Joint source channel coding using sequential decoding

Abstract

In systems using conventional source encoding, source sequence is changed into a series of approximately independent equally likely binary digits. Performance of a code is bounded with the rate distortion function and improves as the redundancy of the encoder output is decreased. However decreasing the redundancy implies increasing the block length and hence the complexity. For the systems requiring low complexity at transmitter, joint source channel (JSC) coding can be successfully used for direct encoding of source into the channel for lossless recovery. In such a system, without any distortion, compression depends on the redundancy of the source, and is bounded by the Renyi entropy of the source. In this thesis we analyze transmission of English text with a JSC coding system. Written English is a good example for sources with natural redundancy. Since we are unable to calculate the Renyi entropy of written English, we obtain estimates and compare with the experimental results. We also work on an alternative source encoding method for accuracycompression trade-off in joint source channel coding systems. The proposed stochastic distortion encoder (SDE) is capable of achieving accuracycompression trade-off at any average distortion constraint with very low block lengths, and hence performs better than or as good as an equivalent rate distortion encoder. As block length approaches infinity the performance of stochastic distortion encoder approaches rate distortion function. Formulations for optimal SDE design and results for block lengths 1,2 and 3 are also given.