With fewer feature dimensions, filter banks are often used in light-weig...
Target speaker information can be utilized in speech enhancement (SE) mo...
Attention mechanism has been widely utilized in speech enhancement (SE)
...
Attention mechanism has been widely utilized in speech enhancement (SE)
...
Domain adaptation aims to transfer the knowledge acquired by models trai...
We present Hybrid Infused Reranking for Passages Retrieval (HYRR), a
fra...
Knowledge distillation learns a lightweight student model that mimics a
...
Recently, substantial progress has been made in text ranking based on
pr...
Much recent research on information retrieval has focused on how to tran...
Deep neural network (DNN) based speech enhancement models have attracted...
The recently proposed semi-blind source separation (SBSS) method for
non...
Deep neural network based full-band speech enhancement systems face
chal...
The direct expansion of deep neural network (DNN) based wide-band speech...
State-of-the-art neural models typically encode document-query pairs usi...
Open Set Recognition (OSR) has been an emerging topic. Besides recognizi...
The pre-trained language model (eg, BERT) based deep retrieval models
ac...
It has been shown that dual encoders trained on one domain often fail to...
Scene video text spotting (SVTS) is a very important research topic beca...
The dual-path RNN (DPRNN) was proposed to more effectively model extreme...
In this paper, we introduce a technique to enhance the computational
eff...
This paper focuses on the analytical probabilistic modeling of vehicular...
In this paper we explore the effects of negative sampling in dual encode...
Click-through rate (CTR) prediction is one of the fundamental tasks for
...
The complete decomposition performed by blind source separation is
compu...
As one of the largest B2C e-commerce platforms in China, JD.com also pow...
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes ...
In object recognition applications, object images usually appear with
di...
Acoustic echo cannot be entirely removed by linear adaptive filters due ...
Image-text matching tasks have recently attracted a lot of attention in ...
A major problem with user-written bug reports, indicated by developers a...
A robust method for linear array is proposed to address the difficulty o...
This paper proposes an unified framework for efficiently spotting scene ...
The frequency-domain Kalman filter (FKF) has been utilized in many audio...
The TRINICON ('Triple-N ICA for convolutive mixtures') framework is an
e...
Adaptive algorithm based on multi-channel linear prediction is an effect...
Online learning represents an important family of machine learning
algor...
SOL is an open-source library for scalable online learning algorithms, a...
In this paper we present an efficient algorithm for the segmentation of ...