality of device, and a processor configured to, based on a user speech signal including a request related to a device being received, extract a first keyword related to a type of the device and a second keyword related to a characteristic of the device from the user speech signal, obtain specification information of the plurality of devices based on identification information of a plurality of devices corresponding to the first keyword stored in the memory, compare specification information of the plurality of devices and select a device corresponding to the second keyword, and perform an operation corresponding to the user speech signal using identification information of the selected device.

First claim

The invention claimed is:

1. An electronic apparatus comprising:
a communication interface;
a memory configured to store identification information of a plurality of devices; and
a processor configured to:
based on a user speech signal including a request related to a device being received, extract a first keyword related to a type of the device and a second keyword related to a characteristic of the device from the user speech signal,
obtain specification information of the plurality of devices based on identification information of a plurality of devices corresponding to the first keyword stored in the memory,
compare specification information of the plurality of devices and select a device corresponding to the second keyword, the second keyword including the extracted second keyword and an inference of the extracted second keyword stored in a knowledge base,
perform an operation corresponding to the user speech signal using identification information of the selected device,
generate a natural language corresponding to the selected device based on specification information of the selected device, and
request confirmation of a user regarding the selected device by generating a speech signal including the generated natural language.

2. The electronic apparatus as claimed in claim 1 , wherein the processor is further configured to identify specification information related to the second keyword from among the specification information of the plurality of devices and select a device corresponding to the second keyword by comparing specification information related to the second keyword.

3. The electronic apparatus as claimed in claim 1 , wherein the processor is further configured to:
based on a user speech signal requesting information related to a device being received, determine a display device to display information related to the device,
obtain specification information of the display device based on identification information of the display device,
generate a natural language corresponding to the display device using specification information of the display device, and
provide information corresponding to a user request along with a speech signal including the generated natural language corresponding to the display device.

4. The electronic apparatus as claimed in claim 1 ,
wherein the memory is configured to include a use history regarding the plurality of devices, and
wherein the processor is further configured to, based on specification information of a plurality of devices corresponding to the first keyword being identical, select a device corresponding to the second keyword.

5. The electronic apparatus as claimed in claim 4 , wherein the processor is further configured to:
based on a use history regarding a plurality of devices corresponding to the first keyword being identical, generate a control signal regarding one device from among the plurality of devices,
transmit the control signal to the one device, and
request a response of a user regarding the one device.

6. The electronic apparatus as claimed in claim 5 , wherein the processor is further configured to generate a natural language corresponding to the one device according to a user response regarding the one device, and store the generated natural language corresponding to the one device in the memory.

7. The electronic apparatus as claimed in claim 1 , wherein the specification information includes at least one of capacity, efficiency, service providing area, size, color, shape and manipulation method of the electronic apparatus.

8. A speech recognition method of an electronic apparatus, the method comprising:
receiving a user speech signal including a request related to a device;
extracting a first keyword related to a type of the device and a second keyword related to a characteristic of the device from the user speech signal;
obtaining specification information of a plurality of devices based on identification information of a plurality of devices corresponding to the first keyword;
comparing specification information of the plurality of devices and selecting a device corresponding to the second keyword, the second keyword including the extracted second keyword and an inference of the extracted second keyword stored in a knowledge base;
performing an operation corresponding to the user speech signal using identification information of the selected device,
generating a natural language corresponding to the selected device based on specification information of the selected device; and
requesting confirmation of a user regarding the selected device by generating a speech signal including the generated natural language.

9. The method as claimed in claim 8 , wherein the selecting of the device corresponding to the second keyword comprises:
identifying specification information related to the second keyword from among the specification information of the plurality of devices; and
selecting a device corresponding to the second keyword by comparing specification information related to the second keyword.

10. The method as claimed in claim 8 , the method further comprising:
based on a user speech signal requesting information related to a device being received, determining a display device to display information related to the device;
obtaining specification information of the display device based on identification information of the display device;
generating a natural language corresponding to the display device using specification information of the display device; and
providing information corresponding to a user request along with a speech signal including the generated natural language corresponding to the display device.

11. The method as claimed in claim 8 , the method further comprising:
based on specification information of a plurality of devices corresponding to the first keyword being identical, selecting a device corresponding to the second keyword.

12. The method as claimed in claim 11 , the method further comprising:
based on a use history regarding a plurality of devices corresponding to the first keyword being identical, generating a control signal regarding one device from among the plurality of devices;
transmitting the control signal to the one device; and
requesting a response of a user regarding the one device.

13. The method as claimed in claim 12 , the method further comprising:
generating a natural language corresponding to the one device according to a user response regarding the one device; and
storing the generated natural language corresponding to the one device in a memory.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choi Wonjong
• Kim Soofeel
• Park Yewon
• Ham Jina

Classifications

• G10L17/24 Primary

  the user being prompted to utter a password or a predefined phrase · CPC title

• G10L15/183

  using context dependencies, e.g. language models · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L17/02

  Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title