Vector quantization using frequency-sensitive competitive-learning neural networks
Stanley C. Ahalt, Ashok Kumar Krishnamurthy, Prakoon Chen et al. · International Conference on Systems Engineering · 1989
We present a training algorithm for a competitive learning network. This algorithm is applied to the problem of vector quantization using neural networks. An important advantage of using neural networks for vector quantization is that the computat.ions can be carried out in parallel by the neural units. The performance of this algorithm is compared with other neural network and traditional non-neural algorthims for vector quantization. The basic properties of the new algorithm are discussed and we present the results of quantizing vectors of Linear Prediction Coefficients from a speech signal and show that our net yields results which are comparable to the traditional algorithm.
Cited by 0 works.