SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition

TL;DR

SpikCommander introduces a novel spiking transformer architecture with multi-view learning and temporal-aware attention, significantly improving energy-efficient speech command recognition performance on benchmark datasets.

Contribution

The paper proposes SpikCommander, a fully spike-driven transformer with MSTASA and SCR-MLP, advancing temporal modeling and feature integration in SNN-based speech recognition.

Findings

Outperforms state-of-the-art SNN methods on SHD, SSC, and GSC datasets.

Uses fewer parameters while maintaining high accuracy.

Demonstrates robustness and efficiency in speech command recognition.

Abstract

Spiking neural networks (SNNs) offer a promising path toward energy-efficient speech command recognition (SCR) by leveraging their event-driven processing paradigm. However, existing SNN-based SCR methods often struggle to capture rich temporal dependencies and contextual information from speech due to limited temporal modeling and binary spike-based representations. To address these challenges, we first introduce the multi-view spiking temporal-aware self-attention (MSTASA) module, which combines effective spiking temporal-aware attention with a multi-view learning framework to model complementary temporal dependencies in speech commands. Building on MSTASA, we further propose SpikCommander, a fully spike-driven transformer architecture that integrates MSTASA with a spiking contextual refinement channel MLP (SCR-MLP) to jointly enhance temporal context modeling and channel-wise feature integration. We evaluate our method on three benchmark datasets: the Spiking Heidelberg Dataset (SHD), the Spiking Speech Commands (SSC), and the Google Speech Commands V2 (GSC). Extensive experiments demonstrate that SpikCommander consistently outperforms state-of-the-art (SOTA) SNN approaches with fewer parameters under comparable time steps, highlighting its effectiveness and efficiency for robust speech command recognition.