Speaker Identification using Frequency Dsitribution in the Transform Domain
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2012, Vol 3, Issue 2
Abstract
In this paper, we propose Speaker Identification using the frequency distribution of various transforms like DFT (Discrete Fourier Transform), DCT (Discrete Cosine Transform), DST (Discrete Sine Transform), Hartley, Walsh, Haar and Kekre transforms. The speech signal spoken by a particular speaker is converted into frequency domain by applying the different transform techniques. The distribution in the transform domain is utilized to extract the feature vectors in the training and the matching phases. The results obtained by using all the seven transform techniques have been analyzed and compared. It can be seen that DFT, DCT, DST and Hartley transform give comparatively similar results (Above 96%). The results obtained by using Haar and Kekre transform are very poor. The best results are obtained by using DFT (97.19% for a feature vector of size 40).
Authors and Affiliations
Dr. H B Kekre , Vaishali Kulkarni
Keywords
Related Articles
- EP ID EP140283
- DOI -
- Views 117
- Downloads 0
Dynamic Time Warping and FFT: A Data Preprocessing Method for Electrical Load Forecasting
For power suppliers, an important task is to accurately predict the short-term load. Thus many papers have introduced different kinds of artificial intelligent models to improve the prediction accuracy. In recent years,...
An Evaluation of the Proposed Framework for Access Control in the Cloud and BYOD Environment
As the bring your own device (BYOD) to work trend grows, so do the network security risks. This fast-growing trend has huge benefits for both employees and employers. With malware, spyware and other malicious downloads,...
Phishing Websites Classification using Hybrid SVM and KNN Approach
Phishing is a potential web threat that includes mimicking official websites to trick users by stealing their important information such as username and password related to financial systems. The attackers use social eng...
Current Trends and Research Challenges in Spectrum-Sensing for Cognitive Radios
The ever increasing demand of wireless communication systems has led to search of suitable spectrum bands for transmission of data. The research in the past has revealed that radio spectrum is under-utilized in most of t...
Image Blocks Model for Improving Accuracy in Identification Systems of Wood Type
Image-based recognition systems commonly use an extracted image from the target object using texture analysis. However, some of the proposed and implemented recognitionues systems of wood types up to this time have not b...