Spline Adaptive Exponential Functional Link Filter for Nonlinear Acoustic Echo Cancellation

The paper discusses the challenge posed by nonlinear distortions in preserving the quality of audio and speech signals. This research involves a comprehensive analysis to determine the optimal approach for Nonlinear Acoustic Echo Cancellation (NAEC) and audio signal processing. The experimental results are evaluated not only in terms of signal quality but also in relation to its intelligibility. To tackle this issue, nonlinear models are employed, and spline-based estimation has drawn attention from the scientific community due to its promising performance in system identification and various tasks. We propose a novel framework centered around a Functional Link Adaptive Filter (FLAF), designed for different classes of nonlinear systems. This framework improves the performance consistency by incorporating a Functional Expansion Block (FEB) before the spline nonlinearity. Our simulations demonstrate convincing results that outperform traditional FLAF models.