Enhanced Method of Audio Coding Using CNN-Based Spectral Recovery with Adaptive Structure

Abstract

A process of spectral recovery can enhance the performance of transform-based audio coding by transmitting only a portion of spectral data and recovering the missing spectral data in the decoder. This study proposes an enhanced method of audio coding based on spectral recovery with an adaptive structure that yields improved sound quality compared with the previous method. The spectral data to be recovered are arranged in an adaptive pattern depending on the difficulty of recovery. In addition, according to the spectral characteristics, prior information associated with these spectral data is selectively transmitted that helps a neural network improve the performance of magnitude recovery. Prior information also provides the signs of recovered magnitudes. A subjective performance evaluation shows that, for mono coding without window switching at 40 kbps, the proposed coding method provides better sound quality than the conventional method on average.