A Powerful Method for Extracting the Original Signal from the Noisy Input Signal by using the Iterative Reconstruction Framework of the Short Time Fourier Transformation

Abstract

In the current system for the reconstruction of speech, it is used iterative reconstruction framework of short time Fourier transformation (STFT). When a lot of noise is added to the input speech, the iterative reconstruction framework of STFT can not properly reconstruct the input speech. In this paper, we offer a method that by using it, we will be able to extract the original signal from the noisy input signal. For achieving this goal, in each step of the iterative reconstruction of input speech, by taking a threshold value For magnitude spectrum, we remove the smaller amounts of threshold and for preserving the original signal features, we consider the phase spectrum then with combination of the modified magnitude spectrum information and the phase spectrum information, we reconstruction part of the signal in each iteration. Two experiments were examined. In the first experiment, we evaluated the reconstruction of input speech with changing the threshold value and in the second experiment, we evaluated the reconstruction of input speech with different numbers of iterations. The results showed that by using our method, when a lot of noise is added to the input speech, we can reconstruct the original signal very well.

Authors and Affiliations

Saeed Karimi

Keywords

Related Articles

Stabilization of Black Cotton Soil by Using Waste Foundry Sand and Crushed Waste Glass

Generally Black Cotton Soil exhibits undesirable engineering properties like shrinkage and swelling properties losses its strength, when come in contact with water. Thereby poor bearing capacity and higher compressibilit...

A Deep Neural Network Approach to Detect and Classify Skin Cancer

Among all cancers, skin cancer is one of the serious disease which effects major population across the globe. If the detection and diagnosis would not happen in early stages it can be spread to other body parts rapidly f...

Measurement and Implementation of Patient Satisfaction in the Healthcare Industry: Part 2

Increasingly knowledgeable consumers, with rising demands to have information available for them to make appropriate health care decisions, have driven healthcare managers and administrators to focus on an improvement of...

A Review on Smart City Using IOT

The Internet of the Things is a network that connects various gadgets and technologies without requiring human interaction. As a consequence, cities that are wiser (or more intelligent) may be constructed all over the gl...

Speed Control of DC Motor Using ACO Based FOPID Controller

Direct current (DC) motors are widely used because of their easily controllable and reliable access. DC motors have many salient features that includes a wide range of torque speed control, reliable operation with greate...

Download PDF file
  • EP ID EP748552
  • DOI -
  • Views 31
  • Downloads 0

How To Cite

Saeed Karimi (2016). A Powerful Method for Extracting the Original Signal from the Noisy Input Signal by using the Iterative Reconstruction Framework of the Short Time Fourier Transformation. International Journal of Innovative Research in Computer Science and Technology, 4(3), -. https://europub.co.uk/articles/-A-748552