Research Article Open Access

Feature Extraction Method for Improving Speech Recognition in Noisy Environments

Youssef Zouhir1 and Kaïs Ouni1
  • 1 University of Carthage, Tunisia

Abstract

The paper presents a feature extraction method, named as Normalized Gammachirp Cepstral Coefficients (NGCC) that incorporates the properties of the peripheral auditory system to improve robustness in noisy speech recognition. The proposed method is based on a second order low-pass filter and normalized gammachirp filterbank to emulate the mechanisms performed in the outer/middle ear and cochlea. The speech recognition performance of this method is conducted on the speech signals in real-world noisy environments. Experimental results demonstrate that method outperformed the classical feature extraction methods in terms of speech recognition rate. The used Hidden Markov Models based speech recognition system is employed on the HTK 3.4.1 platform (Hidden Markov Model Toolkit).

Journal of Computer Science
Volume 12 No. 2, 2016, 56-61

DOI: https://doi.org/10.3844/jcssp.2016.56.61

Submitted On: 20 December 2015 Published On: 25 March 2016

How to Cite: Zouhir, Y. & Ouni, K. (2016). Feature Extraction Method for Improving Speech Recognition in Noisy Environments. Journal of Computer Science, 12(2), 56-61. https://doi.org/10.3844/jcssp.2016.56.61

  • 3,032 Views
  • 2,370 Downloads
  • 16 Citations

Download

Keywords

  • Feature Extraction
  • Peripheral Auditory Model
  • Hidden Markov Models
  • Noisy Speech Recognition