# US 10,319,367 B2 · Speech signal processing method and speech signal processing apparatus

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

- Number: US 10,319,367 B2
- Document ID: US10319367B2
- Status: Granted
- Kind: B2
- Application number: 14/936,043
- Filed: 2015-11-09
- Published: 2016-05-12
- Granted: 2019-06-11
- Earliest claimed: 2014-11-07
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Tae-yoon Kim; Sang-ha Kim; Sung-soo Kim; Jin-sik Lee; Chang-woo Han; Eun-kyoung Kim; Jae-won Lee
- Web page: https://patentgrep.com/patent/US10319367B2

## CPC

- G10L 15/063: {Training}
- G10L 15/18: using natural language modelling
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G10L 15/04: Segmentation; Word boundary detection
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 15/187: Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
- G10L 2015/0635: {updating or merging of old and new templates; Mean values; Weighting}
- G10L 2015/227: {of the speaker; Human-factor methodology}
- 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)

## Abstract

A speech signal processing method of a user terminal includes: receiving a speech signal, detecting a personalized information section including personal information in the speech signal, performing data processing on the personalized information section of the speech signal by using a personalized model generated based on the personal information, and receiving, from a server, a result of the data processing performed by the server on a general information section of the speech signal that is different than the personalized information section of the speech signal.

## Claims

### Claim 1

A speech signal processing method of a user terminal, the speech signal processing method comprising:
receiving a speech signal;
detecting a personalized information section including personal information in the speech signal;
performing data processing on the personalized information section of the speech signal by using a personalized model generated based on the personal information;
receiving, from the server, speech section information about the personalized information section and a general information section, wherein the speech section information includes section marking information that marks a location of the personalized information section in the speech signal;
receiving, from a server, a result of the data processing performed by the server on the general information section of the speech signal that is different than the personalized information section of the speech signal;
performing data processing based on the speech section information received from the server, wherein the performing data processing comprises performing data processing on the personalized information section corresponding to the section marking information received from the server; and
providing the result to a user of the user terminal.

### Claim 2 (depends on 1)

The speech signal processing method of claim 1, wherein the result of the data processing performed on the speech signal corresponding to the general information section, which is received from the server, comprises a result of the data processing performed on the speech signal corresponding to the general information section by the server using a general model.

### Claim 3

A user terminal comprising:
a receiver configured to receive a speech signal;
a communication interface configured to communicate with a server; and
a controller configured to detect a personalized information section including personal information in the speech signal, and perform data processing on the personalized information section of the speech signal by using a personalized model generated based on the personal information,
wherein the communication interface is further configured to receive, from the server:
speech section information about the personalized information section and a general information section, wherein the speech section information includes section marking information that marks a location of the personalized information section in the speech signal, and
a result of data processing performed by the server on the general information section of the speech signal that is different than the personalized information section of the speech signal, and
wherein the controller is further configured to perform data processing based on the speech section information received from the server, wherein the data processing performed by the controller includes performing data processing on the personalized information section corresponding to the section marking information received from the server.

### Claim 4 (depends on 3)

The user terminal of claim 3, wherein the controller is configured to generate speech section information about the personalized information section and the general information section and control the communication interface to transmit the speech section information to the server.

### Claim 5 (depends on 3)

The user terminal of claim 3, wherein a result of the data processing performed on the general information section of the speech signal, which is received from the server, comprises a result of the data processing performed on the general information section of the speech signal by the server using a general model.

### Claim 6

A speech signal processing method of a user terminal, the speech signal processing method comprising:
receiving a speech signal;
receiving, from a server, speech section information about a personalized information section and a general information section, wherein the speech section information includes section marking information that marks a location of the personalized information section in the speech signal;
receiving, from the server, a result of data processing performed by the server on the speech signal by using a general model; and
performing data processing on the speech signal based on the speech section information by using the result of the data processing and a personalized model generated based on personal information, wherein the performing data processing comprises performing data processing on the personalized information section corresponding to the section marking information received from the server.