公开(公告)号：US20250140276A1

公开(公告)日：2025-05-01

申请号：US18928934

申请日：2024-10-28

Applicant: 42dot Inc.

Inventor： Younglo LEE ,  Shukjae CHOI ,  Byeongyeol KIM

IPC: G10L21/0272 ,  G10L13/02

Abstract: Provided are a speaker separation method and device. A speaker separation method for separating an unknown number of speakers from a recorded mixture signal based on an encoder-decoder separation model, including: mapping the mixture signal to an N-dimensional latent representation using an encoder of the encoder-decoder separation model; inputting the N-dimensional latent representation into a separator of the encoder-decoder separation model, wherein the separator includes a dual-path processing block for modeling spectrotemporal patterns, a transformer decoder-based attractor (TDA) calculation module for handling an unknown number of speakers, and a triple-path processing block for modeling inter-speaker relations; performing speaker estimation for speaker separation using the separator to obtain source representations corresponding to the number of separated speakers; and outputting an audio signal for each source representation corresponding to the number of separated speakers using a decoder of the encoder-decoder separation model.

公开(公告)号：US20240377205A1

公开(公告)日：2024-11-14

申请号：US18563938

申请日：2022-05-26

Applicant: 42DOT INC.

Inventor： Ho Sung KIM ,  Jong Bum CHOI ,  Ja Yong LEE

IPC: G01C21/32

Abstract: The disclosure relates to a method and an apparatus for determining a lane centerline network. A lane centerline network determination method according to an embodiment of the disclosure may include obtaining a driving trajectory of a vehicle by using a global positioning system (GPS) mounted on the vehicle, matching a road map with the driving trajectory, generating road feature information considering the driving trajectory based on an image captured by an image capturing device mounted on the vehicle, determining a position of a section node dividing a road on the road map into a plurality of sections based on the road feature information, determining a lane centerline placement for each section by determining a lane centerline for the traveling lane of the vehicle among a plurality of lanes included in the section based on the driving trajectory, and estimating lane centerlines for remaining lanes, determining a final longitudinal position of the section node based on reliability of the section node for each of driving trajectories through which the vehicle has passed a same road repeatedly, determining a section network connection relationship between the section, a previous section, and a next section based on the lane centerline placement for each section, determining a geometry of the lane centerline placement for each section based on reliability of a section link connecting the section nodes to each other, and generating a lane centerline network based on the section network connection relationship and a lane centerline geometry within the section.

公开(公告)号：US20240347049A1

公开(公告)日：2024-10-17

申请号：US18630399

申请日：2024-04-09

Applicant: 42dot Inc.

Inventor： Cheoneum Park ,  Byeongyeol Kim ,  Juae Kim ,  Seohyoeng Jeong

IPC: G10L15/16 ,  G10L15/02 ,  G10L15/06 ,  G10L15/183

CPC classification number: G10L15/16 ,  G10L15/02 ,  G10L15/063 ,  G10L15/183

Abstract: An electronic device includes a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions, in which when the instructions are executed by the processor, the processor is configured to perform a plurality of operations, in which the plurality of operations includes deriving a frequently-asked-questions (FAQ) pair from speech data based on a neural network model trained in an end-to-end manner, in which the neural network model is based on a multi-modal language model (LM) capable of using text data and speech data simultaneously, and contrastive learning is performed on the neural network model based on symmetric loss to shift speech data, which is original data, to text data, which is augmented data

公开(公告)号：US20240223732A1

公开(公告)日：2024-07-04

申请号：US18392447

申请日：2023-12-21

Applicant: 42dot Inc.

Inventor： Dae Sung AHN

IPC: H04N7/18 ,  B60W60/00 ,  H04N7/035

CPC classification number: H04N7/181 ,  B60W60/00 ,  H04N7/035 ,  B60W2420/403

Abstract: Provided is a sensor data processing apparatus and method for autonomous driving. The sensor data processing apparatus for autonomous driving includes a receiver configured to receive a plurality of pieces of sensor data from a plurality of sensors, and a processor configured to obtain information related to the plurality of pieces of sensor data based on a generation time point of the plurality of pieces of sensor data, generate an event indicating an update of a synchronization data group and the plurality of pieces of sensor data based on the information, and transmit synchronized sensor data to a client based on the synchronization data group and the event.

公开(公告)号：US20240060783A1

公开(公告)日：2024-02-22

申请号：US18259409

申请日：2021-12-13

Applicant: 42DOT INC.

Inventor： Seung Hyun JI

IPC: G01C21/34

CPC classification number: G01C21/3446 ,  G01C21/3476 ,  G01C21/3461

Abstract: Disclosed are a method of generating a circular traveling route of a vehicle, a device for generating a circular traveling route of a vehicle, and a recording medium in which a program for executing the method of generating a circular traveling route of a vehicle. The present disclosure is implemented through a process of receiving a request for generating a circular traveling route including information about a list of roads to be circulated, information about the number of repeated travels on the roads to be circulated, information about a preferred traveling direction at a road branch point, and information about a travelable time of the vehicle, grouping the list of roads to be circulated into a plurality of groups, determining a vehicle traveling sequence in the plurality of groups, and generating the circular traveling route of the vehicle on the basis of a vehicle traveling sequence in the determined plurality of groups, the information about the number of repeated travels on the roads to be circulated, and the information about the travelable time of the vehicle, by a route generation device. According to the present disclosure, an optimal circular traveling route for a vehicle, which needs to travel through the entire list of predetermined roads for a specific purpose, such as building a road map, obtaining image data, or performing road maintenance work, may be efficiently generated. In addition, according to the present disclosure, an optimal circular traveling route for a vehicle, which needs to repeatedly travel a list of predetermined roads a certain number of times depending on the purpose of vehicle travel, may be generated.

公开(公告)号：US20240010220A1

公开(公告)日：2024-01-11

申请号：US18347651

申请日：2023-07-06

Applicant: 42DOT INC.

Inventor： Ji Hoon KIM ,  Tae Suk Kim ,  Mo Ran Kim ,  Jung Hee Son ,  Su Ho Kim ,  Yoo Ra Choi ,  Hyun Woo Choi ,  Dong Hoo Kim ,  Zzy Hyun Oh ,  Jae In Chang ,  Da Ye Kwon ,  Hyun Gul Roh ,  Man Gyu Park

IPC: B60W50/14 ,  G07C5/06 ,  G08G1/0968

CPC classification number: B60W50/14 ,  G07C5/06 ,  G08G1/096855 ,  B60W60/001

Abstract: Provided are a method and apparatus for providing a driver interface. The method of providing a driver interface may include, based on a state of a vehicle, determining a main interface configured to display information regarding a vehicle operation service, and generating the determined main interface, wherein the generating of the main interface may include determining a before-starting-work interface as the main interface, in response to the state of the vehicle being switched to a moving-to-workplace state, determining a moving-to-workplace interface as the main interface, and in response to the state of the vehicle being switched to a standby-for-dispatch state, determining a standby-for-dispatch interface as the main interface.

公开(公告)号：US20230386324A1

公开(公告)日：2023-11-30

申请号：US18245219

申请日：2021-09-06

Applicant: 42DOT INC.

Inventor： Seung Hyun JI

IPC: G08G1/01

CPC classification number: G08G1/0112 ,  G08G1/0125 ,  G06Q50/30

Abstract: A method of generating traffic flow statistical data by using wiper motion information of a vehicle, a method of calculating an estimated time of arrival, by using the traffic flow statistical data generated using the wiper motion information of the vehicle, and a management server used therein are provided. The present disclosure is implemented as the management server receives, from a vehicle, vehicle driving information including location information of the vehicle which is driving on a road and wiper motion information of the vehicle, and generates traffic flow statistical data of the road on which the vehicle is driving, based on the vehicle driving information. According to the present disclosure, traffic flow statistical data including weather information in units of roads may be obtained by generating traffic flow statistical data by using vehicle driving information including wiper motion information of a vehicle driving on a road. In addition, according to the present disclosure, an estimated time of arrival may be calculated based on traffic flow statistical data including weather information in units of roads, and thus, the estimated time of arrival that is calculated with very high accuracy, by considering the weather conditions of a road may be provided to a driver.

公开(公告)号：US20230358555A1

公开(公告)日：2023-11-09

申请号：US18044539

申请日：2021-09-08

Applicant: 42DOT INC.

Inventor： Jin Ju YU ,  Ji Hye SYNN

IPC: G01C21/36 ,  G01C21/00

CPC classification number: G01C21/3602 ,  G01C21/3885 ,  G01C21/3667

Abstract: A navigation device in accordance with one embodiment may comprise a communication unit configured to send a driving image of a vehicle captured through at least one camera installed in the vehicle to an external terminal and to receive driving assistance information inputted by a user of the external terminal for the driving image and a control unit configured to output information generated based on the driving assistance information by controlling at least one of a display unit and a speaker.

公开(公告)号：US20220383442A1

公开(公告)日：2022-12-01

申请号：US17818790

申请日：2022-08-10

Applicant: 42DOT INC.

Inventor： Myung Hyun CHO ,  Seung Hyun JI

IPC: G06Q50/30 ,  G01C21/34 ,  G06Q10/02

Abstract: The present disclosure generally relates to a transportation service, and more particularly, a method of recommending a boarding location for a transportation vehicle requested from a passenger over a data communications network, and a management server used therefor. The recommended boarding location allows the passenger to easily board the transportation vehicle by avoiding a pickup location with an obstacle such as a fence. Street view images of the boarding location are also provided to passengers and drivers to help them to quickly find the boarding location.

公开(公告)号：US20240404509A1

公开(公告)日：2024-12-05

申请号：US18678560

申请日：2024-05-30

Applicant: 42dot Inc

Inventor： Hongsun Yang ,  Yooncheol Ju ,  Jihwan Park ,  Hyungyong Kim ,  Shukjae Choi

IPC: G10L13/10 ,  G10L13/047 ,  G10L17/02 ,  G10L25/18

Abstract: Disclosed are a speech generation method and device for performing zero-shot speech generation by using prosody control and random speaker generation. The speech generation method may include: receiving paired text and speaker audio for an ith speaker and an jth utterance from a training set; inputting the speaker audio to a speaker encoder to perform extraction of a speaker identity, and obtaining first embedding representing a representation of the speaker identity; inputting the first embedding to a speaker quantizer and obtaining quantized second embedding; inputting the text and the first embedding to a text prior encoder and obtaining a first intermediate representation; inputting the first intermediate representation and the first embedding to a prosody predictor, adding a prosodic hidden representation to the first intermediate representation, and obtaining a second intermediate representation; inputting the second intermediate representation and the first embedding to an intermediate decoder, and obtaining a final representation; and converting the final representation to a waveform by using the decoder to generate speech.