Distributed labelling of audio sources in wireless acoustic sensor networks using consensus and matching

In this paper, we propose a new method for distributed labelling of audio sources in wireless acoustic sensor networks (WASNs). We consider WASNs comprising of nodes equipped with multiple microphones observing signals transmitted by multiple sources. An important step toward a cooperation between the nodes, e.g. for a voice-activity-detection, is a network-wide consensus on the source labelling such that all nodes assign the same unique label to each source. In this paper, a hierarchical approach is applied such that first a network clustering algorithm is performed and then in each sub-network, the energy signatures of the sources are estimated using a non-negative independent component analysis over the energy patterns observed by the different nodes. Finally the source labels are obtained by an iterative consensus and matching algorithm, which compares and matches the energy signatures estimated in different sub-networks. The experimental results show the effectiveness of the proposed method.

[1]  Mark D. Plumbley,et al.  BLIND SEPARATION OF POSITIVE SOURCES USING NON-NEGATIVE PC A , 2003 .

[2]  James R. Glass,et al.  Non-Negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[3]  Stephen P. Boyd,et al.  Fast linear iterations for distributed averaging , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[4]  Marc Moonen,et al.  Unsupervised diffusion-based LMS for node-specific parameter estimation over wireless sensor networks , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Jont B. Allen,et al.  Image method for efficiently simulating small‐room acoustics , 1976 .

[6]  Marc Moonen,et al.  Blind sampling rate offset estimation based on coherence drift in wireless acoustic sensor networks , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[7]  Hugo Van hamme,et al.  Speaker age estimation using Hidden Markov Model weight supervectors , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[8]  Georgios B. Giannakis,et al.  Distributed Clustering Using Wireless Sensor Networks , 2011, IEEE Journal of Selected Topics in Signal Processing.

[9]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[10]  Marc Moonen,et al.  Energy-based multi-speaker voice activity detection with an ad hoc microphone array , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Dimitri P. Bertsekas,et al.  Auction algorithms for network flow problems: A tutorial introduction , 1992, Comput. Optim. Appl..

[12]  Alexander Bertrand,et al.  Applications and trends in wireless acoustic sensor networks: A signal processing perspective , 2011, 2011 18th IEEE Symposium on Communications and Vehicular Technology in the Benelux (SCVT).

[13]  Abdelhak M. Zoubir,et al.  Generalized Bayesian Information Criterion for Source Enumeration in Array Processing , 2013, IEEE Transactions on Signal Processing.

[14]  Marc Moonen,et al.  Distributed signal estimation in a wireless sensor network with partially-overlapping node-specific interests or source observability , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Israel Cohen,et al.  Distributed Multiple Constraints Generalized Sidelobe Canceler for Fully Connected Wireless Acoustic Sensor Networks , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[16]  Meir Feder,et al.  Multi-channel signal separation by decorrelation , 1993, IEEE Trans. Speech Audio Process..

[17]  Sergios Theodoridis,et al.  Distributed robust labeling of audio sources in heterogeneous wireless sensor networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Marc Moonen,et al.  Distributed computation of the Fiedler vector with application to topology inference in ad hoc networks , 2013, Signal Process..

[19]  Marc Moonen,et al.  Blind separation of non-negative source signals using multiplicative updates and subspace projection , 2010, Signal Process..