相关论文: Unraveling Complex Data Diversity in Underwater Ac…

Underwater acoustic target recognition has emerged as a prominent research area within the field of underwater acoustics. However, the current availability of authentic underwater acoustic signal recordings remains limited, which hinders…

Building a robust underwater acoustic recognition system in real-world scenarios is challenging due to the complex underwater environment and the dynamic motion states of targets. A promising optimization approach is to leverage the…

Recognizing underwater targets from acoustic signals is a challenging task owing to the intricate ocean environments and variable underwater channels. While deep learning-based systems have become the mainstream approach for underwater…

Key challenges in developing underwater acoustic localization methods are related to the combined effects of high reverberation in intricate environments. To address such challenges, recent studies have shown that with a properly designed…

Large Language Models (LLMs) encounter significant challenges in continual learning due to catastrophic forgetting, where new information overwrites previously acquired knowledge. This limitation leads to substantial environmental and…

Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leading to substantial performance degradation for other accents.…

Underwater acoustic target recognition is critical for maritime applications, yet it faces challenges arising from the complex and diverse nature of ship-radiated noise. To address these issues, we propose a robust deep learning-based…

This paper presents a novel deep learning approach for analyzing massive underwater acoustic data by leveraging a model trained on a broad spectrum of non-underwater (aerial) sounds. Recognizing the challenge in labeling vast amounts of…

We present a new supervised architecture termed Mediated Mixture-of-Experts (MMoE) that allows us to improve classification accuracy of Deep Convolutional Networks (DCN). Our architecture achieves this with the help of expert networks: A…

In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains. Such solutions are sub-optimal as…

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target recognition (UATR) using ship-radiated noise. Inspired by neural mechanism of auditory perception, this paper provides a new deep…

Underwater acoustic target recognition is an intractable task due to the complex acoustic source characteristics and sound propagation patterns. Limited by insufficient data and narrow information perspective, recognition models based on…

A useful strategy to deal with complex classification scenarios is the "divide and conquer" approach. The mixture of experts (MOE) technique makes use of this strategy by joinly training a set of classifiers, or experts, that are…

To overcome the constraints of the underwater environment and improve the accuracy and robustness of underwater target detection models, this paper develops a specialized dataset for underwater target detection and proposes an efficient…

Remotely detecting and classifying underwater acoustic targets is critical for environmental monitoring and defence. However, the complexity of ship-radiated and environmental noise poses significant challenges for accurate signal…

Reliable channel estimation (CE) is fundamental for robust communication in dynamic wireless environments, where models must generalize across varying conditions such as signal-to-noise ratios (SNRs), the number of resource blocks (RBs),…

Sparse Mixture of Experts (SMoE) has become the key to unlocking unparalleled scalability in deep learning. SMoE has the potential to exponentially increase parameter count while maintaining the efficiency of the model by only activating a…

The Mixture-of-Experts (MoE) layer, a sparsely-activated model controlled by a router, has achieved great success in deep learning. However, the understanding of such architecture remains elusive. In this paper, we formally study how the…

In this study we present a Deep Mixture of Experts (DMoE) neural-network architecture for single microphone speech enhancement. By contrast to most speech enhancement algorithms that overlook the speech variability mainly caused by phoneme…

Sparse Mixture of Experts (SMoE) enables efficient training of large language models by routing input tokens to a select number of experts. However, training SMoE remains challenging due to the issue of representation collapse. Recent…