Towards efficient keyword spotting using spike-based time difference encoders
Keyword spotting in edge devices is becoming increasingly important as voice-activated assistants are widely used. However, its deployment is often limited by the extreme low-power constraints of the target embedded systems. Here, we explore the Temporal Difference Encoder (TDE) performance in keyword spotting. This recent neuron model encodes the time difference in instantaneous frequency and spike count to perform efficient keyword spotting with neuromorphic processors. We use the TIdigits dataset of spoken digits with a formant decomposition and rate-based encoding into spikes. We compare three Spiking Neural Networks (SNNs) architectures to learn and classify spatio-temporal signals. The proposed SNN architectures are made of three layers with variation in its hidden layer composed of either (1) feedforward TDE, (2) feedforward Current-Based Leaky Integrate-and-Fire (CuBa-LIF), or (3) recurrent CuBa-LIF neurons. We first show that the spike trains of the frequency-converted spoken digits have a large amount of information in the temporal domain, reinforcing the importance of better exploiting temporal encoding for such a task. We then train the three SNNs with the same number of synaptic weights to quantify and compare their performance based on the accuracy and synaptic operations. The resulting accuracy of the feedforward TDE network (89%) is higher than the feedforward CuBa-LIF network (71%) and close to the recurrent CuBa-LIF network (91%). However, the feedforward TDE-based network performs 92% fewer synaptic operations than the recurrent CuBa-LIF network with the same amount of synapses. In addition, the results of the TDE network are highly interpretable and correlated with the frequency and timescale features of the spoken keywords in the dataset. Our findings suggest that the TDE is a promising neuron model for scalable event-driven processing of spatio-temporal patterns.
Code (0)
등록된 구현이 없습니다.
Tasks
Keyword SpottingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Comparison of Temporal Encoders for Neuromorphic Keyword Spotting with Few Neurons
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 ClassificationKeyword Spottingspeech-recognitionSpeech RecognitionMetric Learning for Keyword Spotting
The goal of this work is to train effective representations for keyword spotting via metric learning. Most existing works address keyword spotting as a closed-set classification problem, where both target and non-target …
Keyword SpottingMetric LearningKeyword Transformer: A Self-Attention Model for Keyword Spotting
The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of c…
Keyword SpottingSpeech RecognitionEfficient Continual Learning in Keyword Spotting using Binary Neural Networks
Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as a…
Continual LearningKeyword SpottingFeature exploration for almost zero-resource ASR-free keyword spotting using a multilingual bottleneck extractor and correspondence autoencoders
We compare features for dynamic time warping (DTW) when used to bootstrap keyword spotting (KWS) in an almost zero-resource setting. Such quickly-deployable systems aim to support United Nations (UN) humanitarian relief …
Dynamic Time WarpingHumanitarianKeyword Spotting