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

Routing protocols in underground coalmine environment: A Review

Researchers have worked on routing issues for adhoc-networks, VANET’s, and Wireless Sensor Networks in a normal scenario; recently there has been a recent trend towards the study on underground wireless networks and prop...

A Symmetric FHE Scheme Based on Linear Algebra

FHE is considered to be Holy Grail of cloud computing. Many applications of cloud computing inherently need symmetric keys while very few FHE schemes have been proposed with symmetric keys. Even with the schemes based on...

A Secure Image Steganography Method Based on Neural Network

Steganography is the term used to describe the hiding of data in images to avoid detection by attackers. Steganalysis is the method used by attackers to determine if images have hidden data and to recover that data. By m...

CLASSIFICATION TECHNIQUES APPLIED FOR INTRUSION DETECTION

Intrusion detection system (IDS) was designed to monitor the network activity and it identifies the normal and abnormal behavioral pattern in the network. If there was any abnormal pattern, it indicates the system is in...

TOWARDS DEVELOPMENT OF CLOUD OPERATING SYSTEMS

Cloud operating system provides the abstraction of complex physical datacenter infrastructure by providing different interfaces for local and remote users. It manages the interaction between aplications and their interfa...

Download PDF file
  • EP ID EP120197
  • DOI -
  • Views 105
  • 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