Zobrazeno 1 - 10
of 386
pro vyhledávání: '"Han, Sung Won"'
Expressive Text-to-Speech (TTS) using reference speech has been studied extensively to synthesize natural speech, but there are limitations to obtaining well-represented styles and improving model generalization ability. In this study, we present Dif
Externí odkaz:
http://arxiv.org/abs/2406.19135
In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite their high performance, these approaches frequently involve complex traini
Externí odkaz:
http://arxiv.org/abs/2405.20610
Autor:
Kim, Taehyeong, Han, Sung Won, Kang, Minji, Lee, Se Ha, Kim, Jong-Ho, Joo, Hyung Joon, Sohn, Jang Wook
Publikováno v:
JMIR Medical Informatics, Vol 9, Iss 2, p e25530 (2021)
BackgroundExisting bacterial culture test results for infectious diseases are written in unrefined text, resulting in many problems, including typographical errors and stop words. Effective spelling correction processes are needed to ensure the accur
Externí odkaz:
https://doaj.org/article/2569d34f84e4477cb727f7bf027bc454
Sound event localization and detection (SELD) combines the identification of sound events with the corresponding directions of arrival (DOA). Recently, event-oriented track output formats have been adopted to solve this problem; however, they still h
Externí odkaz:
http://arxiv.org/abs/2303.15703
Voice Conversion (VC) must be achieved while maintaining the content of the source speech and representing the characteristics of the target speaker. The existing methods do not simultaneously satisfy the above two aspects of VC, and their conversion
Externí odkaz:
http://arxiv.org/abs/2303.09057
While point cloud semantic segmentation is a significant task in 3D scene understanding, this task demands a time-consuming process of fully annotating labels. To address this problem, recent studies adopt a weakly supervised learning approach under
Externí odkaz:
http://arxiv.org/abs/2210.01558
Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation studies on speec
Externí odkaz:
http://arxiv.org/abs/2208.10367
In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency. Recently, dual-path models have been adopted to represent long sequential features, but they still have limited representatio
Externí odkaz:
http://arxiv.org/abs/2203.02181
Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance. To achieve satisfactory performance, the methods employ refined edge inform
Externí odkaz:
http://arxiv.org/abs/2112.07380
Autor:
Han, Sung Won
For the last several decades, sequential change point problems have been studied in both the theoretical area (sequential analysis) and the application area (industrial SPC). In the conventional application, the baseline process is assumed to be stat
Externí odkaz:
http://hdl.handle.net/1853/34828