Repairing highly corrupted speech and images with U-net autoencoders

Michael S. Lee; John S. Hyatt; Samuel N. Edwards

doi:10.1117/12.2552796

21 April 2020 Repairing highly corrupted speech and images with U-net autoencoders

Michael S. Lee, John S. Hyatt, Samuel N. Edwards

Proceedings Volume 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II; 114130E (2020) https://doi.org/10.1117/12.2552796
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

Recovering data from high amounts of loss and corruption would be useful for a wide variety of civilian and military applications. Highly corrupted data (e.g., speech and images) has been less studied relative to the problem of light corruption, but would be advantageous for applications such as low-light imagery and weak signal reception in acoustic sensing and radio communication. Unlike milder signal corruptions, resolving strong noise interference may require a more robust approach than simply removing predictable noise, namely actively looking for the expected signal, a type of problem well suited for machine learning. In this work, we evaluate a variant of the U-net autoencoder neural network topology for accomplishing the difficult task of denoising highly corrupted images and English speech when noise floors are 2-10x stronger than the clean signal. We test our methods on corruptions including additive white Gaussian noise and channel dropout.

Conference Presentation

Citation Download Citation

Michael S. Lee, John S. Hyatt, and Samuel N. Edwards "Repairing highly corrupted speech and images with U-net autoencoders", Proc. SPIE 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II, 114130E (21 April 2020); https://doi.org/10.1117/12.2552796

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available