Neural network vector quantizer design using sequential and parallel learning techniques

Many techniques for quantizing large sets of input vectors into much smaller sets of output vectors have been developed. Various neural-network-based techniques for generating the input vectors via system training are studied. The variations are centered around a neural-net vector quantization (NNVQ) method which combines the well-known conventional LBG technique and the neural-net-based Kohonen technique. Sequential and parallel learning techniques for designing efficient NNVQs are given. The schemes presented require less computation time due to a new modified gain formula, partial/zero neighbor updating, and parallel learning of the code vectors. Using Gaussian-Markov source and speech signal benchmarks, it is shown that these new approaches lead to distortion as good as or better than that obtained using the LBG and Kohonen approaches.