# US 2022/0036882 A1 · Electronic apparatus, system and method for using speech recognition service

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

- Number: US 2022/0036882 A1
- Document ID: US20220036882A1
- Status: Published application
- Kind: A1
- Application number: 17/276,309
- Filed: 2019-09-20
- Published: 2022-02-03
- Earliest claimed: 2018-09-21
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Jin Hyeong AHN; Hyoung-Jin LEE
- Web page: https://patentgrep.com/patent/US20220036882A1

## CPC

- G10L 15/08: Speech classification or search
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- G06F 2209/541: Client-server
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 2015/088: {Word spotting}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

According to an embodiment, an electronic apparatus includes a plurality of service engines corresponding to a plurality of speech recognition services, respectively; a communication module connected via wireless communication to a plurality of service servers for providing the plurality of speech recognition services, respectively; a mike configured to receive speech of a user; and a service controller configured to store at least one wakeup word corresponding to each of the plurality of speech recognition services in advance, determine a speech recognition service corresponding to a wakeup word received by the mike from among the plurality of speech recognition services based on the plurality of wakeup words stored in advance, send a user command received by the mike to a service engine corresponding to the determined speech recognition service among the plurality of service engines.

## Claims

### Claim 1

An electronic apparatus comprising:
a plurality of service engines corresponding to a plurality of speech recognition services, respectively;
a communication module connected via wireless communication to a plurality of service servers for providing the plurality of speech recognition services, respectively;
a mike configured to receive speech of a user; and
a service controller configured to:
store at least one wakeup word corresponding to each of the plurality of speech recognition services in advance,
determine a speech recognition service corresponding to a wakeup word received by the mike from among the plurality of speech recognition services based on the plurality of wakeup words stored in advance, and
send a user command received by the mike to a service engine corresponding to the determined speech recognition service among the plurality of service engines.

### Claim 2 (depends on 1)

The electronic apparatus of claim 1, wherein the plurality of service engines are configured to run a plurality of applications, respectively, to use the plurality of speech recognition services.

### Claim 3 (depends on 1)

The electronic apparatus of claim 1, wherein the service engine corresponding to the determined speech recognition service is configured to transmit the user command to a service server which provides the determined speech recognition service among the plurality of service servers, through the communication module.

### Claim 4 (depends on 3)

The electronic apparatus of claim 3, wherein the service engine corresponding to the determined speech recognition service is configured to receive a service response corresponding to the user command from the service server which provides the determined speech recognition service among the plurality of service servers, through the communication module.

### Claim 5 (depends on 1)

The electronic apparatus of claim 1, wherein the service controller is configured to recognize and convert a wakeup word received by the mike to text.

### Claim 6 (depends on 1)

The electronic apparatus of claim 1, wherein at least one of the plurality of service engines is configured to recognize and convert a wakeup word received by the mike to text.

### Claim 7

A method for using a speech recognition service to use a plurality of speech recognition services in a single electronic apparatus, the method comprising:
receiving a user command uttered by a user through a mike equipped in the single electronic apparatus;
determining a service domain corresponding to the received user command;
determining a speech recognition service corresponding to the service domain from among the plurality of speech recognition services;
sending the received user command to a service engine corresponding to the determined speech recognition service, among a plurality of service engines corresponding to the plurality of speech recognition services, respectively; and
transmitting, by the service engine, the received user command to a service server which provides the determined speech recognition service.

### Claim 8 (depends on 7)

The method of claim 7, wherein the determining of the service domain corresponding to the received user command comprises performing text matching or keyword matching on the received user command

### Claim 9 (depends on 8)

The method of claim 8, wherein the determining of the service domain corresponding to the received user command comprises:
storing at least one text corresponding to each of a plurality of service domains in advance; and
determining whether the at least one text stored in advance matches the received user command, to perform the text matching.

### Claim 10 (depends on 8)

The method of claim 8, wherein the determining of the service domain corresponding to the received user command comprises:
storing at least one keyword corresponding to each of a plurality of service domains in advance; and
determining whether the received user command includes the at least one keyword stored in advance, to perform the keyword matching.

### Claim 11 (depends on 10)

The method of claim 10, wherein the determining of the service domain corresponding to the received user command comprises:
setting priorities between the plurality of service domains in advance; and
determining a service domain corresponding to the received user command based on the priorities when the received user command includes keywords corresponding to two or more service domains.

### Claim 12 (depends on 8)

The method of claim 8, further comprising:
updating a database used for the text matching or the keyword matching based on a user feedback about the determined service domain when the user feedback is entered.

### Claim 13 (depends on 7)

The method of claim 7, further comprising:
sending the received user command to the plurality of service engines when the determining of the service domain corresponding to the received user command fails; and
transmitting, by the plurality of service engines, the received user command to a plurality of service servers which provide the plurality of speech recognition services, respectively.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
outputting a service response corresponding to the received user command when the service response is transmitted from at least one of the plurality of service servers.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
receiving a user feedback about the output service response; and
updating a database used to determine the service domain, based on the user feedback.
