Isolated Pali Word (IPW) Feature Extraction using MFCC & KNN Based on ASR
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2018, Vol 20, Issue 6
Abstract
Speech is most prominent & primary mode of Communication among human being. Past after years of research and development & the accuracy of automatic speech recognition remains the important challenges in research. The design of Speech Recognition system require careful attentions the following issues: Definition of various types of speech classes, speech representation, feature extraction techniques, speech classifier, and database and performance evaluation. The problems are existing in ASR and the various techniques to solve these problems constructed by various research work have been presented in a chronological order. The objective of this research paper is to summarize and compare some of the well-known methods used in various stages of speech recognition system and to identify research topic and applications which is front of this exciting and challenging field. In this paper is computed acoustic features using MFCC on ‘IPW’ Isolated Pali Word Database which contain collection of isolated number (0-10) and isolated month (Jan-Dec) words of 20 speakers. The performance of the isolated digit and month’s words based on MFCC and KNN classification were 80.36% and 81.83% respectively.
Authors and Affiliations
Siddharth S More, Prashant kumar L. Borde, Sunil S Nimbhore
Keywords
Related Articles
- EP ID EP423562
- DOI 10.9790/0661-2006026974.
- Views 94
- Downloads 0
A Quantitative Measurement of Software Requirement Factors using Goal Question Metric (GQM) Approach
Abstract: Every application software that we propose to develop can be thought of a group or collection of related requirements specified by the user and these requirements are the foundation from which the quality...
Improved Text Analysis Approach for Predicting Effects of Nutrient on Human Health using Machine Learning Techniques
Abstract : A text analysis method is introduced which processes the unstructured information from document collection in order to support efficient text classification and information extraction. The Information ex...
Dendritic Cell Algorithm and Dempster Belief Theory Based Approach for Intrusion Detection System
Abstract: Everyone knows the services of the Internet. Internet services contain large scale of data. Security is one of the important issues during transmission of data over the network. To avoid misuse of data an...
Encryption Technique for a Trusted Cloud ComputingEnvironment
With varying amount of computing power present with everyone, it has become necessity of the hour to usecloud computing systems. It helps us to store our data within a virtual cloud structure. When we use the cloud...
Detecting contiguous regions having traffic problems using taxi trajectories
Nowadays, taxi is one of the most popular transportation modes. There is a large amount of passenger using taxi everyday and taxi trajectories represent the mobility of people. In the big cities, taxi is equipped GPS dev...