Matrix computations (3rd ed.)
Parallel and Distributed Computation: Numerical Methods
Parallel and Distributed Computation: Numerical Methods
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Robust distributed noise reduction in hearing aids with external acoustic sensor nodes
EURASIP Journal on Advances in Signal Processing - Special issue on digital signal processing for hearing instruments
IEEE Transactions on Signal Processing
Diffusion Least-Mean Squares Over Adaptive Networks: Formulation and Performance Analysis
IEEE Transactions on Signal Processing - Part II
Optimal dimensionality reduction of sensor data in multisensor estimation fusion
IEEE Transactions on Signal Processing
Incremental Adaptive Strategies Over Distributed Networks
IEEE Transactions on Signal Processing
Distributed Estimation Using Reduced-Dimensionality Sensor Observations
IEEE Transactions on Signal Processing
Diffusion Recursive Least-Squares for Distributed Estimation Over Adaptive Networks
IEEE Transactions on Signal Processing
Reduced-Bandwidth and Distributed MWF-Based Noise Reduction Algorithms for Binaural Hearing Aids
IEEE Transactions on Audio, Speech, and Language Processing
IEEE Transactions on Signal Processing
Location Feature Integration for Clustering-Based Speech Separation in Distributed Microphone Arrays
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
| Hi-index | 35.69 |
In this paper, we revisit an earlier introduced distributed adaptive node-specific signal estimation (DANSE) algorithm that operates in fully connected sensor networks. In the original algorithm, the nodes update their parameters in a sequential round-robin fashion, which may yield a slow convergence of the estimators, especially so when the number of nodes in the network is large. When all nodes update simultaneously, the algorithm adapts more swiftly, but convergence can no longer be guaranteed. Simulations show that the algorithm then often gets locked in a suboptimal limit cycle. We first provide an extension to the DANSE algorithm, in which we apply an additional relaxation in the updating process. The new algorithm is then proven to converge to the optimal estimators when nodes update simultaneously or asynchronously, be it that the computational load at each node increases in comparison with the algorithm with sequential updates. Finally, based on simulations it is demonstrated that a simplified version of the new algorithm, without any extra computational load, can also provide convergence to the optimal estimators.