Research map / Architectures and efficiency / Spiking networks
SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognition
Jiaqi Wang, Liutao Yu, Xiongri Shen, Sihang Guo, Chenlin Zhou, Leilei Zhao, Yi Zhong, Zhiguo Zhang, Zhengyu Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add data augmentation (ablation) | SpikCommander 2L · SSC | accuracy (%): 82.87 -> 83.49 | Improved |
| add data augmentation (ablation) | SpikCommander 1L · GSC | accuracy (%): 96.28 -> 96.71 | Improved |
| add V-branch to MSTASA (ablation) | SpikCommander 2L · SSC | accuracy (%): 82.38 -> 82.87 | Improved |
| add V-branch to MSTASA (ablation) | SpikCommander 1L · GSC | accuracy (%): 96.00 -> 96.28 | Improved |
| add SWA-STASA branch (ablation) | SpikCommander 2L · SSC | accuracy (%): 82.03 -> 82.38 | Improved |
| add SWA-STASA branch (ablation) | SpikCommander 1L · GSC | accuracy (%): 95.67 -> 96.00 | Improved |
| use SCR-MLP instead of standard MLP (ablation) | SpikCommander 2L · SSC | accuracy (%): 79.87 -> 82.03 | Improved |
| use SCR-MLP instead of standard MLP (ablation) | SpikCommander 1L · GSC | accuracy (%): 94.67 -> 95.67 | Improved |
| use SEE instead of Conv1D projection (ablation) | SpikCommander 2L · SSC | accuracy (%): 79.37 -> 79.87 | Improved |
| use SEE instead of Conv1D projection (ablation) | SpikCommander 1L · GSC | accuracy (%): 92.70 -> 94.67 | Improved |
| increase time steps from 100 to 250 | SpikCommander 2L · SSC | accuracy (%): 83.49 -> 85.98 | Improved |
| increase time steps from 200 to 250 | SpikCommander 2L · GSC | accuracy (%): 97.08 -> 97.06 | No clear effect |
Closest papers by meaning
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · similarity 0.88)
- LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units (ICLR 2024 · similarity 0.87)
- Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration (ICML 2024 · similarity 0.87)
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024 · similarity 0.86)
- Rethinking Spiking Neural Networks from an Ensemble Learning Perspective (ICLR 2025 · similarity 0.86)
- SpikF: Spiking Fourier Network for Efficient Long-term Prediction (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
