Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks

TL;DR

Spiking-LEAF is a novel learnable auditory front-end designed for spiking neural networks, significantly improving speech processing tasks by enhancing accuracy and robustness through biologically inspired neuron models and adaptive filtering.

Contribution

The paper introduces Spiking-LEAF, combining a learnable filter bank with IHC-LIF neurons, advancing SNN-based speech processing with improved encoding and noise robustness.

Findings

Outperforms state-of-the-art spiking auditory front-ends

Achieves higher classification accuracy in speech tasks

Demonstrates enhanced noise robustness and encoding efficiency

Abstract

Brain-inspired spiking neural networks (SNNs) have demonstrated great potential for temporal signal processing. However, their performance in speech processing remains limited due to the lack of an effective auditory front-end. To address this limitation, we introduce Spiking-LEAF, a learnable auditory front-end meticulously designed for SNN-based speech processing. Spiking-LEAF combines a learnable filter bank with a novel two-compartment spiking neuron model called IHC-LIF. The IHC-LIF neurons draw inspiration from the structure of inner hair cells (IHC) and they leverage segregated dendritic and somatic compartments to effectively capture multi-scale temporal dynamics of speech signals. Additionally, the IHC-LIF neurons incorporate the lateral feedback mechanism along with spike regularization loss to enhance spike encoding efficiency. On keyword spotting and speaker identification tasks, the proposed Spiking-LEAF outperforms both SOTA spiking auditory front-ends and conventional real-valued acoustic features in terms of classification accuracy, noise robustness, and encoding efficiency.