Efficient Speech Recognition System for Isolated Digits
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2013, Vol 4, Issue 3
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
- EP ID EP120197
- DOI -
- Views 100
- Downloads 0
Detect and prevent HELLO FLOOD Attack using Centralized technique in WSN
In wireless sensor networks, wirelessly nodes communicate with each other. WSN is a very large array of diverse sensor nodes that are interconnected by a communication network . The battery lifetime of nodes in wireless...
Fault Tolerance in Wireless Sensor Networks using Stiffed Delaunay Triangulation
In this chapter, we introduce fault tolerance in Wireless Sensor Networks. Firstly, we start with a short description of sensor networks, fault tolerance and its different techniques. Then we discuss the different phases...
A COMPARATIVE STUDY OF CLOUDS IN CLOUD COMPUTING
Cloud computing has now become one of the rapidly growing technologies in computer science. Cloud Computing makes its greatest impact on the IT ecosystem. It refers to the delivery of services like hardware, software, st...
Remote Based Security System
Background Subtraction is one of the vital image handling steps for video surveillance and many computer vision difficulties such as recognition, classification, activity investigation &tracking. Detection of moving...
Enhancing Efficiency and Accuracy of Imbalanced Datasets Using Fuzzy Neural Network
In Data Mining the class Imbalance classification problem is considered to be one of the emergent challenges. This problem occurs when the number of examples that represents one of the classes of the dataset is much lowe...