Speech Recognition in ATMs: Application of Linear Predictive Coding and Support Vector Machines
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2017, Vol 5, Issue 3
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
- EP ID EP23295
- DOI http://doi.org/10.22214/ijraset.2017.3100
- Views 284
- Downloads 9
Modelling Of Gas Turbine Rotor Blade with Internal Cooling Passages
Gas turbines are extensively used for land-based power generation, aircraft propulsion and industrial applications. The turbine blade temperature plays a critical role in developing the thermal efficiency and power outp...
slugDesign of Remote Monitoring System for the Detection of Vital Signs
Chronic heart failure (CHF) patients are commonly addicted to frequent hospital admissions. They should be constantly monitored for that sake they should be admitted in hospital. But frequent...
Basics of Marketing Management
This paper deals with basics of the marketing process, marketing concept and marketing mix i.e. product, price, place and promotion. Marketing is the business function that identifies unfulfilled needs and wants, and he...
Domain Based Categorisation Using Adaptive Preprocessing
As the number users accessing network for various purposes increases and simultaneously size of the Network and Internet traffic increase so, there is need for categorization web pages according to domain for easy acces...
A Survey on Efficient Object Localization and Image Classification for Thumbnail Browsing
Nowadays, with an increasing demand of advanced intelligent systems, computer vision applications dealing with foreground objects are becoming more challenging. The common assumption taken into consideration in most of...