Abstract: A method for fabricating a semiconductor device includes: forming a mold structure including a mold layer and a supporter layer over a semiconductor substrate; forming an opening penetrating the mold structure; forming a protective layer on a bottom surface and a sidewall of the opening; forming a lower electrode over the protective layer; selectively etching the supporter layer to form a supporter that supports the lower electrode; removing the mold layer to define a non-exposed portion and an exposed portion of an outer wall of the protective layer; and selectively trimming the exposed portion of the protective layer to form a protective layer pattern between the supporter and the lower electrode.

Abstract: Disclosed are a method and an apparatus for detecting a voice end point by using acoustic and language modeling information to accomplish strong voice recognition. A voice end point detection method according to an embodiment may comprise the steps of: inputting an acoustic feature vector sequence extracted from a microphone input signal into an acoustic embedding extraction unit, a phonemic embedding extraction unit, and a decoder embedding extraction unit, which are based on a recurrent neural network (RNN); combining acoustic embedding, phonemic embedding, and decoder embedding to configure a feature vector by the acoustic embedding extraction unit, the phonemic embedding extraction unit, and the decoder embedding extraction unit; and inputting the combined feature vector into a deep neural network (DNN)-based classifier to detect a voice end point.

Abstract: A voice signal estimation apparatus using attention mechanism according to an embodiment may comprise a microphone encoder that receives a microphone input signal including an echo signal, and a user's voice signal, converts the microphone input signal into first input information, and outputs the converted first input information, a far-end signal encoder that receives a far-end signal, converts the far-end signal into second input information, and outputs the converted second input information, an attention unit outputting weight information by applying an attention mechanism to the first input information and the second input information, a pre-learned first artificial neural network with third input information, which is the sum information of the weight information and the second input information, as input information, and with first output information including mask information for estimating the voice signal from the second input information as output information and a voice signal estimator outputtin

Abstract: Provided are methods and apparatuses for improving compression efficiency in directional intra-prediction. A video encoding apparatus, which does not need to record intra mode information, includes a mode selector that selects one from among a plurality of intra modes on the basis of a directionality of at least one neighboring block that has already been reconstructed before a current block is reconstructed, an intra predictor that obtains a prediction block of the current block from the at least one neighboring block according to the directionality of the selected mode, and obtains a residual block by subtracting the prediction block from the current block, and a unit for encoding the obtained residual block.

Abstract: [SUMMARY] An integrated noise and echo signal removal device using parallel deep neural network according to an embodiment comprises a microphone encoder that receives a microphone input signal including an echo signal, and a speaker's voice signal, converts the microphone input signal into first input information, and outputs the converted first input information, a far-end signal encoder that receives a far-end signal, converts the far-end signal into second input information, and outputs the converted second input information, a pre-learned second artificial neural network having a third input information, which is the sum of the first input information and the second input information, as input information, and having an estimated echo signal obtained by estimating the echo signal from the second input information as output information, a pre-learned third artificial neural network having the third input information as input information and having an estimated noise signal obtained by estimating the noise

Abstract: Disclosed herein are compounds of Formula (I), or pharmaceutically acceptable salts thereof, that are inhibitors of Polo Like Kinase 4 (PLK4). Also disclosed herein are pharmaceutical compositions comprising the compounds of Formula (I), or pharmaceutically acceptable salts thereof, and one or more pharmaceutically acceptable excipients. Further disclosed herein are methods of treating cancer in a subject in need thereof, comprising administering to the subject an amount of a compound of Formula (I), or a pharmaceutically acceptable salt thereof.

Abstract: A multi-channel based noise and echo signal integrated cancellation device using deep neural network according to an embodiment comprises a plurality of microphone encoders that receive a plurality of microphone input signals including an echo signal, and a speaker's voice signal, convert the plurality of microphone input signals into a plurality of conversion information, and output the plurality of conversion information, a channel convert unit for compressing the plurality of pieces of conversion information and converting them into first input information having a size of a single channel and outputting the converted first input information, a far-end signal encoder that receives a far-end signal, converts the far-end signal into second input information, and outputs the converted second input information, an attention unit outputting weight information by applying an attention mechanism to the first input information and the second input information, a pre-learned first artificial neural network taking t

Abstract: Provided is a ceiling storage system capable of correcting a working position and constantly checking stability of a structure by detecting an amount of change in a facility. According to the ceiling storage system, a transport vehicle moves to an upper portion of a first storage area of a plurality of storage areas in a state of gripping an article, and the transport vehicle measures a first distance value between the transport vehicle and the first storage area using a distance sensor and measures a relative position value between the transport vehicle and the first storage area using a vision sensor, before unloading the article from the first storage area.

Abstract: According to an aspect, method for synthesizing multi-speaker speech using an artificial neural network comprises generating and storing a speech learning model for a plurality of users by subjecting a synthetic artificial neural network of a speech synthesis model to learning, based on speech data of the plurality of users, generating speaker vectors for a new user who has not been learned and the plurality of users who have already been learned by using a speaker recognition model, determining a speaker vector having the most similar relationship with the speaker vector of the new user according to preset criteria out of the speaker vectors of the plurality of users who have already been learned, and generating and learning a speaker embedding of the new user by subjecting the synthetic artificial neural network of the speech synthesis model to learning, by using a value of a speaker embedding of a user for the determined speaker vector as an initial value and based on speaker data of the new user.

Abstract: Disclosed herein are compounds of Formula (I), or pharmaceutically acceptable salts thereof, that are inhibitors of Polo Like Kinase 4 (PLK4). Also disclosed herein are pharmaceutical compositions comprising the compounds of Formula (I), or pharmaceutically acceptable salts thereof, and one or more pharmaceutically acceptable excipients. Further disclosed herein are methods of treating cancer in a subject in need thereof, comprising administering to the subject an amount of a compound of Formula (I), or a pharmaceutically acceptable salt thereof.

Abstract: The present invention relates to a display apparatus that allows a compensated data voltage to be supplied to each pixel by compensating for the data voltage so as to prevent burn-in from occurring in a display panel, a method for compensating a data signal thereof, and a method for generating a deep learning-based compensation model. To implement same, the present invention provides the display apparatus comprising a timing controller having mounted therein the compensation model generated by learning, in a deep learning method, the temperature, time, average brightness, and data voltage for each pixel. Accordingly, the present invention has an effect of preventing burn-in from occurring in each pixel by supplying each pixel with the compensated data voltage generated via the compensation model.

Abstract: Presented are a combined learning method and device using a transformed loss function and feature enhancement based on a deep neural network for speaker recognition that is robust to a noisy environment.

Abstract: Provided is a ceiling storage system for increasing storage capacity by utilizing a ceiling space inside a fab. The ceiling storage system includes a first overhead rack including a plurality of storage positions for storing a plurality of articles; first and second support rails above the first overhead rack and extending in one direction; a first driving rail above the first overhead rack and in parallel with the first and second support rails; a second driving rail coupled to the first and second support rails and the first driving rail and moving along the first and second support rails and the first driving rail; and a first transport vehicle including a carriage coupled to the second driving rail and moving along the second driving rail, and a hoist and a hand unit installed on the carriage and for loading and unloading the articles to and from the first overhead rack.

Abstract: A variable displacement swash plate type compressor which smoothly supplies oil contained in a refrigerant inside a crank-case to a drive shaft seal region of a front housing, and thus the frictional heat temperature between the drive shaft and a sealing member can be reduced, leakage of refrigerant and pressure is prevented, and durability can be improved.

Abstract: Disclosed is a transformer-based voice recognition technology using an improved voice as a conditioning feature. A voice recognition method performed by a voice recognition system may include inputting, to a voice recognition model, clean voice data estimated by a voice improvement model and voice data including noise and performing voice recognition based on the estimated clean voice data and the voice data including the noise by using the voice recognition model. The voice recognition model may be trained to perform the voice recognition robust against noise through a combination of a voice feature of the voice data including the noise and a voice feature of the estimated clean voice data by using the estimated clean voice data as a conditioning feature.

Abstract: Disclosed herein are compounds of Formula (I), or pharmaceutically acceptable salts thereof, that are inhibitors of Polo Like Kinase 4 (PLK4). Also disclosed herein are pharmaceutical compositions comprising the compounds of Formula (I), or pharmaceutically acceptable salts thereof, and one or more pharmaceutically acceptable excipients. Further disclosed herein are methods of treating cancer in a subject in need thereof, comprising administering to the subject an amount of a compound of Formula (I), or a pharmaceutically acceptable salt thereof.

Abstract: A deep learning-based coloring system includes a memory network configured to provide a color feature in response to a specific query and a coloring network configured to perform coloring, based on the color feature generated by the memory network. The memory network includes: a query generation unit configured to generate a query; a neighbor calculation unit configured to calculate k-nearest neighbors, based on similarities between the query and key memory values; a color feature determination unit configured to generate color features for indicating color information stored in the key memory; a threshold triplet loss calculation unit configured to calculate a threshold triplet loss, based on a comparison between a threshold and a distance between the color features; and a memory update unit configured to update a memory, based on whether a distance between a top value and a value of a newly input query is within the threshold.

Abstract: Disclosed are a system and method for automating the design of a sound source separation deep learning model. A method of automating a design of a sound source separation deep learning model, which is performed by a design automation system, may include automatically searching for a combination of hyper parameters of a separation model constructed in a sound source separation deep learning model by using a neural architecture search (NAS) algorithm and reconstructing the sound source separation deep learning model based on the retrieved combination of the hyper parameters of the separation model.

Abstract: A method of automatically creating an artificial intelligence (AI) diagnostic model for diagnosing an abnormal state of a vehicle includes: acquiring noise and vibration data measured by a sensor of the vehicle as input data, processing the input data, searching and selecting an architecture of the AI diagnostic model based on the processed input data, and providing the AI diagnostic model to diagnose the abnormal state of the vehicle, where an efficient neural architecture search (ENAS) is applied to update the AI diagnostic model and a parameter configuring the AI diagnostic model, the ENAS sharing the parameter with the updated AI diagnostic model.

Abstract: A method for rearranging webtoon content includes obtaining first content including a plurality of image cuts including a plurality of elements, extracting the plurality of elements included in the first content, generating a plurality of image cut layers by reconstructing the extracted plurality of elements, and generating second content by arranging the generated plurality of image cut layers in a designated arrangement.