Adaptive Central Frequencies Locally Competitive Algorithm for Speech

TL;DR

This paper introduces an enhanced adaptive sparse coding algorithm for speech processing that dynamically adjusts both modulation parameters and central frequencies, leading to improved efficiency and accuracy on neuromorphic hardware.

Contribution

It presents the ALCA-CF algorithm, which adaptively tunes central frequencies and modulation parameters for better speech representation and power efficiency in neuromorphic systems.

Findings

Improved speech reconstruction quality and sparsity.

Significant reduction in power consumption.

Maintained classification accuracy on neuromorphic hardware.

Abstract

Neuromorphic computing, inspired by nervous systems, revolutionizes information processing with its focus on efficiency and low power consumption. Using sparse coding, this paradigm enhances processing efficiency, which is crucial for edge devices with power constraints. The Locally Competitive Algorithm (LCA), adapted for audio with Gammatone and Gammachirp filter banks, provides an efficient sparse coding method for neuromorphic speech processing. Adaptive LCA (ALCA) further refines this method by dynamically adjusting modulation parameters, thereby improving reconstruction quality and sparsity. This paper introduces an enhanced ALCA version, the ALCA Central Frequency (ALCA-CF), which dynamically adapts both modulation parameters and central frequencies, optimizing the speech representation. Evaluations show that this approach improves reconstruction quality and sparsity while significantly reducing the power consumption of speech classification, without compromising classification accuracy, particularly on Intel's Loihi 2 neuromorphic chip.