DESIGN OF MULTIPLE DESCRIPTION SCALAR QUANTIZERS

The design of scalar quantizers for communication systems that use diversity to overcome channel impairments is considered. The design problem is posed as an optimization problem and necessary conditions for optimality are derived. A design algorithm, a generalization of Lloyd's algorithm for quantizer design, is developed. Unlike a single channel scalar quantizer, the performance of a multiple description scalar quantizer is dependent on the index assignment. The problem of index assignment is addressed. Good index assignments, performance results, and sample quantizer designs are presented for a memoryless Gaussian source. Furthermore, comparisons are made against rate distortion bounds for the multiple descriptions problem.