A Decision Criterion to Relocate Codewords for Adaptive Vector Quantization

In many adaptive vector quantization (AVQ) algorithms, codeword relocation is employed for quick adaptation to changes in non-stationary source statistics. However, those algorithms generally determine codeword relocation using heuristically predetermined parameters as thresholds; thereby, their performance seriously depends on parameters. This paper proposes a valid decision criterion whose threshold is automatically adjusted according to optimality of a codebook assessed from the viewpoint of the equidistortion condition. In this paper, an AVQ algorithm is also presented to verify the criterion validity. Experimental results show that the proposed AVQ algorithm can minimize expected distortion and also quickly adapt to changing non-stationary signal sources by properly relocating codewords. Accordingly, validity of the proposed criterion is clarified via experimental results.