FR4.R3.4

Quasi-OSD of Binary Image of RS Codes with Applications to JSCC

Xiangping Zheng, Qianfan Wang, Baodian Wei, Xiao Ma, Sun Yat-sen University, China

Session:
List Decoding

Track:
1: Algebraic Aspects of Coding Theory

Location:
Ypsilon IV-V-VI

Presentation Time:
Fri, 12 Jul, 17:25 - 17:45

Session Chair:
Vinayak Ramkumar, Tel Aviv University
Abstract
THIS PAPER IS ELIGIBLE FOR THE STUDENT PAPER AWARD. We propose quasi ordered statistic decoding (quasi-OSD) of binary image of Reed-Solomon (RS) codes and explore the application of RS codes to joint source-channel coding (JSCC). Unlike the conventional OSD algorithms that use Gaussian elimination to obtain the systematic matrix, the proposed quasi-OSD algorithm utilizes the parallel Lagrange interpolation at the symbol level, which achieves a lower complexity and comparable performance compared with the locally constrained OSD (LC-OSD), for high-rate RS codes in the high signal-to-noise ratio (SNR) region. Additionally, we apply RS codes to the JSCC with known source statistics. At the transmitter, a new partition criterion is introduced in the classified enumerative (CE) coding to encode the source information. Then the multiple-rate RS coding transforms the variable-length codeword of the CE coding into a fixed-length transmitted codeword. At the receiver, parallel decoding is performed to recover the source. Simulation results demonstrate that the proposed JSCC scheme outperforms the double polar JSCC scheme by one dB, as expected by Gallager’s JSCC bound
Resources