JIITA, vol.7 no.1, p.675-680, 2023, DOI: 10.22664/ISITA.2021.7.1.675
Hong-Jin Kim 1) , Jeong Tak Ryu 2) and Kyuman Jeong 1,3,*)
1)School of AI, Daegu University, Daegu, Korea
2)College of Information and Communication Engineering, Daegu University, Daegu, Korea
3) School of AI, Daegu University, Daegu, Korea
Abstract: Artificial intelligence technology, in which computers perform human-like actions or behaviors, is becoming popular. Particularly, efforts are being made to implement technologies that classify objects or respond to user behavior. It is also attracting attention in fields that require much 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 an image restoration technique using threedimensional data. In particular, audio data has changed from the way of using physical storage devices in the past to the way of being provided on a network basis. In this paper, we propose an algorithm to recover high – quality audio data from the internal storage device that can be self – produced by receiving compressed audio data. We propose a method of restoring audio data that is arranged and reproduced by changing time-dependent one-dimensional data using lossless audio data and lost audio data after compression through a deep learning technology, CNN (Convolutional Neural Network).
Keywords: component, formatting, style, styling, insert
Fullpaper: