Yazar "Halis Altun" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Accurate parameter estimation for an articulatory speech synthesizer with an improved neural network mapping
    (2001) Halis Altun; Tankut Yalçınöz; K. Mervyn Curtıs
    Neural network (NN) applications have recently been employed to extract the parameters of an articulatory speech synthesizer from a given speech signal. Results from these attempts showed that a single NN is insufficient to cover all of the possible configurations uniquely. Moreover, apart from their computational advantages, NN mapping is so far not superior to the other mapping techniques [1]. Thus there is a clear need to improve NN solution to the inverse problem. Results from our earlier experiments with an articulatory speech synthesizer have shown that the statistical characteristic of the articulatory target pattern vectors can be exploited for an improvement in the estimation performance of a Multi-Layer Perceptron (MLP) NN [2]. In this paper, the effect of the modification to the distribution characteristic of the acoustic input pattern vectors will be investigated. The theoretical background for the effect of the input distribution characteristics on neural learning has been detailed elsewhere [3]. Empirical results for a more correct estimation of articulatory speech synthesizer parameters through exploiting the behavior of the Back Propagation (BP) algorithm are focused on here.
  • Küçük Resim Yok
    Öğe
    Comparison of simulation algorithms for the Hopfield neural network: An application of economic dispatch
    (2000) Tankut Yalçınöz; Halis Altun
    This paper is mainly concerned with an investigation of the suitability of Hopfield neural network structures in solving the power economic dispatch problem. For Hopfield neural network applications to this problem three important questions have been answered: what the size of the power system is; how efficient the computational method; and how to handle constraints. A new mapping process is formulated and a computational method for obtaining the weights and biases is described. A few simulation algorithms used to solve the dynamic equation of the Hopfield neural network are discussed. The results are compared with those of a classical technique, Hopfield neural network approaches and an improved Hopfield neural network approach [1].