Zobrazeno 1 - 10
of 363
pro vyhledávání: '"Kim, Chanwoo"'
Autor:
Lee, Yongjoon, Kim, Chanwoo
Speech Super-Resolution (SSR) is a task of enhancing low-resolution speech signals by restoring missing high-frequency components. Conventional approaches typically reconstruct log-mel features, followed by a vocoder that generates high-resolution sp
Externí odkaz:
http://arxiv.org/abs/2409.09337
As diffusion models are deployed in real-world settings, data attribution is needed to ensure fair acknowledgment for contributors of high-quality training data and to identify sources of harmful content. Previous work focuses on identifying individu
Externí odkaz:
http://arxiv.org/abs/2407.03153
Autor:
Eom, SooHwan, Yoon, Eunseop, Yoon, Hee Suk, Kim, Chanwoo, Hasegawa-Johnson, Mark, Yoo, Chang D.
In Automatic Speech Recognition (ASR) systems, a recurring obstacle is the generation of narrowly focused output distributions. This phenomenon emerges as a side effect of Connectionist Temporal Classification (CTC), a robust sequence learning tool t
Externí odkaz:
http://arxiv.org/abs/2403.11578
Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and can be intractable for large datasets. These methods require efficient approximations, and learning a ne
Externí odkaz:
http://arxiv.org/abs/2401.15866
Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the le
Externí odkaz:
http://arxiv.org/abs/2401.10465
Autor:
Adiga, Nagaraj, Park, Jinhwan, Kumar, Chintigari Shiva, Singh, Shatrughan, Lee, Kyungmin, Kim, Chanwoo, Gowda, Dhananjaya
Recently, the cascaded two-pass architecture has emerged as a strong contender for on-device automatic speech recognition (ASR). A cascade of causal and shallow non-causal encoders coupled with a shared decoder enables operation in both streaming and
Externí odkaz:
http://arxiv.org/abs/2312.09842
Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy
Autor:
Kim, Junsu, Hong, Sumin, Kim, Chanwoo, Kim, Jihyeon, Tiruneh, Yihalem Yimolal, On, Jeongwan, Song, Jihyun, Choi, Sunhwa, Baek, Seungryul
Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability to object
Externí odkaz:
http://arxiv.org/abs/2312.09139
Autor:
Jin, Jiaxin, Kim, Chanwoo
Motivated by the stellar wind ejected from the upper atmosphere (Corona) of a star, we explore a boundary problem of the two-species nonlinear relativistic Vlasov-Poisson systems in the 3D half space in the presence of a constant vertical magnetic fi
Externí odkaz:
http://arxiv.org/abs/2310.09865
Autor:
Jin, Jiaxin, Kim, Chanwoo
We study linear two-half dimensional Vlasov equations under the logarithmic gravity potential in the half space of diffuse reflection boundary. We prove decay-in-time of the exponential moments with a polynomial rate, which depends on the base logari
Externí odkaz:
http://arxiv.org/abs/2310.07947
Autor:
Bae, Jae-Sung, Lee, Joun Yeop, Lee, Ji-Hyun, Mun, Seongkyu, Kang, Taehwa, Cho, Hoon-Young, Kim, Chanwoo
Previous works in zero-shot text-to-speech (ZS-TTS) have attempted to enhance its systems by enlarging the training data through crowd-sourcing or augmenting existing speech data. However, the use of low-quality data has led to a decline in the overa
Externí odkaz:
http://arxiv.org/abs/2310.03538