Skip to main content
Article
Real time noise-speech discrimination in time domain for speech recognition application
Scientific Research and Essays (2011)
  • Faisal Rafiq Mahamd Adikan, University of Malaya
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.
Keywords
  • noise-speech discrimination noisy signal local mean
Publication Date
January, 2011
Publisher Statement
you can e-mail to me for the full text of my jurnal at rafiq@um.edu.my
Citation Information
Faisal Rafiq Mahamd Adikan. "Real time noise-speech discrimination in time domain for speech recognition application" Scientific Research and Essays Vol. 6 Iss. 1 (2011)
Available at: http://works.bepress.com/faisalrafiq_mahamdadikan/13/