Related papers: Multi-channel U-Net for Music Source Separation
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…
Standard neural networks struggle to generalize under distribution shifts in computer vision. Fortunately, combining multiple networks can consistently improve out-of-distribution generalization. In particular, weight averaging (WA)…
Cloud segmentation amounts to separating cloud pixels from non-cloud pixels in an image. Current deep learning methods for cloud segmentation suffer from three issues. (a) Constrain on their receptive field due to the fixed size of the…
Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake and remixing. In this…
In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates directly on the time domain. The standard Wave-U-Net is…
Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved,…
This research paper presents a novel deep learning-based neural network architecture, named Y-Net, for achieving music source separation. The proposed architecture performs end-to-end hybrid source separation by extracting features from…
Learning with labels noise has gained significant traction recently due to the sensitivity of deep neural networks under label noise under common loss functions. Losses that are theoretically robust to label noise, however, often makes…
Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several…
Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning…
This work examines the use of two-way training to efficiently discriminate the channel estimation performances at a legitimate receiver (LR) and an unauthorized receiver (UR) in a multiple-input multiple-output (MIMO) wireless system. This…
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…
Most of the currently successful source separation techniques use the magnitude spectrogram as input, and are therefore by default omitting part of the signal: the phase. To avoid omitting potentially useful information, we study the…
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…
The U-net is a deep-learning network model that has been used to solve a number of inverse problems. In this work, the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, were evaluated for…
Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality,…
Given recent advances in deep music source separation, we propose a feature representation method that combines source separation with a state-of-the-art representation learning technique that is suitably repurposed for computer audition…
Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning,…
In this paper we propose an improved method for transfer learning that takes into account the balance between target and source data. This method builds on the state-of-the-art Multisource Tradaboost, but weighs the importance of each…
Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore the separation ability of models. In this work, we reveal that…