Opens in a new tab

AES E-Library

← Back to search

Conference Paper

Speech Enhancement with Microphone Array Using Frequency-Domain Alignment Technique

Authors: Stolbov, Mikhail; Aleinik, Sergei

AES Conference: 54th International Conference: Audio Forensics · Paper 5-1 · June 2014

Abstract

A new adaptive technique for speech capturing in adverse conditions with microphone arrays is presented in this paper. The proposed technique is based on frequency-domain alignment of microphone signals with the output of fixed beamformer directed to the target speaker. This alignment procedure improves pattern directivity and reduces sidelobes. The low complexity of the technique is achieved by means of frequency-domain implementation of algorithms. This makes it possible to implement this technique in real-time forensic applications with a large number of microphones. This technique was evaluated on speech data corrupted by varying levels and directions of noise and interference. Experimental results with an 8-microphone array show suppression of diffuse noise by about 23 dB and suppression of wide band interference up to 17 dB.

Details

Published in
AES Conference: 54th International Conference: Audio Forensics
Paper number
5-1
Publication date
June 6, 2014
Session subject
Speech Intelligibility
Affiliation
National Research University of Information Technologies, Mechanics and Optics, St. Petersburg, Russia; Speech Technology Center, St. Petersburg, Russia (See document for exact affiliation information.)
Type
Conference Paper