Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio

TL;DR

This paper introduces an adaptive method using the Locally Competitive Algorithm to optimize gammachirp filter parameters for sparse audio representations, achieving better performance with less computation suitable for real-time use.

Contribution

It presents a novel adaptive approach that leverages LCA's neural architecture and backpropagation to optimize gammachirp filters, improving sparsity and reconstruction quality.

Findings

Enhanced sparsity and reconstruction quality with the proposed method

Reduced convergence time compared to traditional methods

Potential for real-time audio processing applications

Abstract

Gammachirp filterbank has been used to approximate the cochlea in sparse coding algorithms. An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (MP) algorithm's sparsity along with the reconstruction quality. However, this combination of a greedy algorithm with a grid search at each iteration is computationally demanding and not suitable for real-time applications. This paper presents an adaptive approach to optimize the gammachirp's parameters but in the context of the Locally Competitive Algorithm (LCA) that requires much fewer computations than MP. The proposed method consists of taking advantage of the LCA's neural architecture to automatically adapt the gammachirp's filterbank using the backpropagation algorithm. Results demonstrate an improvement in the LCA's performance with our approach in terms of sparsity, reconstruction quality, and convergence time. This approach can yield a significant advantage over existing approaches for real-time applications.