|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Artificial intelligence technology, in which computers perform actions or behaviors similar to humans, is becoming popular. In particular, many efforts have been made to implement a technology that distinguishes objects or responds to user actions. Furthermore, it is also in the limelight in fields that require a lot of time and effort, such as restoring paintings drawn in the past. It is expected that it can be used in various fields as well as image restoration techniques using 3D data. In particular, audio data has changed from the method of using physical storage devices in the past to the form of being provided on a network basis, and the future market value is also great. In this paper, we propose an algorithm to restore compressed audio data so that it can self-produce high-quality audio data from an internal storage device. We propose a method of restoring audio data that is reproduced by enumerating one-dimensional data that changes over time using lossless audio data and audio data lost after compression through a convolutional neural network (CNN), a deep learning technology.
Keyword
Artificial Intelligence, CNN, Audio Super-Resolution, Deep Learning
PDF Download (click here)
|
|
|
|
|