Optimising the combined source and channel coding of a discrete communication system

The problem of optimising the structure of the encoder/decoder pair in a discrete communication system, with an additive distortion measure, is formulated in terms of a quadratic programming (QP) problem. This new formulation benefits from the following special features: it optimises the joint effects of the source/channel coding on the end-to-end distortion; and the encoder and the decoder structures are not restricted to being the inverse of each other. A method which obtains an e-minimiser approximation of an optimum point of a general QP problem is discussed. Some simulation results based on this method are also given.