Full Length Research Paper
Abstract
A simple noise-speech discrimination method in time domain is presented. The random signal noise characteristics were studied in time domain. Using the characteristics information, in real time processing, a simple algorithm to detect starting and ending point of speech samples in time domain is being demonstrated. Out of 100 attempts, about 94% of successful attempts of noise-speech discrimination have been obtained with white noise background by choosing the critical thresholds values.
Key words: Noise-speech discrimination, noisy signal, local mean.
Copyright © 2024 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0