Improving Impulse Audio Source Separation using Generative Adversarial Networks for Phase Generation
This thesis explored separating impulse noise from a desired signal, for the purposes of hearing protection for soldiers and musicians. An evaluation of current techniques in source separation, such as matrix demixing methods (Independent Component Analysis, Independent Vector Analysis), and masking...
Main Author: | Piercy, Phoebe K. |
---|---|
Other Authors: | Lang, Jeffrey H. |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/138956 |
Similar Items
-
Improving Impulse Audio Source Separation using Generative Adversarial Networks for Phase Estimation
by: Piercy, Phoebe
Published: (2021) -
Generating human faces by generative adversarial networks
by: S Sri Kalki
Published: (2022) -
Generating human faces by generative adversarial networks
by: Quek, Chin Wei
Published: (2020) -
Generating human faces by generative adversarial network
by: Tao, Weijing
Published: (2021) -
Music generation with generative adversarial network (GAN)
by: Tan, Yi Zhuang
Published: (2021)