Generating audio mixtures using deep convolutional neural networks

Update Item Information
Publication Type honors thesis
School or College College of Engineering
Department Computing
Faculty Mentor Suresh Venkatasubramanian
Creator Herbert-Voss, Ariel
Title Generating audio mixtures using deep convolutional neural networks
Year graduated 2016
Date 2016-05
Description Deep neural networks have recently been used in a generative capacity to separate and convolve the content and style of two input images. This is done using a joint cost function during gradient descent that encodes information about style and content to iteratively calculate forward node activations. We extend this methodology to the auditory domain using sound clips converted to spectrograms using the short-time Fourier transform and discuss optimizing signal reconstruction.
Type Text
Publisher University of Utah
Subject Computer sound processing; Computer music; Machine learning; Neural networks; Audio mixtures; Spectrograms; Split integer scaling
Language eng
Rights Management (c) Ariel Herbert-Voss
Format Medium application/pdf
Format Extent 25,041 bytes
Identifier honors/id/2
Permissions Reference URL https://collections.lib.utah.edu/details?id=1273120
ARK ark:/87278/s6b88jcz
Setname ir_htoa
ID 205654
Reference URL https://collections.lib.utah.edu/ark:/87278/s6b88jcz
Back to Search Results