Zobrazeno 1 - 10
of 99
pro vyhledávání: '"Truong, Duc P."'
Autor:
Adak, Dibyendu, Truong, Duc P., Vuchkov, Radoslav, De, Saibal, DeSantis, Derek, Roberts, Nathan V., Rasmussen, Kim Ø., Alexandrov, Boian S.
In this paper, we present a new space-time Petrov-Galerkin-like method. This method utilizes a mixed formulation of Tensor Train (TT) and Quantized Tensor Train (QTT), designed for the spectral element discretization (Q1-SEM) of the time-dependent co
Externí odkaz:
http://arxiv.org/abs/2411.04026
The ASVspoof 2021 benchmark, a widely-used evaluation framework for anti-spoofing, consists of two subsets: Logical Access (LA) and Deepfake (DF), featuring samples with varied coding characteristics and compression artifacts. Notably, the current st
Externí odkaz:
http://arxiv.org/abs/2409.14712
Autor:
Danis, Mustafa Engin, Truong, Duc P., DeSantis, Derek, Petersen, Mark, Rasmussen, Kim O., Alexandrov, Boian S.
In this paper, we introduce a high-order tensor-train (TT) finite volume method for the Shallow Water Equations (SWEs). We present the implementation of the $3^{rd}$ order Upwind and the $5^{th}$ order Upwind and WENO reconstruction schemes in the TT
Externí odkaz:
http://arxiv.org/abs/2408.03483
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
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
Spectral methods provide highly accurate numerical solutions for partial differential equations, exhibiting exponential convergence with the number of spectral nodes. Traditionally, in addressing time-dependent nonlinear problems, attention has been
Externí odkaz:
http://arxiv.org/abs/2406.02505
Autor:
Danis, Mustafa Engin, Truong, Duc, Boureima, Ismael, Korobkin, Oleg, Rasmussen, Kim, Alexandrov, Boian
In this study, we introduce a tensor-train (TT) finite difference WENO method for solving compressible Euler equations. In a step-by-step manner, the tensorization of the governing equations is demonstrated. We also introduce \emph{LF-cross} and \emp
Externí odkaz:
http://arxiv.org/abs/2405.12301
Emerging tensor network techniques for solutions of Partial Differential Equations (PDEs), known for their ability to break the curse of dimensionality, deliver new mathematical methods for ultrafast numerical solutions of high-dimensional problems.
Externí odkaz:
http://arxiv.org/abs/2402.18073
Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification
Publikováno v:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 10336-10340
Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the conventional label-l
Externí odkaz:
http://arxiv.org/abs/2309.14838
Autor:
Truong, Duc P., Ortega, Mario I., Boureima, Ismael, Manzini, Gianmarco, Rasmussen, Kim Ø., Alexandrov, Boian S.
Tensor network techniques, known for their low-rank approximation ability that breaks the curse of dimensionality, are emerging as a foundation of new mathematical methods for ultra-fast numerical solutions of high-dimensional Partial Differential Eq
Externí odkaz:
http://arxiv.org/abs/2309.03347