Zobrazeno 1 - 10
of 7 881
pro vyhledávání: '"Park， Hyung In"'
This paper develops a novel Bayesian approach for nonlinear regression with symmetric matrix predictors, often used to encode connectivity of different nodes. Unlike methods that vectorize matrices as predictors that result in a large number of model
Externí odkaz:
http://arxiv.org/abs/2407.13865
In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage of the net
Externí odkaz:
http://arxiv.org/abs/2406.05983
This paper presents a Bayesian regression model relating scalar outcomes to brain functional connectivity represented as symmetric positive definite (SPD) matrices. Unlike many proposals that simply vectorize the matrix-valued connectivity predictors
Externí odkaz:
http://arxiv.org/abs/2401.16749
Stepped wedge cluster randomized trials (SWCRTs) often face challenges with potential confounding by time trends. Traditional frequentist methods can fail to provide adequate coverage of the intervention's true effect using confidence intervals, wher
Externí odkaz:
http://arxiv.org/abs/2401.03287
In speaker verification, ECAPA-TDNN has shown remarkable improvement by utilizing one-dimensional(1D) Res2Net block and squeeze-and-excitation(SE) module, along with multi-layer feature aggregation (MFA). Meanwhile, in vision tasks, ConvNet structure
Externí odkaz:
http://arxiv.org/abs/2312.08603
This paper presents a formulation for deterministically calculating optimized paths for a multiagent system consisting of heterogeneous vehicles. The key idea is the calculation of the shortest time for each agent to reach every grid point from its k
Externí odkaz:
http://arxiv.org/abs/2310.14507
Autor:
Shin, Ui-Hyeop, Park, Hyung-Min
In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR). By modeling the target speech as a non-stationary Laplacian distribution, a mask-based statistical beamforming algor
Externí odkaz:
http://arxiv.org/abs/2306.07562
Autor:
Park, Hyung G.
This paper presents a Bayesian reformulation of covariate-assisted principal (CAP) regression of Zhao and others (2021), which aims to identify components in the covariance of response signal that are associated with covariates in a regression framew
Externí odkaz:
http://arxiv.org/abs/2306.07181
With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of speech repres
Externí odkaz:
http://arxiv.org/abs/2304.03940
Autor:
Park, Jeongkyun, Hwang, Jung-Wook, Choi, Kwanghee, Lee, Seung-Hyun, Ahn, Jun Hwan, Park, Rae-Hong, Park, Hyung-Min
Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed. However, most existing datasets focus on English, induce dependencies with various prediction models during dataset preparation, and
Externí odkaz:
http://arxiv.org/abs/2301.06375