TITLE

Simultaneous Suppression of Noise and Reverberation by Applying a Two Stage Process

pdf PDF

ABSTRACT

In speech processing, reflections of sound wave in a bounded space have considered as speech reverberation. Although for musical instruments and their related recording devices these reflections are useful, however, some other applications face serious problems receiving them along with speech signal. Reverberation causes speech degradation and unintelligibility as well as quality reduction. Dereverberation algorithms are essential for Automatic Speech Recognition (ASR), telecommunication and hearing aid devices, which are some of the mostly used applications. Even though dereverberation itself is a challenging issue, dereverberating a speech signal recorded only by one microphone (or channel) requires more attention and resolution. Aside from that, in acoustic environments, interference signals such as White Gaussian Noise and any other type of noise decrease the quality of received signal even more. In this paper, we propose a two stage algorithm for enhancement of reverberant speech from one microphone recordings. In the first stage, Kalman filter has been employed to reduce the effects of noise on received speech signal. In this stage, different values of SNR of additive White Gaussian Noise have been practiced on a reverberated speech signal. Furthermore, the results of noise reduction stage have been compared to show the grade of effectiveness of each adaptive filter. In the second stage, an inverse filter has been applied for reducing the reverberation’s effect on received speech signal.

KEYWORDS

Speech Signal, Reverberation, Noisy Acoustic Environments, Single-Channel, Dereverberation, Adaptive Filter

 

Cite this paper

Marjan Joorabchi, Seyed Ghorshi, Ali Sarafnia. (2018) Simultaneous Suppression of Noise and Reverberation by Applying a Two Stage Process. International Journal of Signal Processing, 3, 38-48

 

cc.png
Copyright © 2018 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0