Multilayered network for LPC based speech recognition

This paper presents efficient artificial neural network based linear predictive coding. Speech recognition is fundamentally pattern classification task. The objective is to input pattern, the speech and classify a sequence of patterns. The linear predictive coefficients of the slowly varying speech signals are stored. A feedforward network is determined by linear predictive coefficients. A three layered feedforward network was used with back propagation as the training algorithm. The network and learning techniques are proved for their correctness and applied to the problem of speech recognition. The suggested novel scheme yields results in finite accuracy and recognition performance.