Acoustic model parameter estimation using distributed incremental adaptive networks

In this paper, we propose employing distributed incremental adaptive networks for the aim of acoustic signature identification, as a time-varying autoregressive (TVAR) stochastic model. A distributed adaptive sensor network considers spatio-temporal challenges simultaneously. By formulating the problem under non-stationary conditions, we proceed showing the superiority of the proposed incremental adaptive algorithm comparing to the classical single point observations methods. To practically prove this efficiency, the proposed algorithms are implemented on a real sensor network dataset recorded from moving vehicles, to be a substantial real-world validation test. The experimental results well support the claim and demonstrate the excellence and competence of distributed incremental adaptive networks for this case.