Speech Recognition in ATMs: Application of Linear Predictive Coding and Support Vector Machines

Abstract

Today, Automated Teller Machines (ATMs) are extensively used by people for financial transactions. It provides a convenient, fast and easy way for customers to access cash. In this paper, a speech recognition system is developed for financial transactions in ATMs using Linear Predictive Coding (LPC) and Support Vector Machines (SVM). Voice signals are sampled directly from the microphone and then they are processed using LPC for extracting the features. Training, testing and pattern recognition are performed using Support Vector Machines. The proposed method is implemented for 200 speakers uttering 10 spoken digits in English. This hybrid architecture of LPC and SVM produced rather good recognition accuracy of 80.25%.

Authors and Affiliations

Dr. Sonia Sunny, Sreekala M

Keywords

Related Articles

slugA Study on Dynamic Skyline Queries

Skyline computation has recently received considerable attention in database community, especially for retrieving set of interesting points from large database i.e., it return a set of points that are not dominated by a...

A 4-Dimensional Parity based Data Decoding Scheme for EDAC in Communication Systems

The applications and use of hardware in wireless communication is increasing day by day. Portability of systems with data integrity during communication is the basic need of the systems in communication technology. This...

Design of Endplate to Improve the Rate of Pressure Distribution in Fuel Cell

A proper stacking design and cell assembly are important to the performance of fuel cells. The cell assembly will affect the contact behaviour of the bipolar plates with the membrane electrode assembly (MEA). Not enough...

Modelling & Analysis of Shunt Active Power Filter for Thd Reduction of Input Source Current in 12-Pulse Rectifier Circuit Load

In this paper we have presented a MATLAB-SIMULINK model of Shunt Active Power Filter, and 12-pulse rectifier circuit. We have discussed the design of the 12-pulse rectifier for input harmonics reduction with negligible...

Can Based Data Display Unit Using Arm

this paper presents an overview of controller area network (CAN), its protocol and standards. CAN was developed by Robert Bosch in 1986 as a multi-master, message broadcast system specifically designed for automotive ap...

Download PDF file
  • EP ID EP23295
  • DOI http://doi.org/10.22214/ijraset.2017.3100
  • Views 290
  • Downloads 9

How To Cite

Dr. Sonia Sunny, Sreekala M (2017). Speech Recognition in ATMs: Application of Linear Predictive Coding and Support Vector Machines. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(3), -. https://europub.co.uk/articles/-A-23295