Files in this item

FilesDescriptionFormat

application/pdf

application/pdfLIM-THESIS-2018.pdf (12MB)
(no description provided)PDF

Description

Title:Audio super-resolution with deep neural networks
Author(s):Lim, Teck Yian
Advisor(s):Do, Minh N.
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Deep Neural Networks
Audio
Signal Processing
Generative Adversarial Networks
GAN
DNN
Super resolution
Abstract:This thesis reports various attempts at applying generative deep neural networks to audio for the task of recovering a high quality audio signal when given a low sample rate signal. Our experiments show that deep networks are able to discover patterns in speech and music signals by working in both time and frequency domains jointly. Such a network structure outperforms other methods that work either in the time domain or frequency domain exclusively. In our evaluations with speech signals, our method outperforms a time-domain only method by Kuleshov et. al. by 1.4 dB for 4x and by up to 2.0 dB for 8x upsampling.
Issue Date:2018-04-23
Type:Text
URI:http://hdl.handle.net/2142/100932
Rights Information:Copyright 2018 Teck Yian Lim
Date Available in IDEALS:2018-09-04
Date Deposited:2018-05


This item appears in the following Collection(s)

Item Statistics