We propose a first step toward multilingual end-to-end automatic speech
...
Previous Multimodal Information based Speech Processing (MISP) challenge...
Using kinematic properties of handwriting to support the diagnosis of
ne...
We propose a multi-dimensional structured state space (S4) approach to s...
In this work, we devise a parameter-efficient solution to bring differen...
We propose a quantum kernel learning (QKL) framework to address the inhe...
This study addresses the speech enhancement (SE) task within the causal
...
We propose an ensemble learning framework with Poisson sub-sampling to
e...
Differential privacy (DP) is one data protection avenue to safeguard use...
In this paper, we propose two techniques, namely joint modeling and data...
We propose a variational Bayesian (VB) approach to learning distribution...
In this study, we propose a novel adversarial reprogramming (AR) approac...
We propose a novel neural model compression strategy combining data
augm...
We propose using an adversarial autoencoder (AAE) to replace generative
...
To improve device robustness, a highly desirable key feature of a compet...
We propose a novel decentralized feature extraction approach in federate...
In this paper, we exploit the properties of mean absolute error (MAE) as...
In this paper, we show that, in vector-to-vector regression utilizing de...
In this paper, we propose a domain adaptation framework to address the d...
In this paper, we propose a sub-utterance unit selection framework to re...
This paper investigates different trade-offs between the number of model...
In this technical report, we present a joint effort of four groups, name...
We propose a tensor-to-vector regression approach to multi-channel speec...
We present a Bayesian approach to adapting parameters of a well-trained
...