公开(公告)号：US11445139B2

公开(公告)日：2022-09-13

申请号：US16746213

申请日：2020-01-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sung Yong Kim ,  Kyung-Min Kim ,  Hyuk Oh ,  Hyeok Jong Lee ,  Seung Hoon Jung ,  Woong Joo ,  Hee Sung Chae

IPC: H04N5/378 ,  H04N5/369 ,  H03M1/56

Abstract: An analog-digital converter includes a count code generator to receive a code generation clock signal from a clock signal generator and to output a count code according to the code generation clock signal, a latch to latch the count code, an operating circuit to generate a count value of the count code and to output a digital signal based on the count value, and a transfer controller to transfer the count code from the latch to the operating circuit. The transfer controller determines whether to transfer the count code according to a logic level of a count enable clock signal generated from the clock signal generator.

公开(公告)号：US12125498B2

公开(公告)日：2024-10-22

申请号：US17570557

申请日：2022-01-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seungbeom Ryu ,  Sungjae Park ,  Hyuk Oh ,  Myeungyong Choi ,  Junkwon Choi

IPC: G10L15/00 ,  G06N3/045 ,  G10L15/02 ,  G10L15/16 ,  G10L15/22 ,  G10L25/84 ,  H04R1/08 ,  H04R3/00

CPC classification number: G10L25/84 ,  G06N3/045 ,  G10L15/02 ,  G10L15/16 ,  G10L15/22 ,  H04R1/08 ,  H04R3/00 ,  G10L2015/223 ,  H04R2420/07

Abstract: According to various embodiments, an electronic device may include: a microphone; an audio connector; a wireless communication circuit; a processor operatively connected to the microphone, the audio connector, and the wireless communication circuit; and a memory operatively connected to the processor, wherein the memory may store instructions that, when executed, cause the processor to: receive a first audio signal through the microphone, the audio connector, or the wireless communication circuit, extract audio feature information from the first audio signal, and recognize a speech section in a second audio signal, received after the first audio signal through the microphone, the audio connector, or the wireless communication circuit, using the audio feature information.

公开(公告)号：US11601611B2

公开(公告)日：2023-03-07

申请号：US17523100

申请日：2021-11-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyuk Oh ,  Sungyong Kim ,  Beomsu Yun

IPC: H04N5/376 ,  H04N5/378 ,  H04N5/357 ,  H03K19/20 ,  H03K19/21 ,  H03K3/03 ,  H03M1/56 ,  H03K3/037

Abstract: An image sensor is provided. The image sensor includes a counting code generator configured to generate a counting code, a pixel array including at least one pixel, a correlated double sampling (CDS) circuit configured to compare a magnitude of a pixel signal output from the at least one pixel with a magnitude of a ramp signal and to output a corresponding comparison signal, a pulse generator configured to generate a pulse signal synchronized with a first clock signal based on the comparison signal, and a counter circuit configured to latch a value of the counting code to correspond to a transition of a level of the comparison signal based on the pulse signal.

公开(公告)号：US12096147B2

公开(公告)日：2024-09-17

申请号：US17878285

申请日：2022-08-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sung Yong Kim ,  Kyung-Min Kim ,  Hyuk Oh ,  Hyeok Jong Lee ,  Seung Hoon Jung ,  Woong Joo ,  Hee Sung Chae

IPC: H04N25/75 ,  H04N25/709 ,  H03M1/56

CPC classification number: H04N25/75 ,  H04N25/709 ,  H03M1/56

Abstract: An analog-digital converter includes a count code generator to receive a code generation clock signal from a clock signal generator and to output a count code according to the code generation clock signal, a latch to latch the count code, an operating circuit to generate a count value of the count code and to output a digital signal based on the count value, and a transfer controller to transfer the count code from the latch to the operating circuit. The transfer controller determines whether to transfer the count code according to a logic level of a count enable clock signal generated from the clock signal generator.

公开(公告)号：US20230419979A1

公开(公告)日：2023-12-28

申请号：US18046041

申请日：2022-10-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Myungjong Kim ,  Taeyeon Ki ,  Vijendra Raj Apsingekar ,  Sungjae Park ,  SeungBeom Ryu ,  Hyuk Oh

IPC: G10L21/028 ,  G10L17/06 ,  G10L17/02

CPC classification number: G10L21/028 ,  G10L17/06 ,  G10L17/02

Abstract: A method includes obtaining at least a portion of an audio stream containing speech activity. At least the portion of the audio stream includes multiple segments. The method also includes, for each of the multiple segments, generating an embedding vector that represents the segment. The method further includes, within each of multiple local windows, clustering the embedding vectors into one or more clusters to perform speaker identification. Different clusters correspond to different speakers. The method also includes presenting at least one first sequence of speaker identities based on the speaker identification performed for the local windows. The method further includes, within each of multiple global windows, clustering the embedding vectors into one or more clusters to perform speaker identification. Each global window includes two or more local windows. In addition, the method includes presenting at least one second sequence of speaker identities based on the speaker identification performed for the global windows.

公开(公告)号：US20230368781A1

公开(公告)日：2023-11-16

申请号：US18357594

申请日：2023-07-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Myeungyong Choi ,  Godawari Sudhakar Rao ,  Ranjan Kumar Samal ,  Dasom Kim ,  Hyuk Oh ,  Junkwon Choi ,  Priyadarshini Panemangalore Pai ,  Rahul Kumar ,  Vijeta Gour ,  Sungjae Park ,  Seungbeom Ryu

IPC: G10L15/183 ,  G10L15/05 ,  G10L15/22

CPC classification number: G10L15/183 ,  G10L15/05 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/227

Abstract: Various embodiments of the disclosure relate to an apparatus for supporting automatic speech recognition in an electronic device capable of performing natural language processing, and an operating method thereof. To this end, based on one or more partial texts recognized sequentially from an audio signal input from a microphone, the electronic device may identify an utterance type for the input audio signal. The electronic device may adaptively determine a hangover time, based on the utterance type, and may detect an end of an utterance of the audio signal by applying the determined hangover time.