Multi microphone Signal Processing Technique to Remove Room Reverberation with Unbiased Coherent-To-Diffuse Power Ratio Estimation

Abstract

In everyday humans encounter different types of speech communication applications, such as hands-free mobile telephony, voice-controlled systems, hearing aids etc, the recorded microphone signals are corrupted by background noise, room reverberation and far-end echo signals. The signal degradation can lead to total unintelligibility of the original speech signal and degrades the performance of automatic speech recognition systems. In this project the estimation of frequency and time-dependent coherent-to-diffuse power ratio (CDR) from the measured spatial coherence between two omni directional microphones were investigated. From traditional methods for unbiased CDR estimators it is shown that knowledge of either direction of arrival (DOA) of the target source or the coherence of noise field is sufficient for unbiased CDR estimation. A CDR-based dereverberation system is presented and evaluated using signal-based quality measures as well as automatic speech recognition accuracy.

Authors and Affiliations

Nikhil S

Keywords

Related Articles

Artificial Bee Colony algorithm using Structured Swarm

Swarm Intelligence is a meta-heuristic approach in the field of nature inspired techniques that is used to solve optimization problems. It is based on the collective behaviour of social creatures. Social creatures utili...

Recognition of American Sign Language Fingerspelling by Applying Matrix Matching Algorithm Using Leap Motion Controller Sensor

This paper presents the recognition of American Sign Language Fingerspelling by applying Matrix Matching algorithm using Leap Motion Controller Sensor. The study focused on the recognition of all the static and dynamic...

Development of Analogue Computer for the Simulation of Linear Circuits and Systems

In order to better understand the physical world, scientists use mathematical models to predict the reaction of various physical systems, such as the motion of a mass attached to a spring, to external stimuli. Such syst...

Analysis of Bulk Data from Social Media for Obtaining Public Sentiments

For every production house, getting an idea of how their movies are going to perform before release can be essential. A decade ago this would have been a very difficult task but now, the arrival social media has made it...

Curvelet Based Image fusion techniques for Medical Images

Image fusion integrates multiple images of the same scene from multiple image sensor data. It has acquired an integral role in medical field. This paper introduces the various means image fusion based on transform domai...

Download PDF file
  • EP ID EP22783
  • DOI -
  • Views 202
  • Downloads 3

How To Cite

Nikhil S (2016). Multi microphone Signal Processing Technique to Remove Room Reverberation with Unbiased Coherent-To-Diffuse Power Ratio Estimation. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 4(11), -. https://europub.co.uk/articles/-A-22783