Financial Transactions in ATM Machines using Speech Signals

Abstract

Speech is the natural and simp lest way of co mmunicat ion and Speech Recognition is a fascinating application of Dig ital Signal Processing which has many real-world applicat ions. In this paper, a speech recognition system is developed for Automated Teller Mach ines (ATMs) using Wavelet Packet Decomposition (WPD) and Artificial Neural Networks (ANN). Speech signals are one-dimensional and are random in nature. ATM machines communicate with the customers using the stored speech samples and the user communicates with the mach ine using spoken digits. Daubechies wavelets are employed here. A mu ltilayer neural network trained with back propagation training algorith m is used for classification purpose. The proposed method is implemented for 500 speakers uttering 10 spoken digits in English. The experimental results show good recognition accuracy of 87.38% and the efficiency of co mbin ing these two techniques.