# US 2021/0280178 A1 · Electronic device and voice recognition method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0280178 A1
- Document ID: US20210280178A1
- Status: Published application
- Kind: A1
- Application number: 16/317,865
- Filed: 2017-07-18
- Published: 2021-09-09
- Earliest claimed: 2017-07-18
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Jae-hyun BAE
- Web page: https://patentgrep.com/patent/US20210280178A1

## CPC

- G10L 15/04: Segmentation; Word boundary detection
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/08: Speech classification or search
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G10L 2015/088: {Word spotting}
- G10L 2015/225: {Feedback of the input speech}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

An electronic device is disclosed. The electronic device comprises: a voice reception unit for receiving user's voice; a storage unit for storing a first voice recognition module for recognizing user's voice and a second voice recognition module for recognizing only predetermined voice in the user's voice; and a processor for performing voice recognition of only a part of the user's voice through the first voice recognition module, when a result of voice recognition through the second voice recognition module shows that the user's voice includes the predetermined voice.

## Claims

### Claim at position 1

-15. (canceled)

### Claim 16

An electronic device, comprising:
a voice input unit configured to receive a user voice input; and
a processor configured to:
receive the user voice input through the voice input unit,
based on a predetermined voice input being identified in the user voice input, obtain a text corresponding to a part of the user voice input excluding the predetermined voice input, and
perform a function corresponding to a voice recognition based on the text corresponding to the part of the user voice input.

### Claim 17 (depends on 16)

The electronic device as claimed in claim 16, wherein the predetermined voice input includes a voice input which is uttered with an intention of canceling voice input uttered by a user prior to the predetermined voice input.

### Claim 18 (depends on 17)

The electronic device as claimed in claim 17, wherein the processor is configured to perform the function corresponding to the voice recognition of only voice input received after the predetermined voice input.

### Claim 19 (depends on 16)

The electronic device as claimed in claim 16, wherein the predetermined voice input includes voice input which is meaninglessly uttered by a user.

### Claim 20 (depends on 19)

The electronic device as claimed in claim 19, wherein the processor is configured to perform the function corresponding to the voice recognition of only remaining voice input other than the predetermined voice input included in the user voice input.

### Claim 21 (depends on 16)

The electronic device as claimed in claim 16, wherein the processor is configured to control an operation of the electronic device based on a result of the voice recognition.

### Claim 22 (depends on 16)

The electronic device as claimed in claim 16, wherein the processor is configured to, if a voice recognition score calculated for the predetermined voice input is greater than or equal to a predetermined threshold, perform the function corresponding to the voice recognition of only a part of the user voice input.

### Claim 23 (depends on 16)

The electronic device as claimed in claim 16, wherein the processor is configured to, when the predetermined voice input is not recognized in the user voice input, control an operation of the electronic device based on a result of the voice recognition of the user voice input.

### Claim 24 (depends on 16)

The electronic device as claimed in claim 16, wherein the processor is configured to recognize the user voice input through a first voice recognition module and recognize the predetermined voice input included in the user voice input through a second recognition module.

### Claim 25

A voice recognition method of an electronic device, the voice recognition method comprising:
receiving a user voice input;
based on a predetermined voice input being identified in the user voice input, obtaining a text corresponding to a part of the user voice input excluding the predetermined voice input; and
performing a function corresponding to a voice recognition based on the text corresponding to the part of the user voice input.

### Claim 26 (depends on 25)

The voice recognition method as claimed in claim 25, wherein the predetermined voice input includes a voice input which is uttered with an intention of cancelling voice input uttered by a user prior to the predetermined voice input.

### Claim 27 (depends on 26)

The voice recognition method as claimed in claim 26, wherein the performing comprises performing the function corresponding to the voice recognition of only voice input received after the predetermined voice input.

### Claim 28 (depends on 25)

The voice recognition method as claimed in claim 25, wherein the predetermined voice input includes voice which is meaninglessly uttered by a user.

### Claim 29 (depends on 28)

The voice recognition method as claimed in claim 28, wherein the performing comprises performing the function corresponding to the voice recognition of only remaining voice input other than the predetermined voice input included in the user voice input.

### Claim 30 (depends on 25)

The voice recognition method as claimed in claim 25, further comprising: controlling an operation of the electronic device based on a result of the voice recognition.

### Claim 31 (depends on 25)

The voice recognition method as claimed in claim 25, wherein the performing comprises if a voice recognition score calculated for the predetermined voice input is greater than or equal to a predetermined threshold, performing the function corresponding to the voice recognition of only a part of the user voice input.

### Claim 32 (depends on 25)

The voice recognition method as claimed in claim 25, further comprising: when the predetermined voice input is not recognized in the user voice input, controlling an operation of the electronic device based on a result of the voice recognition of the user voice input.

### Claim 33 (depends on 25)

The voice recognition method as claimed in claim 25, wherein the user voice input is recognized by a first voice recognition module and the predetermined voice input is recognized by a second voice recognition module.

### Claim 34

An electronic device, comprising:
a voice input unit configured to receive a user voice input; and
a processor configured to:
receive the user voice input through the voice input unit,
based on a predetermined voice input being identified in the user voice input, obtain a text corresponding to a part of the user voice input excluding the identified predetermined voice input in the user voice input and perform a function corresponding to a voice recognition based on the text corresponding to the part of the user voice input, and
based on the predetermined voice input being not identified in the user voice input, obtain a text corresponding to the user voice input and perform a function corresponding to a voice recognition based on the text corresponding to the user voice input,
wherein the predetermined voice input is a voice input for canceling a voice input received prior to the predetermined voice input or the predetermined voice input is a meaninglessly voice input, and
wherein the meaninglessly voice input is received between a first voice input and a second voice input included in the user voice input and is not related to an operation of the electronic device executed based on the function corresponding to the voice recognition.

### Claim 35 (depends on 34)

The electronic device as claimed in claim 34, wherein the processor is configured to recognize the user voice input through a first voice recognition module and recognize the predetermined voice input included in the user voice input through a second recognition module.
