Published on Tue Mar 24 2020

Training a U-Net based on a random mode-coupling matrix model to recover acoustic interference striations

Xiaolei Li, Wenhua Song, Dazhi Gao, Wei Gao, Haozhong Wan

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of training data. The performance of AIS recovery is tested in range-dependent waveguides.

0
0
0
Abstract

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones. A random mode-coupling matrix model is introduced to generate a large number of training data quickly, which are used to train the U-Net. The performance of AIS recovery of the U-Net is tested in range-dependent waveguides with nonlinear internal waves (NLIWs). Although the random mode-coupling matrix model is not an accurate physical model, the test results show that the U-Net successfully recovers AISs under different signal-to-noise ratios (SNRs) and different amplitudes and widths of NLIWs for different shapes.

Mon Oct 12 2020
Machine Learning
Conditioning Trick for Training Stable GANs
In this paper we propose a conditioning trick, called difference departure from normality, applied on the generator network. We force the generator to get closer to the Schur decomposition function of real samples. This binding makes the generator amenable to exploring all the possible modes.
0
0
0
Sat Feb 08 2020
Machine Learning
ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning
0
0
0
Tue Jul 02 2019
Machine Learning
Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations
Conditioned-U-Net adds a control mechanism to the standard U-Net. The control mechanism allows us to train a unique and generic U- net to perform the separation of various instruments. The C-U -Net decides the instrument to isolate according to a one-hot-
0
0
0
Fri Nov 29 2019
Machine Learning
J-Net: Randomly weighted U-Net for audio source separation
A positive correlation exists between performance of randomly weighted neural networks and their fully trained counterparts. Fixing the decoder (up-sample path) with random weights results in better performance.
0
0
0
Wed Oct 30 2019
Machine Learning
Fast acoustic scattering using convolutional neural networks
Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications. We propose training a convolutional neural network to map from a convex scatterer's cross-section to a 2D slice of the spatial loudness distribution.
0
0
0
Wed Jan 13 2021
Machine Learning
Reproducing Activation Function for Deep Learning
We propose reproducing activation functions (RAFs) to improve deep learning accuracy. RAFs can be used for various applications ranging from computer vision to scientific computing. With RAFs, the errors of audio/video reconstruction, PDEs, and eigenvalue problems are decreased.
0
0
0