Neural Network Based Adaptive Microphone Array System for Speech Enhancement

Document type: Conference Papers
Peer reviewed: Yes
Author(s): Nedelko Grbic, Mattias Dahl, Ingvar Claesson
Title: Neural Network Based Adaptive Microphone Array System for Speech Enhancement
Conference name: IEEE World Congress on Computational Intelligence
Year: 1998
Pagination: 2180-3 vol.3
ISBN: 0-7803-4859-1
City: Anchorage, USA
ISI number: 000074493400397
Organization: Blekinge Institute of Technology
Department: Dept. of Signal Processing (Institutionen för signalbehandling)
Dept. of Signal Processing S-372 25 Ronneby
+46 455 38 50 00
Language: English
Abstract: Presents a microphone array system for use in handsfree mobile telephone equipment. The array is based on a fast and efficient “on-site” and “self-calibration” scheme. The performance in suppressing the interior car cabin noise and the far-end speech is approximately 17 dB, respectively, while maintaining the near-end speaker level. The near-end signal is almost undistorted. The performance of two different algorithms, normalized least-mean-square (NLMS) and fully connected backpropagation supervised neural network (MLP-NN) are evaluated. The proposed microphone array calibration scheme can also be used in other situations such as speech recognition devices.
Subject: Signal Processing\General
Keywords: acoustic transducer arrays, adaptive filters, backpropagation, calibration, echo suppression, land mobile radio, least mean squares methods, microphones, multilayer perceptrons, radio equipment, speech enhancement, telecommunication computing