Current speaker recognition systems primarily rely on supervised approac...
Speaker extraction and diarization are two crucial enabling techniques f...
Target speaker extraction aims to extract the speech of a specific speak...
Software plays a crucial role in our daily lives, and therefore the qual...
Deep neural network-based systems have significantly improved the perfor...
Recent research has shown that bit-flip attacks (BFAs) can manipulate de...
Causal discovery is a powerful technique for identifying causal relation...
Screening prioritisation in medical systematic reviews aims to rank the ...
Binary silhouettes and keypoint-based skeletons have dominated human gai...
In this paper, we propose a new way of remembering by introducing a memo...
Query-based object detectors directly decode image features into object
...
A physical simulation engine (PSE) is a software system that simulates
p...
Multi-contrast magnetic resonance imaging (MRI) reflects information abo...
While federated learning (FL) improves the generalization of end-to-end
...
This report showcases the results achieved using the wespeaker toolkit f...
Understanding causal relations is vital in scientific discovery. The pro...
The utilization of discrete speech tokens, divided into semantic tokens ...
The objective of neural network (NN) robustness certification is to dete...
Recent years have witnessed a huge demand for artificial intelligence an...
Automatic segmentation of fluid in OCT (Optical Coherence Tomography) im...
Autonomous parking (AP) is an emering technique to navigate an intellige...
Training a Named Entity Recognition (NER) model often involves fixing a
...
There has been an increasing interest in enhancing the fairness of machi...
Voice conversion is an increasingly popular technology, and the growing
...
We explore how weak supervision on abundant unlabeled data can be levera...
This paper proposes a novel Attention-based Encoder-Decoder network for
...
EXplainable AI (XAI) is an essential topic to improve human understandin...
Nowadays, recognition-synthesis-based methods have been quite popular wi...
Deep neural networks (DNNs) achieve promising performance in visual
reco...
Source-free domain adaptation aims to adapt deep neural networks using o...
As the popularity of large language models (LLMs) soars across various
a...
In the Internet of Things (IoT) networks, edge learning for data-driven ...
Meta-reinforcement learning enables artificial agents to learn from rela...
Dataset expansion can effectively alleviate the problem of data scarcity...
Video Instance Segmentation(VIS) aims at segmenting and categorizing obj...
Exploring data is crucial in data analysis, as it helps users understand...
Opinion summarization provides an important solution for summarizing opi...
Test time adaptation (TTA) aims to adapt deep neural networks when recei...
Multi-modality medical imaging is crucial in clinical treatment as it ca...
In this paper, considering the balance of data/model privacy of model ow...
Recent progress in large language code models (LLCMs) has led to a drama...
Temporal concept drift refers to the problem of data changing over time....
Systematic reviews are comprehensive reviews of the literature for a hig...
The Linux kernel makes considerable use of Berkeley Packet Filter (BPF) ...
Phosphorescent metal complexes have been under intense investigations as...
Federated clustering (FedC) is an adaptation of centralized clustering i...
In this paper, we propose an effective unified control law for accuratel...
Objects in a scene are not always related. The execution efficiency of t...
Boolean query construction is often critical for medical systematic revi...
Medical systematic reviews typically require assessing all the documents...