Wavesense Efficient Temporal Convolutions With Spiking Neural Networks For Keyword Spotting

# WaveSense: Efficient Temporal Convolutions with Spiking Neural Networks for Keyword Spotting

**arXiv ID:** 2111.01456
**Authors:** Philipp Weidel, Sadique Sheik
**Published:** 2021-11-02T09:38:22Z
**Abstract:**
Ultra-low power local signal processing is a crucial aspect for edge applications on always-on devices. Neuromorphic processors emulating spiking neural networks show great computational power while fulfilling the limited power budget as needed in this domain. In this work we propose spiking neural dynamics as a natural alternative to dilated temporal convolutions. We extend this idea to WaveSense, a spiking neural network inspired by the WaveNet architecture. WaveSense uses simple neural dynamics, fixed time-constants and a simple feed-forward architecture and hence is particularly well suited for a neuromorphic implementation. We test the capabilities of this model on several datasets for keyword-spotting. The results show that the proposed network beats the state of the art of other spiking neural networks and reaches near state-of-the-art performance of artificial neural networks such as CNNs and LSTMs.

## Skill Description

This skill is generated from the arXiv paper: WaveSense: Efficient Temporal Convolutions with Spiking Neural Networks for Keyword Spotting (2111.01456).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2111.01456](http://arxiv.org/abs/2111.01456v1)