Distributed robust labeling of audio sources in heterogeneous wireless sensor networks
Symeon Chouvardas, Michael Muma, Khadidja Hamaidi, Sergios Theodoridis, Abdelhak M. Zoubir
Abstract
A novel algorithm for distributed labeling of speech sources is proposed. We consider a wireless sensor network comprising devices that are equipped with multiple microphones, which can “hear” a number of speech signals. The labeling task is performed in a decentralized fashion with a new two-step approach. The first step corresponds to the distributed extraction of proper source-specific features from the mixed signals. In the second step, these features are exploited via a distributed unsupervised learning technique. We present approaches that can be used in hierarchically organized or in non-hierarchically organized network configurations. Numerical examples using real data display the performance of the proposed technique.
BibTeX
@inproceedings{icassp2015_distributedrobus,
title = {Distributed robust labeling of audio sources in heterogeneous wireless sensor networks},
author = {Symeon Chouvardas and Michael Muma and Khadidja Hamaidi and Sergios Theodoridis and Abdelhak M. Zoubir},
booktitle = {ICASSP 2015},
year = {2015}
}