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

arXiv: https://arxiv.org/abs/2309.09469 · HTML: https://mlsanity.com/paper/2309.09469/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2023.

## Built on by (most cited first, 6 of 6)

- [ED-sKWS: Early-Decision Spiking Neural Networks for Rapid,and Energy-Efficient Keyword Spotting](https://mlsanity.com/paper/2406.12726/) (2024)
- [SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition](https://mlsanity.com/paper/2503.15986/) (2025)
- [Memory-Free and Parallel Computation for Quantized Spiking Neural Networks](https://mlsanity.com/paper/2503.00040/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [IML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech Processing](https://mlsanity.com/paper/2507.07396/) (2025)
- [Conjoint Audio-to-Spikes Encoding and Processing for Efficient Neuromorphic Speech Recognition](https://mlsanity.com/paper/2608.30792/) (2026)

## Abstract (arXiv)

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.