A Neural Network Trained Microphone Array System for Noise Reduction

Document type: Conference Papers
Peer reviewed: Yes
Author(s): Mattias Dahl, Ingvar Claesson
Title: A Neural Network Trained Microphone Array System for Noise Reduction
Conference name: 1996 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing (NNSP96)
Year: 1996
Pagination: 311-319
Publisher: IEEE
City: Kyoto, Japan
ISI number: A1996BG22Q00032
Organization: Blekinge Institute of Technology
Department: Dept. of Signal Processing (Institutionen för signalbehandling)
Dept. of Signal Processing S-372 25 Ronneby
+46 455 780 00
Authors e-mail: Mattias.Dahl@isb.hk-r.se
Language: English
Abstract: This paper presents a neural network based microphone array system, which is capable to continuously perform speech enhancement and adaptation to nonuniform quantization, such as A-law and $mu@-law. Such a quantizer is designed to increase the Signal to Quantization Noise Ratio (SQNR) for small amplitudes in telecommunications systems. The proposed method primarily developed for hands-free mobile telephones, suppresses the ambient car noise with approximately 10 dB. The system is based upon a multi-layered nonlinear back-propagation trained network by using a built-in calibration technique.
Subject: Signal Processing\Beamforming
Signal Processing\Speech Enhancement
Keywords: Microphones, Interference suppression, Speech analysis, Signal to noise ratio, Cellular telephone systems, Backpropagation, Algorithms