Related papers: Meta-learning based Selective Fixed-filter Active …
Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal…
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…
Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…
Active noise control (ANC) has become popular for reducing noise and thus enhancing user comfort in headphones. While feedback control offers an effective way to implement ANC, it is restricted by uncertainty of the controlled system that…
Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution…
Multi-class cell segmentation in high-resolution gigapixel whole slide images (WSIs) is crucial for various clinical applications. However, training such models typically requires labor-intensive, pixel-wise annotations by domain experts.…
Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is…
Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…
In this paper, we consider the problem of finding a meta-learning online control algorithm that can learn across the tasks when faced with a sequence of $N$ (similar) control tasks. Each task involves controlling a linear dynamical system…
Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct…
Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise,…
We study how to safely control nonlinear control-affine systems that are corrupted with bounded non-stochastic noise, i.e., noise that is unknown a priori and that is not necessarily governed by a stochastic model. We focus on safety…
We study online control for continuous-time linear systems with finite sampling rates, where the objective is to design an online procedure that learns under non-stochastic noise and performs comparably to a fixed optimal linear controller.…
In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully…
The combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under quiet conditions. However, when noise signals are involved,…
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification…
In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fixed once trained, lacking flexibility during inference and…
Acoustic Echo Cancellation (AEC) plays a key role in voice interaction. Due to the explicit mathematical principle and intelligent nature to accommodate conditions, adaptive filters with different types of implementations are always used…
Automatic modulation classification (AMC) has emerged as a key technique in cognitive radio networks in sixth-generation (6G) communications. AMC enables effective data transmission without requiring prior knowledge of modulation schemes.…
Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the…