조재진 교수

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of requiring more data compared to conventional DNN-HMM systems. In this work, we attempt to use data from 10 BABEL languages to build a multilingual seq2seq model as a prior model, and then port them towards 4 other BABEL languages using transfer learning approach.

In this paper, we propose to improve emotion recognition by combining acoustic information and conversation transcripts.On the one hand, a LSTM network was used to detect emotion from acoustic features like f0, shimmer, jitter, MFCC, etc.On the other hand, a multi-resolution CNN was used to detect emotion from word sequences.This CNN consists of several parallel convolutions with different kernel sizes to exploit contextual information at different levels.A temporal pooling layer aggregates the

The periodontal ligament-derived mesenchymal stem cell is regarded as a source of adult stem cells due to its multipotency. However, the proof of chondrogenic potential of the cells is scarce. Therefore, we investigated the chondrogenic differentiation capacity of periodontal ligament derived mesenchymal stem cells induced by transforming growth factor (TGF)-β3 and bone morphogenetic protein (BMP)-6. After isolation of periodontal ligament stem cells (PDLSCs) from human periodontal ligament, the

Recently, the selective laser melting (SLM) method of manufacturing three dimensional (3D) dental prosthetics by applying a laser to metal powder has been widely used in the field of dentistry. This study investigated human adipose derived stem cell (hADSC) behavior on a 3D printed cobalt-chrome (Co-Cr) alloy and its surface characteristics and compared them those of a nickel-chrome (Ni-Cr) alloy. Alloys were divided into four groups according to the material and manufacturing methods. Co-Cr dis

Toll-like receptors (TLRs) are usually expressed on immune cells such as macrophages, dendritic cells, mast cells, as well as on eosinophils and some epithelial cells. They play a central role in the recognition of harmful molecules that belong to invading microorganisms or internal damaged tissues, which lead to inflammation. Among the hallmarks of cancer, there is immune evasion and inflammation. Summing this with the discovery that a majority of cancers also seem to express TLRs, made researc

PURPOSE: To accurately separate water and fat signals for bipolar multi-echo gradient-recalled echo sequence using a convolutional neural network (CNN). METHODS: A CNN architecture was designed and trained using the relationship between multi-echo images from the bipolar multi-echo gradient-recalled echo sequence and artifact-free water-fat-separated images. The artifact-free water-fat-separated images for training the CNN were obtained from multiple signals with different TEs by using iterative

We discovered a novel small-molecule modulator 5{i,2} that can specifically induce the chondrogenic differentiation of human bone marrow-derived mesenchymal stem cells (hBM-MSCs). Based on our biochemical and histological studies, 5{i,2} showed more of a directed differentiation of MSCs to chondrocyte balls compared to TGF-β3.

The dynamics of uterine endometrium is important for successful establishment and maintenance of embryonic implantation and development, along with extensive cell differentiation and proliferation. The tissue event is precisely and complicatedly regulated as several signaling pathways are involved including two main hormones, estrogen and progesterone signaling. We previously showed a novel signaling molecule, Serine/threonine protein kinase 3/4 (STK3/4), which is responded to hormone in the mou

Abstract Purpose Volumetric, high‐resolution, quantitative mapping of brain‐tissue relaxation properties is hindered by long acquisition times and SNR challenges. This study combines time‐efficient wave–controlled aliasing in parallel imaging (wave‐CAIPI) readouts with the 3D quantification using an interleaved Look‐Locker acquisition sequence with a T 2 preparation pulse (3D‐QALAS), enabling full‐brain quantitative T 1 , T 2 , and proton density (PD) maps at 1.15‐mm 3 isotropic voxels in 3 min.

A recently introduced model-based deep learning (MoDL) technique successfully incorporates convolutional neural network (CNN)-based regularizers into physics-based parallel imaging reconstruction using a small number of network parameters. Wave-controlled aliasing in parallel imaging (CAIPI) is an emerging parallel imaging method that accelerates imaging acquisition by employing sinusoidal gradients in the phase- and slice/partition-encoding directions during the readout to take better advantage

Endothelin-1 (ET-1) induces contraction, proliferation, and collagen synthesis of activated hepatic stellate cells and is a potent mediator of portal hypertension. Endothelin-converting enzyme-1 (ECE-1) generates ET-1 from the inactive precursor big-endothelin-1. The cellular distribution and activity of ECE-1 in the liver is unknown. Hepatic fibrogenesis was induced in rats by CCl₄ administration and secondary biliary cirrhosis after 6 weeks of complete bile duct occlusion (BDO). The

This technical report describes Johns Hopkins University speaker recognition system submitted to Voxceleb Speaker Recognition Challenge 2021 Track 3: Self-supervised speaker verification (closed). Our overall training process is similar to the proposed one from the first place team in the last year's VoxSRC2020 challenge. The main difference is a recently proposed non-contrastive self-supervised method in computer vision (CV), distillation with no labels (DINO), is used to train our initial mode

Abstract Canine mesenchymal stem cells (cMSCs) are gaining popularity in the veterinary field as a regenerative therapy. But, their limited culture lifespan makes it an obstacle for preclinical investigation and therapeutic use. In this study, primary canine adipose tissue‐derived MSCs (PCAT‐MSCs) were isolated from adipose tissue and were transfected with the SV40‐T retrovirus resulting in a life‐extended immortalized canine adipose tissue‐derived MSCs (ICAT‐MSCs). A comparison was made through

The umbilical cord contains mucinous connective tissue, called Wharton's jelly. It consists of stromal cells, collagen fibers, and amorphous ground substances composed of proteoglycan. Recently, these stromal cells have been redefined as a new cell therapy source, named human umbilical cord-derived mesenchymal stromal cells (hUCMSCs). However, there are few studies on the ultrastructural features and immune-phenotypic characteristics of isolated hUCMSCs and comparisons with the cells found in or