Zobrazeno 1 - 10
of 811
pro vyhledávání: '"So-Yeon Jun"'
Publikováno v:
Materials, Vol 16, Iss 4, p 1739 (2023)
Thermo-compression bonding (TCB) properties of Cu/SnAg pillar bumps on electroless palladium immersion gold (EPIG) were evaluated in this study. A test chip with Cu/SnAg pillar bumps was bonded on the surface-finished Cu pads with the TCB method. The
Externí odkaz:
https://doaj.org/article/443b55c5a35b4ab592144b1f8d07c633
Autor:
Singla, Karan, Jalalvand, Shahab, Kim, Yeon-Jun, Daniel, Antonio Moreno, Bangalore, Srinivas, Ljolje, Andrej, Stern, Ben
Recent studies have made some progress in refining end-to-end (E2E) speech recognition encoders by applying Connectionist Temporal Classification (CTC) loss to enhance named entity recognition within transcriptions. However, these methods have been c
Externí odkaz:
http://arxiv.org/abs/2311.04753
Publikováno v:
Scientific Data, Vol 11, Iss 1, Pp 1-9 (2024)
Abstract Wasabi (Eutrema japonicum) is a plant belonging to the Brassicaceae family that produces its distinctive pungent taste through allyl isothiocyanate. This study achieved a high-quality chromosome-level genome assembly of the E. japonicum ‘M
Externí odkaz:
https://doaj.org/article/d8070599ca7145bca246445d5e8588a2
Autor:
Yeon Jun Kang, Woorim Song, Su Jeong Lee, Seung Ah Choi, Sihyun Chae, Bo Ruem Yoon, Hee Young Kim, Jung Ho Lee, Chulwoo Kim, Joo-Youn Cho, Hyun Je Kim, Won-Woo Lee
Publikováno v:
Experimental and Molecular Medicine, Vol 56, Iss 8, Pp 1776-1790 (2024)
Abstract Branched-chain amino acids (BCAAs), particularly leucine, are indispensable AAs for immune regulation through metabolic rewiring. However, the molecular mechanism underlying this phenomenon remains unclear. Our investigation revealed that T-
Externí odkaz:
https://doaj.org/article/b4e53a082b53482fac20f35f352142b7
In human-computer conversations, extracting entities such as names, street addresses and email addresses from speech is a challenging task. In this paper, we study the impact of fine-tuning pre-trained speech encoders on extracting spoken entities in
Externí odkaz:
http://arxiv.org/abs/2302.10186
Autor:
Hee Young Kim, Yeon Jun Kang, Dong Hyun Kim, Jiyeon Jang, Su Jeong Lee, Gwanghun Kim, Hee Byung Koh, Ye Eun Ko, Hyun Mu Shin, Hajeong Lee, Tae-Hyun Yoo, Won-Woo Lee
Publikováno v:
eLife, Vol 12 (2024)
Trained immunity is the long-term functional reprogramming of innate immune cells, which results in altered responses toward a secondary challenge. Despite indoxyl sulfate (IS) being a potent stimulus associated with chronic kidney disease (CKD)-rela
Externí odkaz:
https://doaj.org/article/9eb8ae6c169940bc94e3c57d9296c4a5
Autor:
Singla, Karan, Pressel, Daniel, Price, Ryan, Chinnari, Bhargav Srinivas, Kim, Yeon-Jun, Bangalore, Srinivas
In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant architecture can
Externí odkaz:
http://arxiv.org/abs/2204.09227
Autor:
Singla, Karan, Jalalvand, Shahab, Kim, Yeon-Jun, Price, Ryan, Pressel, Daniel, Bangalore, Srinivas
Person name capture from human speech is a difficult task in human-machine conversations. In this paper, we propose a novel approach to capture the person names from the caller utterances in response to the prompt "say and spell your first/last name"
Externí odkaz:
http://arxiv.org/abs/2203.15833
Publikováno v:
In Process Biochemistry October 2024 145:153-162
Autor:
Je Moon Yoon, Chae Yeon Lim, Hoon Noh, Seung Wan Nam, Sung Yeon Jun, Min Ji Kim, Mi Yeon Song, Hyemin Jang, Hee Jin Kim, Sang Won Seo, Duk L. Na, Myung Jin Chung, Don-Il Ham, Kyungsu Kim
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-16 (2024)
Abstract We propose a hybrid technique that employs artificial intelligence (AI)-based segmentation and machine learning classification using multiple features extracted from the foveal avascular zone (FAZ)—a retinal biomarker for Alzheimer’s dis
Externí odkaz:
https://doaj.org/article/46c628df1fa44558a812bce2ece00128