Physiologically Motivated Feature Extraction for Robust Automatic Speech Recognition

Abstract

In this paper, a new method is presented to extract robust speech features in the presence of the external noise. The proposed method based on two-dimensional Gabor filters takes in account the spectro-temporal modulation frequencies and also limits the redundancy on the feature level. The performance of the proposed feature extraction method was evaluated on isolated speech words which are extracted from TIMIT corpus and corrupted by background noise. The evaluation results demonstrate that the proposed feature extraction method outperforms the classic methods such as Perceptual Linear Prediction, Linear Predictive Coding, Linear Prediction Cepstral coefficients and Mel Frequency Cepstral Coefficients.

Authors and Affiliations

Ibrahim Missaoui, Zied Lachiri

Keywords

Related Articles

Securing Cognitive Radio Vehicular Ad Hoc Network with Fog Node based Distributed Blockchain Cloud Architecture

Cognitive radio, ad hoc networks' applications are continuously increasing in wireless communication globally. In vehicles' environment, cognitive radio technology with mobile ad hoc networks (MANETs) enables vehicles to...

User Perspective on External Value Creation Factors in Indonesia e-Commerce

Value creation is very important for the e-commerce companies in order to reach customers and increase company's value in the view of customer. Value creation mostly developed based on internal factor of the company. Thi...

Experimentation for Modular Robot Simulation by Python Coding to Establish Multiple Configurations

Most of the Modular Self-reconfigurable (MSR) robots are being developed in order to have the capability of achieving different locomotion gaits. It is an approach of robotic system which involving a group of identical r...

Video Compression by Memetic Algorithm

Memetic Algorithm by hybridization of Standard Particle Swarm Optimization and Global Local Best Particle Swarm Optimization is proposed in this paper. This technique is used to reduce number of computations of video co...

Non-Linear Energy Harvesting Dual-hop DF Relaying System over n-µ Fading Channels

In this work, we analyze a wireless energy harvest-ing decode-and-forward (DF) relaying network with beamforming that is based on a practical non-linear energy harvesting model over η-μ fading channels. We consider a dua...

Download PDF file
  • EP ID EP117836
  • DOI 10.14569/IJACSA.2016.070438
  • Views 89
  • Downloads 0

How To Cite

Ibrahim Missaoui, Zied Lachiri (2016). Physiologically Motivated Feature Extraction for Robust Automatic Speech Recognition. International Journal of Advanced Computer Science & Applications, 7(4), 297-301. https://europub.co.uk./articles/-A-117836