Related papers: SAMA-IR: comprehensive input refinement methodolog…
Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although…
Modern deep learning models are over-parameterized, where the optimization setup strongly affects the generalization performance. A key element of reliable optimization for these systems is the modification of the loss function.…
Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement methods rely on paired training data captured under…
Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adversarially chosen…
The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the…
Today, the optimal performance of existing noise-suppression algorithms, both data-driven and those based on classic statistical methods, is range bound to specific levels of instantaneous input signal-to-noise ratios. In this paper, we…
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalization parameters…
The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single…
The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or…
Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training…
We propose a novel 5-bit/2D-symbol modulation format based on PAM-6 optimized for IM-DD systems dominated by relative intensity noise. The proposed modulation scheme improves SNR by 0.94 dB compared to conventional PAM-6 and achieves…
Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…
Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like…
Optical communication systems are always evolving to support the need for ever-increasing transmission rates. This demand is supported by the growth in complexity of communication systems which are moving towards ultra-wideband transmission…
This paper describes an online algorithm for enhancing monaural noisy speech. Firstly, a novel phase-corrected low-delay gammatone filterbank is derived for signal subband decomposition and resynthesis; the subband signals are then analyzed…
Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-based training scheme for better model robustness.…
We theoretically investigate quantum measurement noise in a hybrid optomechanical system, focusing on radiation pressure back action and its impact on force sensing. The setup consists of an optomechanical cavity with a movable mirror, a…
Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress background noise, they often introduce artifacts that harm recognition. Observation addition (OA)…
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional neural networks (CNNs) against commonly occurring distortions…
Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as…