MDCT-based coder for highly adaptive speech and audio coding

Coding audio material at low bit rates with a consistent quality over a wide range of signals is a current and challenging problem. The high-granularity switched speech and audio coder AMR-WB+ performs especially well for speech and mixed content by promptly adapting its coding model scheme to the signal. However, the high adaptation rate is done at the price of limited performance for non-speech signals. The aim of the paper is to enhance the coding efficiency of AMR-WB+ while maintaining its high flexibility. For this purpose, the original DFT was replaced by the state-of-art transformation MDCT, and the vector quantization by the combination of a scalar quantization and an evolved context-adaptive arithmetic coder. The improvements were measured by both objective and subjective evaluations.