http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Soosung Yoon (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
Fundamental study on electron beam weld sections and strengths using AA6061-T6 aluminum alloy plate
Soosung Kim,정용진,JONG MAN PARK,Yoon Sang Lee 대한기계학회 2013 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.27 No.10
This study was carried out to establish an electron beam welding process for a nuclear fuel plate assembly fabrication. A preliminary investigation for plate fuel fabrication was conducted with a consideration of weld performance using AA6061-T6 aluminum alloy made by the electron beam welding process. The optimum welding parameters for the fuel plate assembly were obtained in terms of the accelerating voltage, beam current and welding time. The soundness of the weld region between the side plate and the end fitting for the fuel plate assembly was proven by the intact of the weld metal on the fractured surfaces. The integrity of the welds by the electron beam welding process was also confirmed by the results of the tensile test, an examination of the cross sections and the fracture surfaces of the welded specimens.
-
Adversarial Domain Adaptation for Noisy Speech Emotion Recognition
Sunyoung Cho,Soosung Yoon,Hyunseung Song 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Speech Emotion Recognition (SER) has achieved many great results with deep learning techniques. However, noise discrepancy is still a challenging task due to the distribution shift between training and test data. In this paper, we present a novel approach based on unsupervised domain adaptation method to alleviate the distribution shift problem for noisy SER. Specifically, we apply an adversarial domain adaptation with bridge mechanism to model an intermediate domain for knowledge transfer. We construct a bridge layer by exploiting speech denoising approach to extract the domain-specific noise representation. Experimental results show that our method provides average improvements of 2.29% and 3.88% in weighted and unweighted accuracies over the baseline for SER with various noise settings.
-
Target Speaker Recognition in The Cocktail Party
Dae-Jin Jung,Sunyoung Cho,Tae Yoon Chun,Soosung Yoon 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
The arise of the deep learning techniques has accelerated the advance of the speaker recognition and the increase in personalized devices weighted the importance of the target speaker recognition (TSR). More precisely, it is important to recognize the target speaker correctly even when a variety of speakers utter at the same time. In this paper the TSR methods are proposed and evaluated in the multi-speaker environments: (1) TSE is performed before the speaker recognition on the input voice; (2) results from (1) and the speaker recognition are fused. Among the proposed methods, the latter method showed the better results; more precisely, the fusion based method showed the relative performance improvements of at least 11% from the ordinary speaker recognition system.
-
Hieu Tran, Van,Park, Hyunjun,Park, Jaekyung,Kwon, Young-Do,Kang, Shinwoo,Ho Jung, Jae,Chang, Keun-A,Chul Lee, Byung,Lee, Sang-Yoon,Kang, Soosung,Kim, Hee-Kwon Elsevier 2019 Bioorganic & medicinal chemistry Vol.27 No.18
<P><B>Abstract</B></P> <P>Translocator protein (TSPO) expression is closely related with neuroinflammation and neuronal damage which might cause several central nervous system diseases. Herein, a series of TSPO ligands (<B>11a</B>–<B>c</B> and <B>13a</B>–<B>d</B>) with a 2-phenylpyrazolo[1,5-<I>a</I>]pyrimidin-3-yl acetamide structure were prepared and evaluated via an <I>in vitro</I> binding assay. Most of the novel ligands exhibited a nano-molar affinity for TSPO, which was better than that of DPA-714. Particularly, <B>11a</B> exhibited a subnano-molar TSPO binding affinity with suitable lipophilicity for <I>in vivo</I> brain studies. After radiolabeling with fluorine-18, [<SUP>18</SUP>F]<B>11a</B> was used for a dynamic positron emission tomography (PET) study in a rat LPS-induced neuroinflammation model; the inflammatory lesion was clearly visualized with a superior target-to-background ratio compared to [<SUP>18</SUP>F]DPA-714. An immunohistochemical examination of the dissected brains confirmed that the uptake location of [<SUP>18</SUP>F]<B>11a</B> in the PET study was consistent with a positively activated microglia region. This study proved that [<SUP>18</SUP>F]<B>11a</B> could be employed as a potential PET tracer for detecting neuroinflammation and could give possibility for diagnosis of other diseases, such as cancers related with TSPO expression.</P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
