Financial Transactions in ATM Machines using Speech Signals
Journal Title: International Journal of engineering Research and Applications - Year 2017, Vol 7, Issue 1
Abstract
Speech is the natural and simplest way of communication and Speech Recognition is a fascinating application of Digital Signal Processing which has many real-world applications. In this paper, a speech recognition system is developed for Automated Teller Machines (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 machine using spoken digits. Daubechies wavelets are employed here. A multilayer neural network trained with back propagation training algorithm 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 combining these two techniques.
Authors and Affiliations
Dr. Sonia Sunny
Keywords
Related Articles
- EP ID EP389849
- DOI 10.9790/9622-0701042528.
- Views 192
- Downloads 0
Ergonomic Design of Arc Welding Workstation Using Younger Age Group Operators
Industrial jobs involving arm posture have a strong association with musculoskeletal disorders and injuries. It also affects the performance and effort (i.e. effort in holding, lifting, and lowering, etc.) of the worker....
Compressive and Split Tensile Strength Characteristics of Silica Fume Modified Fiber Reinforced Concrete
The Cement mainly consumes approximately 10 -15 % of total industrial energy. This energy releases carbon dioxide co2 emission to atmosphere as a result of burning fuels to produce energy needed for cement manufacturing...
Software For The Implementation Of Virtual Lab For Developing Experimental Skills In Courses Of General Chemistry
This paper describes how the use of a group of Virtual Labs favors the development of the experimental skills, contemplated within the General Chemistry Discipline Program; the software was designed and implemented by a...
Study of Statistical Parameters through Image Analysis Technique of 16ABBA Liquid Crystal
Study of statistical parameters of azomethine ester, 4-hexadecyloxy benzylidene-4’-bromoaniline (16ABBA) liquid crystal with image analysis technique is reported in this paper. Textures of the sample are recorded with po...
A Novel Scheduler Framework for 802.11ac
Due to the unpredictable nature of the CSMA/CA media access mechanism in WLANs and also, as WLANS operate in the unlicensed band, assuring time bound guarantees for multimedia applications has always been a challenge. Al...