mlsanityData to 14 Oct 2026

Global-Local Convolution with Spiking Neural Networks for Energy-efficient Keyword Spotting

arXiv 2406.13179 ↗First posted 19 Jun 2024cs.SD cs.AI cs.NEcited by 4

Not on the map. Why?

Abstract (arXiv)

Thanks to Deep Neural Networks (DNNs), the accuracy of Keyword Spotting (KWS) has made substantial progress. However, as KWS systems are usually implemented on edge devices, energy efficiency becomes a critical requirement besides performance. Here, we take advantage of spiking neural networks' energy efficiency and propose an end-to-end lightweight KWS model. The model consists of two innovative modules: 1) Global-Local Spiking Convolution (GLSC) module and 2) Bottleneck-PLIF module. Compared to the hand-crafted feature extraction methods, the GLSC module achieves speech feature extraction that is sparser, more energy-efficient, and yields better performance. The Bottleneck-PLIF module further processes the signals from GLSC with the aim to achieve higher accuracy with fewer parameters. Extensive experiments are conducted on the Google Speech Commands Dataset (V1 and V2). The results show our method achieves competitive performance among SNN-based KWS models with fewer parameters.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

16 of 30 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  3. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  4. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  5. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  6. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  7. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 115
  8. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
  9. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  10. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 35
  11. 2020Low-activity supervised convolutional spiking neural networks applied to speech commands recognitioncited by 19
  12. 2024Event-Driven Learning for Spiking Neural Networkscited by 15
4 more
  1. 2019An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networkscited by 9
  2. 2021WaveSense: Efficient Temporal Convolutions with Spiking Neural Networks for Keyword Spottingcited by 9
  3. 2022CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformercited by 4
  4. 2023Long Short-term Memory with Two-Compartment Spiking Neuroncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modelingcited by 2
  2. 2025SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command Recognitioncited by 2
  3. 2026Adaptive Speech-to-Spike Encoding for Spiking Neural Networkscited by 0
  4. 2026Latency and accuracy tradeoffs in Spiking Neural Networkscited by 0