Zobrazeno 1 - 10
of 3 743
pro vyhledávání: '"Kang Hong"'
Autor:
Li, Yikun, Zhang, Ting, Widyasari, Ratnadira, Tun, Yan Naing, Nguyen, Huu Hung, Bui, Tan, Irsan, Ivana Clairine, Cheng, Yiran, Lan, Xiang, Ang, Han Wei, Liauw, Frank, Weyssow, Martin, Kang, Hong Jin, Ouh, Eng Lieh, Shar, Lwin Khin, Lo, David
Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directly from GitHub, are essential for training machine learning models to d
Externí odkaz:
http://arxiv.org/abs/2411.17274
U-Net is currently the most widely used architecture for medical image segmentation. Benefiting from its unique encoder-decoder architecture and skip connections, it can effectively extract features from input images to segment target regions. The co
Externí odkaz:
http://arxiv.org/abs/2409.14676
We present a comprehensive dataset of Java vulnerability-fixing commits (VFCs) to advance research in Java vulnerability analysis. Our dataset, derived from thousands of open-source Java projects on GitHub, comprises two variants: JavaVFC and JavaVFC
Externí odkaz:
http://arxiv.org/abs/2409.05576
As Deep Neural Networks (DNNs) rapidly advance in various fields, including speech verification, they typically involve high computational costs and substantial memory consumption, which can be challenging to manage on mobile systems. Quantization of
Externí odkaz:
http://arxiv.org/abs/2407.08991
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator
Autor:
Chung, Woo-Jin, Kang, Hong-Goo
We present a novel speaker-independent acoustic-to-articulatory inversion (AAI) model, overcoming the limitations observed in conventional AAI models that rely on acoustic features derived from restricted datasets. To address these challenges, we lev
Externí odkaz:
http://arxiv.org/abs/2406.17329
This paper introduces a novel task in generative speech processing, Acoustic Scene Transfer (AST), which aims to transfer acoustic scenes of speech signals to diverse environments. AST promises an immersive experience in speech perception by adapting
Externí odkaz:
http://arxiv.org/abs/2406.12688
Ad-hoc distributed microphone environments, where microphone locations and numbers are unpredictable, present a challenge to traditional deep learning models, which typically require fixed architectures. To tailor deep learning models to accommodate
Externí odkaz:
http://arxiv.org/abs/2406.09819
Data augmentation techniques apply transformations to existing texts to generate additional data. The transformations may produce low-quality texts, where the meaning of the text is changed and the text may even be mangled beyond human comprehension.
Externí odkaz:
http://arxiv.org/abs/2404.18881
Compiler technologies in deep learning and domain-specific hardware acceleration are increasingly adopting extensible compiler frameworks such as Multi-Level Intermediate Representation (MLIR) to facilitate more efficient development. With MLIR, comp
Externí odkaz:
http://arxiv.org/abs/2404.16947