Audio super-resolution with deep neural networks

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.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2018

Author dc:creator

• Lim, Teck Yian

Contributors dc:contributor

• Do, Minh N.

• Deep Neural Networks
• Audio
• Signal Processing
• Generative Adversarial Networks
• GAN
• DNN
• Super resolution

Statement dc:rights

• Copyright 2018 Teck Yian Lim

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/100932

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/100932