Speaker Independent Recognition System with Mouse Movements
Journal Title: International Journal of P2P Network Trends and Technology(IJPTT) - Year 2012, Vol 2, Issue 1
Abstract
Speech recognition is potentially a multi-billion dollar industry in the near future. It is a natural alternative interface to computers for people with limited mobility in their arms and hands, sight, hearing limitation. For most current voice-mail systems, one has to follow series of touch-tone button presses to navigate through a hierarchical menu. Speech Recognition has the potential to cut through the menu hierarchy. Recently, neural networks have been considered for speech recognition tasks since in many cases they have shown comparable performance than the traditional approaches. There are two in-built threads in the recognition system. Thread 1 maintains the details about input acquisition where as thread 2 contains the classifier and decoder. The classifier used in this research is Radial Basis Function Neural Networks. The HMM graph is used as a decoder. The objective of the research is to make sure that the system is free from bugs. 100% accuracy is achieved by the recognition system.
Authors and Affiliations
Dr. R. L. K. Venkateswarlu#1 , Dr. R. Vasantha Kumari*2 , G. Vani JayaSri#3
Keywords
Related Articles
- EP ID EP98507
- DOI -
- Views 116
- Downloads 0
Methodology for Artificial Immune Systems and Immune Pathology
Artificial immune system (AIS) mimics the superior properties of biological immune system and provides an effective method in intelligent computing and intelligent system designing. But the disease-causing mechanis...
An Efficient Data Hiding Technique for Steganography
Bose Chaudhuri Hochquenghem (BCH) based data hiding scheme for JPEG steganography is presented. Traditional data hiding approaches hide data into each block, where all the blocks are not overlapping each other. Two conse...
Classification algorithm in Data mining: An Overview
Data Mining is a technique used in various domains to give meaning to the available data Classification is a data mining (machine learning) technique used to predict group membership for data instances. In this pap...
Anomaly Intrusion Detection System using Random Forests and k-Nearest Neighbor
This paper proposed a new approach to design the anomaly intrusion detection system using not only misuse but also anomaly intrusion detection for both training and detection of normal or attacks respectively. The...
A Survey on Hierarchical Routing Protocols in Wireless Sensor Networks
There is several issues in Wireless Sensor Networks from which routing are also a major issue which is directly related to energy consumption. In order to increase the lifetime of network energy must be consumed...