A unified computing kernel for MDCT/IMDCT in modern audio coding standards

Abstract

MDCT/IMDCT has been widely adopted to transform an audio sequence from time domain to transform domain by various audio codec standards. This paper presents a unified algorithm and its hardware design for cosine modulated filter bank. In algorithm derivation, both MDCT and IMDCT are first converted to a half size DCT-IV with input or output permutation. The DCT-IV is then realized by a fast DCT-II algorithm. Both radix-3 and radix-2 DCT-II algorithms are analyzed and a unified computing kernel is concluded.