Related papers: Neural modeling of magnetic tape recorders
At present, neural network models show powerful sequence prediction ability and are used in many automatic composition models. In comparison, the way humans compose music is very different from it. Composers usually start by creating…
Recurrent neural networks (RNNs) have demonstrated impressive results for virtual analog modeling of audio effects. These networks process time-domain audio signals using a series of matrix multiplication and nonlinear activation functions…
The increasing need to store large amounts of information with an ultra-dense, reliable, low power and low cost memory device is driving aggressive efforts to improve upon current perpendicular magnetic recording technology. However, the…
The denoising of magnetic resonance (MR) images is a task of great importance for improving the acquired image quality. Many methods have been proposed in the literature to retrieve noise free images with good performances. Howerever, the…
Proposed is a substantially simplified, Preisach-like model for characterization of hysteretic systems, in particular magnetic systems. The main idea is to replace a two-dimensional Preisach density with just two real functions, describing…
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…
In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly. The key point of modeling repeat consumption is…
Magnetic particle imaging reconstructs tracer distributions using a system matrix obtained through time-consuming, noise-prone calibration measurements. Methods for addressing imperfections in measured system matrices increasingly rely on…
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…
This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training…
Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes some pre-trained…
We present a modular neural network architecture Main that learns algorithms given a set of input-output examples. Main consists of a neural controller that interacts with a variable-length input tape and learns to compose modules together…
Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization…
Current and field profiles, and magnetization and ac losses are calculated for arrays of infinitely long superconducting tapes in the critical state in a perpendicularly applied magnetic field. The tapes are arranged both horizontally and…
The decomposition of non-stationary signals is an important and challenging task in the field of signal time-frequency analysis. In the recent two decades, many signal decomposition methods led by the empirical mode decomposition, which was…
Applications of deep learning to automatic multitrack mixing are largely unexplored. This is partly due to the limited available data, coupled with the fact that such data is relatively unstructured and variable. To address these…
Transistors are the basic building blocks for all electronics. Accurate prediction of their current-voltage (IV) characteristics enables circuit simulations before the expensive silicon tape-out. In this work, we propose using deep neural…
Modulation classification, an intermediate process between signal detection and demodulation in a physical layer, is now attracting more interest to the cognitive radio field, wherein the performance is powered by artificial intelligence…
Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that…
Training deep neural networks on real-world datasets is often hampered by the presence of noisy labels, which can be memorized by over-parameterized models, leading to significant degradation in generalization performance. While existing…