Speech file compression by eliminating unvoiced/silence components

Abstract

The main objective of this study is to have noise component of a speech signal eliminated and compressing it by storing the locations and durations of silence regions. The separation between voiced, unvoiced, and silence regions are done by using the Short Time Energy (STE) and Zero Crossing Rate (ZCR) methodologies. All operations in this study have been performed by using the User Interface (UI) developed on MATLAB^®. These operations include voice recording, playing the recording, eliminating the unwanted regions, playing the modified recording, saving of original and compressed files and loading the recording compressed.