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

2021-11-02 · Philipp Weidel, Sadique Sheik

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.

📄 PDF Abstract BibTeX arXiv:2111.01456

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword Spotting

Methods 이 논문이 사용한 방법론

Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…

Mixture of Logistic Distributions 설명 없음

WaveNet WaveNet is an audio generative model based on the PixelCNN architecture. In order to deal with long-range temporal dependencies…

Few-Shot Keyword Spotting With Prototypical Networks

2020-07-25 · arXiv 2020 6 · Archit Parnami, Minwoo Lee

Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home. In order to recognize a set of keywords, most of the recent deep learn…

Keyword Spotting Metric Learning

A Comparison of Temporal Encoders for Neuromorphic Keyword Spotting with Few Neurons

2023-01-24 · Mattias Nilsson, Ton Juny Pina, Lyes Khacef, Foteini Liwicki 외

With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition. One promising appro…

Binary Classification Keyword Spotting speech-recognition Speech Recognition

Efficient keyword spotting using dilated convolutions and gating

2018-11-19 · Alice Coucke, Mohammed Chlieh, Thibault Gisselbrecht, David Leroy 외

We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a mod…

Keyword Spotting Small-Footprint Keyword Spotting

AutoKWS: Keyword Spotting with Differentiable Architecture Search

2020-09-08 · Bo Zhang, Wenfeng Li, Qingyuan Li, Weiji Zhuang 외

Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fas…

Keyword Spotting Neural Architecture Search

Efficient Keyword Spotting by capturing long-range interactions with Temporal Lambda Networks

2021-04-16 · Biel Tura, Santiago Escuder, Ferran Diego, Carlos Segura 외

Models based on attention mechanisms have shown unprecedented speech recognition performance. However, they are computationally expensive and unnecessarily complex for keyword spotting, a task targeted to small-footprint…

Keyword Spotting speech-recognition Speech Recognition