A Maximum-Hamming-Distance-Based Approach to Code Construction for Trellis-Coded Quantization

A thorough description of trellis-coded quantization as a nearly-optimal source coding system is presented. Trelliscoded quantizers couple traditional quantization techniques with finite state machines to build effective high dimensional vector quantizers. In a trellis-coded quantizer, each transition of the related finite state machine is labeled, by means of a convolutional code, with one of the sub-codebooks obtained by partitioning a single extended codebook. Traditional design approaches take advantage of the duality of trellis-coded quantization with trelliscoded modulation, and are then based on the same empiricallyfound convolutional codes. This paper presents a novel approach to construct effective trellis-coded quantizers, which takes advantage of maximum-Hamming-distance convolutional codes. The objective is to describe a new design technique rather than introduce coding systems with highly improved performance. Nevertheless, examples are presented to illustrate the performance of the proposed trellis-coded quantizers, and they are shown to slightly outperform the trellis-coded quantizers found in the literature.