公开(公告)号：US20230245647A1

公开(公告)日：2023-08-03

申请号：US18107652

申请日：2023-02-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gunu JHO ,  Hoseon SHIN

IPC: G10L15/06 ,  G10L15/187 ,  G10L15/22

CPC classification number: G10L15/063 ,  G10L15/187 ,  G10L15/22 ,  G10L2015/0635 ,  G10L2015/223 ,  G10L15/30

Abstract: An example electronic device may include a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions. When the instructions are executed by the processor, the processor may be configured to create an automatic speech recognition (ASR) language model including information about a plurality of candidate transliterations for a variously utterable text, based on a context of a user indicating a situation of the user, a basic language model, or a customized language model and update the customized language model in response to an utterance of the user matching one of the plurality of candidate transliterations.

公开(公告)号：US20220286757A1

公开(公告)日：2022-09-08

申请号：US17686901

申请日：2022-03-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kyounggu WOO ,  Hoseon SHIN ,  Chulmin LEE ,  Youngwoo LEE

IPC: H04N21/81 ,  G11B27/031 ,  G10L15/26 ,  G06F9/451

Abstract: An electronic device according to various embodiments includes: a microphone, a memory, and a processor, wherein the memory stores instructions which, when executed, cause the processor to: control the electronic device to copy a signal acquired from the microphone, record a first signal, and perform voice recognition on a second signal based on a recording operation using the microphone being executed, determine an editing section including unnecessary information in the first signal based on a voice recognition result for the second signal, and generate recording data by editing the unnecessary information included in the determined editing section in the first signal.

公开(公告)号：US20240304190A1

公开(公告)日：2024-09-12

申请号：US18663779

申请日：2024-05-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Taewoo LEE ,  Minseok KWON ,  Kyungtae KIM ,  Gajin SONG ,  Hoseon SHIN ,  Jungin LEE ,  Seokyeong JUNG

IPC: G10L17/04 ,  G10L15/02

CPC classification number: G10L17/04 ,  G10L15/02

Abstract: An electronic device configured to perform speaker verification on a voice input to determine whether the voice input matches a voice of an enrolled speaker, based on determining that the voice input does not match the voice of the enrolled speaker, perform first speech recognition on the voice input based on a first automatic speech recognition (ASR) model, and based on determining that the voice input matches the voice of the enrolled speaker, perform second speech recognition on the voice input based on a sequence summarizing neural network (SSN) and a second ASR model.

公开(公告)号：US20240161738A1

公开(公告)日：2024-05-16

申请号：US18510086

申请日：2023-11-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： JeongYeol KIM ,  Kyungtae KIM ,  Gajin SONG ,  Hoseon SHIN

IPC: G10L15/18 ,  G10L15/183

CPC classification number: G10L15/1815 ,  G10L15/183

Abstract: An electronic device includes a microphone, a memory and at least one processor. The at least one processor is configured to acquire utterance data corresponding to a voice of a user through the microphone, determine an intent and provide content to the user based on the intent. When intent determination fails, then one or more models are updated using text obtained from the utterance data. The intent determination may fail when there is no verb (predicate) in the user utterance. The models are updated by searching for named entities and determining domains to be used for the model updates. The domains are determined based on categories. The categories are found using a named entity search (NES). Examples of categories are music artists, music albums, movie titles, TV program channels, video clip channels, radio programs, and podcast titles.

公开(公告)号：US20240144547A1

公开(公告)日：2024-05-02

申请号：US18359287

申请日：2023-07-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Woojung HAN ,  Gajin SONG ,  Hoseon SHIN ,  Dongchoon HWANG ,  Kyungtae KIM ,  Kanghee LEE

IPC: G06T11/00 ,  G06V20/50

CPC classification number: G06T11/00 ,  G06V20/50 ,  G06V2201/10

Abstract: A processor is configured to identify a specified event based on data output from one or more sensors. The processor is configured to, in response to identifying occurrence of the specified event, transmit, to an external electronic device connected via a communication circuit, a first signal requesting information associated with both the specified event and a virtual space provided by the external electronic device. The processor is configured to provide, by controlling the display based on receiving a second signal corresponding to the first signal from the external electronic device, information included in the second signal in a state that is executable by a second application different from the first application for displaying the virtual space.

公开(公告)号：US20240087220A1

公开(公告)日：2024-03-14

申请号：US18449961

申请日：2023-08-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kanghee LEE ,  Gajin SONG ,  Dongchoon HWANG ,  Kyungtae KIM ,  Hoseon SHIN ,  Woojung HAN

IPC: G06T17/00 ,  G06F3/04815 ,  G06F3/14 ,  G06F21/62

CPC classification number: G06T17/00 ,  G06F3/04815 ,  G06F3/14 ,  G06F21/6218 ,  G06F2221/2141

Abstract: A server for providing content shared to an object is provided. The server is configured to establish communication between a first electronic device of a user and a second electronic device of another user and provide, to the first electronic device and the second electronic device, a virtual space and an object in the virtual space. The server selects, based on an input of the user, at least one content shared to the object in the virtual space by the other user of the second electronic device entering the same virtual space as the first electronic device. The server activates the object to identically output the selected content to at least one electronic device entering the virtual space. Based on the second electronic device leaving the virtual space, the server stops providing the content shared by the other user.

公开(公告)号：US20240071363A1

公开(公告)日：2024-02-29

申请号：US18372898

申请日：2023-09-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jisun CHOI ,  Seolhee KIM ,  Kyungtae KIM ,  Hoseon SHIN

IPC: G10L13/02 ,  G10L25/00

CPC classification number: G10L13/02 ,  G10L25/00

Abstract: Disclosed are an electronic device and a method of controlling a text-to-speech (TTS) rate. An electronic device may include a processor, and a memory configured to store instructions to be executed by the processor. The processor may receive a voice signal of a user. The processor may calculate a speaking rate of the voice signal based on the voice signal. The processor may generate an output text to be output to the user based on the voice signal. The processor may determine a TTS rate of the output text based on the speaking rate. The processor may convert the output text into voice data based on the TTS rate and output the voice data.

公开(公告)号：US20230129555A1

公开(公告)日：2023-04-27

申请号：US17972916

申请日：2022-10-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Cheol RYU ,  Joohwan KIM ,  Gajin SONG ,  Hoseon SHIN ,  Kihyuck RYU ,  Seunghyo CHUN

IPC: G10L15/22 ,  H04L9/40 ,  G10L17/00

Abstract: Disclosed is an electronic device including a microphone, a communication circuit, a memory, and a processor operatively connected to the microphone, the communication circuit, and the memory. The memory may store one or more instructions that, when executed, cause the processor to: receive an utterance through the microphone, execute a function to detect a signal received from at least one external electronic device based on the utterance, identify the at least one external electronic device based on the signal, determine an external electronic device to be registered from among the at least one external electronic device based on device information included in the signal and device information extracted from the utterance, authenticate the external electronic device to be registered, using voiceprint analysis on the utterance, and register the authenticated external electronic device in an external server.

公开(公告)号：US20220277758A1

公开(公告)日：2022-09-01

申请号：US17664025

申请日：2022-05-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoseon SHIN ,  Chulmin LEE ,  Changwoo HAN

IPC: G10L21/0232 ,  G10L25/84

Abstract: An electronic device includes an input device, a processor, and a memory The processor is configured to identify a first filter value of a first signal received from the input device. The processor is configured to receive a second signal after a first time elapses after the first signal is received. The processor is configured to receive a third signal after a second time elapses after the second signal is received. The processor is configured to compare a level of the second signal with a first threshold value for each of the at least one unit section of the second signal. The processor is configured to identify first information indicating that abnormal noise is present in a first section of the second signal. The processor is configured to perform filtering on the third signal based on the first filter value of the first signal according to the first information.

公开(公告)号：US20220270617A1

公开(公告)日：2022-08-25

申请号：US17572095

申请日：2022-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoseon SHIN ,  Chulmin LEE

IPC: G10L17/18 ,  G10L25/78 ,  G10L25/63

Abstract: An electronic device and method are provided. The method includes identifying a speech section of a user and a speech section of a neighbor in a received audio signal, identifying a user utterance in the speech section of the user and a neighbor answer to the user utterance in the speech section of the neighbor, obtaining preference information associated with the user utterance, giving a first reliability to the neighbor answer and a second reliability to an agent answer of an artificial intelligence agent generated in response to the user utterance, based on the preference information, not responding to the user utterance when the second reliability is lower than the first reliability, and outputting the agent answer when the second reliability is equal to or higher than the first reliability.