Efficient Speech Recognition System for Isolated Digits

Abstract

In this paper, an efficient speech recognition system is proposed for speaker-independent isolated digits (0 to 9). Using the Weighted MFCC (WMFCC), low computational overhead is achieved since only 13 weighted MFCC coefficients are used. In order to capture the trends of the extracted features, the local and global features are computed using the Improved Features for Dynamic Time Warping (IFDTW) algorithm. In this work, we propose to reduce the time complexity of the recognition system by time-scale modification using a SOLA-based technique and also by using a faster implementation of IFDTW. The experiments based on TI-Digits corpus demonstrate the effectiveness of proposed system giving higher recognition accuracy of 99.16% and performing about 22 times faster than conventional techniques.

Authors and Affiliations

Santosh V. Chapaneri , Dr. Deepak J. Jayaswal

Keywords

Related Articles

STUDY OF SERVER LOAD BALANCING TECHNIQUES

One of the critical scheduling problems in distributed computing environment is load balancing on a cluster of replicated servers which face a constant pressure of increased network traffic and diverse load levels. The k...

Energy Efficient Techniques In Virtualized Data Center: A Survey

Energy efficiency simply means that how efficiently energy can be used or consumed by any virtualized datacenters providing cloud services. Main aim of energy efficiency is to reduce the amount of energy consumed or requ...

Remote Wireless Automation and Monitoring of Large Farm using wireless sensors networks and Internet

The work includes designing and programming a control panel to watch and control the network by using LabView program which views changes values of the farm as well as the real values required for controlling max. and mi...

Survey on a Novel approach for Reversible Data Hiding: Principles, Techniques and Recent studies

Today data hacking is a very big problem in networking field. There are many security techniques are available for solving the problem. One of these data-hiding, using this concept we can provide security, authentication...

Novel Approach for Detection of Brain Tumor using Segmentation Techniques

Medical Image Processing is one of the standard method to detect the abnormal tissue. The key benefit of this field is reduction of manual work and early detection of the disease. Various types of medical imaging modalit...

Download PDF file
  • EP ID EP120197
  • DOI -
  • Views 103
  • Downloads 0

How To Cite

Santosh V. Chapaneri, Dr. Deepak J. Jayaswal (2013). Efficient Speech Recognition System for Isolated Digits. International Journal of Computer Science & Engineering Technology, 4(3), 228-236. https://europub.co.uk/articles/-A-120197