Zobrazeno 1 - 10
of 25 596
pro vyhledávání: '"Eng, P."'
In their study of the giant component in inhomogeneous random graphs, Bollob\'as, Janson, and Riordan introduced a class of branching processes parametrized by a possibly unbounded graphon. We prove that two such branching processes have the same dis
Externí odkaz:
http://arxiv.org/abs/2408.02528
Radar-based contactless cardiac monitoring has become a popular research direction recently, but the fine-grained electrocardiogram (ECG) signal is still hard to reconstruct from millimeter-wave radar signal. The key obstacle is to decouple the cardi
Externí odkaz:
http://arxiv.org/abs/2408.01672
Publikováno v:
Expert Systems with Applications, Volume 255, 2024, Article 124742
Random forests are considered a cornerstone in machine learning for their robustness and versatility. Despite these strengths, their conventional centralized training is ill-suited for the modern landscape of data that is often distributed, sensitive
Externí odkaz:
http://arxiv.org/abs/2407.19193
Autor:
Tao, Ruijie, Shi, Zhan, Jiang, Yidi, Truong, Duc-Tuan, Chng, Eng-Siong, Alioto, Massimo, Li, Haizhou
The human brain has the capability to associate the unknown person's voice and face by leveraging their general relationship, referred to as ``cross-modal speaker verification''. This task poses significant challenges due to the complex relationship
Externí odkaz:
http://arxiv.org/abs/2407.17902
Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \textbf{1)} generalizable talking-face representation, \te
Externí odkaz:
http://arxiv.org/abs/2407.14841
Autor:
Li, Zhuoxiao, Yao, Shanliang, Chu, Yijie, Garcia-Fernandez, Angel F., Yue, Yong, Lim, Eng Gee, Zhu, Xiaohui
In the rapidly evolving field of 3D reconstruction, 3D Gaussian Splatting (3DGS) and 2D Gaussian Splatting (2DGS) represent significant advancements. Although 2DGS compresses 3D Gaussian primitives into 2D Gaussian surfels to effectively enhance mesh
Externí odkaz:
http://arxiv.org/abs/2407.11840
Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL methods, m
Externí odkaz:
http://arxiv.org/abs/2407.03645
In this paper, we propose reverse inference optimization (RIO), a simple and effective method designed to enhance the robustness of autoregressive-model-based zero-shot text-to-speech (TTS) systems using reinforcement learning from human feedback (RL
Externí odkaz:
http://arxiv.org/abs/2407.02243
Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head self-attention (M
Externí odkaz:
http://arxiv.org/abs/2406.17376
Recent improvements in neural audio codec (NAC) models have generated interest in adopting pre-trained codecs for a variety of speech processing applications to take advantage of the efficiencies gained from high compression, but these have yet been
Externí odkaz:
http://arxiv.org/abs/2406.12434