English
Related papers

Related papers: D3Net: Densely connected multidilated DenseNet for…

200 papers

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context,…

We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed depth refinement…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Rohan Chabra , Julian Straub , Chris Sweeney , Richard Newcombe , Henry Fuchs

4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Minqing Huang , Shouyi Lu , Boyuan Zheng , Ziyao Li , Xiao Tang , Guirong Zhuo

As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling…

Image and Video Processing · Electrical Eng. & Systems 2023-12-01 Wendi Ma , Marlon Bran Lorenzana , Wei Dai , Hongfu Sun , Shekhar S. Chandra

This paper proposes a 1D residual convolutional neural network (CNN) architecture for music genre classification and compares it with other recent 1D CNN architectures. The 1D CNNs learn a representation and a discriminant directly from the…

Sound · Computer Science 2021-05-18 Safaa Allamy , Alessandro Lameiras Koerich

In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections…

Machine Learning · Computer Science 2018-01-08 Xiaoyu Liu , Diyu Yang , Aly El Gamal

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

Sound · Computer Science 2024-06-03 Brandon Colelough , Andrew Zheng

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Gao Huang , Zhuang Liu , Laurens van der Maaten , Kilian Q. Weinberger

This paper describes a hands-on comparison on using state-of-the-art music source separation deep neural networks (DNNs) before and after task-specific fine-tuning for separating speech content from non-speech content in broadcast audio…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-23 Martin Strauss , Jouni Paulus , Matteo Torcoli , Bernd Edler

Music source separation represents the task of extracting all the instruments from a given song. Recent breakthroughs on this challenge have gravitated around a single dataset, MUSDB, only limited to four instrument classes. Larger datasets…

Sound · Computer Science 2021-12-02 Alexandru Mocanu , Benjamin Ricaud , Milos Cernak

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-17 Xue Yang , Changchun Bao

This work addresses the problem of multichannel source separation combining two powerful approaches, multichannel spectral factorization with recent monophonic deep-learning (DL) based spectrum inference. Individual source spectra at…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-04 Antonio J. Muñoz-Montoro , Julio J. Carabias-Orti , Archontis Politis , Konstantinos Drossos

Deep learning architecture with convolutional neural network (CNN) achieves outstanding success in the field of computer vision. Where U-Net, an encoder-decoder architecture structured by CNN, makes a great breakthrough in biomedical image…

Image and Video Processing · Electrical Eng. & Systems 2023-02-13 Qing Xu , Zhicheng Ma , Na HE , Wenting Duan

The high incidence rate of prostate disease poses a requirement in early detection for diagnosis. As one of the main imaging methods used for prostate cancer detection, Magnetic Resonance Imaging (MRI) has wide range of appearance and…

Computer Vision and Pattern Recognition · Computer Science 2018-02-02 Qiuhua Liu , Min Fu , Xinqi Gong , Hao Jiang

In recent years, deep convolutional neural networks have shown fascinating performance in the field of image denoising. However, deeper network architectures are often accompanied with large numbers of model parameters, leading to high…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Wencong Wu , Shicheng Liao , Guannan Lv , Peng Liang , Yungang Zhang

Waveform-based deep learning faces a dilemma between nonparametric and parametric approaches. On one hand, convolutional neural networks (convnets) may approximate any linear time-invariant system; yet, in practice, their frequency…

Sound · Computer Science 2024-07-09 Vincent Lostanlen , Daniel Haider , Han Han , Mathieu Lagrange , Peter Balazs , Martin Ehler

Automated brain structure segmentation is important to many clinical quantitative analysis and diagnoses. In this work, we introduce MixNet, a 2D semantic-wise deep convolutional neural network to segment brain structure in multi-modality…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Long Chen , Dorit Merhof

In this paper, a novel approach for single channel source separation (SCSS) using a deep neural network (DNN) architecture is introduced. Unlike previous studies in which DNN and other classifiers were used for classifying time-frequency…

Neural and Evolutionary Computing · Computer Science 2013-11-13 Emad M. Grais , Mehmet Umut Sen , Hakan Erdogan

Ultrasound imaging is safe, relatively affordable, and capable of real-time performance. One application of this technology is to visualize and to characterize human tongue shape and motion during a real-time speech to study healthy or…

Image and Video Processing · Electrical Eng. & Systems 2019-12-09 M. Hamed Mozaffari , Won-Sook Lee

Since medical image data sets contain few samples and singular features, lesions are viewed as highly similar to other tissues. The traditional neural network has a limited ability to learn features. Even if a host of feature maps is…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Hongfeng You , Long Yu , Shengwei Tian , Xiang Ma , Yan Xing , Xiaojie Ma