UTHM Institutional Repository

Speech signal transformation with FS variation technique for military purposes

Azizi, Azmaliza and Sulong, Muhammad Suhaimi and Ab Rahman, Tasiransurini and Ismail, Nurulhuda and Joret, Ariffuddin (2010) Speech signal transformation with FS variation technique for military purposes. In: 3rd Engineering Conference on Advancement in Mechanical and Manufacturing for Sustainable Environment, 14-16 April 2010, Kuching, Sarawak.


Download (278kB)


Security in human identification system has become a major concern nowadays, especially for sending information verbally. Therefore, the need of protecting the internal factor especially human speech is a main objective in this study. The characteristics of the human speech using several methods has been continuously practiced are outlined, for instance ceptral analysis, linear prediction coding, and the Pitch Synchronous Overlap-Add (PSOLA) method. This paper described the used of frequency sample variation, FSV technique to transform speech signal to a deeper, higher or lower tone. The analysis using PSOLA method with this technique and Matlab as GUI has been performed. The developed system is capable of transforming the input speech into three types of output speech namely male, female and child. The results show that the system is successfully and effectively portray different people with realistic gender changes to conceal the identity. It is said to be a potential system for any kind of security particularly by disguising the character of the voice. The alterations with other voice variable are going to be a further development.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: speech signal transformation; PSOLA method; matlab
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Electrical and Electronic Engineering > Department of Computer Engineering
Depositing User: Normajihan Abd. Rahman
Date Deposited: 26 Feb 2013 04:15
Last Modified: 21 Jan 2015 07:57
URI: http://eprints.uthm.edu.my/id/eprint/3295
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item


Downloads per month over past year