Related papers: Scaling Up Adaptive Filter Optimizers
The high-intensity, repetitive noise associated with functional magnetic resonance imaging hinders on-line monitoring of subjects' speech and/or recording speech signals suitable for off-line analysis. The proposed algorithm enhances the…
Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this,…
The target speech extraction has attracted widespread attention in recent years. In this work, we focus on investigating the dynamic interaction between different mixtures and the target speaker to exploit the discriminative target speaker…
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…
This article offers an elaborate description of a Kalman filter code employed in the active control system. Conventional active noise management methods usually employ an adaptive filter, such as the filtered reference least mean square…
Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…
The social metaverse is a growing digital ecosystem that blends virtual and physical worlds. It allows users to interact socially, work, shop, and enjoy entertainment. However, privacy remains a major challenge, as immersive interactions…
Noise-inclusive fully unsupervised anomaly detection (FUAD) holds significant practical relevance. Although various methods exist to address this problem, they are limited in both performance and scalability. Our work seeks to overcome…
Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full…
Water treatment and liquid storage are the two plants implementing the hydraulic three-tank system. Maintaining certain levels is the critical scenario so that the systems run as desired. To deal with, the optimal linear control and the…
Parallel combinations of adaptive filters have been effectively used to improve the performance of adaptive algorithms and address well-known trade-offs, such as convergence rate vs. steady-state error. Nevertheless, typical combinations…
In this paper, we propose sparsity-aware data-selective adaptive filtering algorithms with adjustable penalties. Prior work incorporates a penalty function into the cost function used in the optimization that originates the algorithms to…
A major challenge in Atomic Force Microscopy (AFM) is to reduce the scan duration while retaining the image quality. Conventionally, the scan rate is restricted to a sufficiently small value in order to ensure a desirable image quality as…
In an age of exponentially increasing data generation, performing inference tasks by utilizing the available information in its entirety is not always an affordable option. The present paper puts forth approaches to render tracking of…
The problem of multisensor multitarget state estimation in the presence of constant but unknown sensor biases is investigated. The classical approach to this problem is to augment the state vector to include the states of all the targets…
Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…
Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…
Semantic communications are expected to be an innovative solution to the emerging intelligent applications in the era of connected intelligence. In this paper, a novel scalable multitask semantic communication system with feature importance…
Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…
In this paper, we present a method for jointly-learning a microphone selection mechanism and a speech enhancement network for multi-channel speech enhancement with an ad-hoc microphone array. The attention-based microphone selection…