Paper Info
Title
A Depthwise Separable Convolution Neural Network for Small-footprint Keyword Spotting Using Approximate MAC Unit and Streaming Convolution Reuse
Abstract
In recent years, many applications of voice wake-up technology have entered people's lives and the key technology is Keyword Spotting (KWS). The keyword spotting system needs to detect the ambient voice and wait for a wake-up at any time, which requires low power consumption and high recognition accuracy. We mainly aim at reducing the power consumption of real-time keyword spotting systems in this paper. Based on Google's speech commands dataset (GSCD), a deep neural network model with Depthwise Separable Convolution (DS-Conv) is constructed and trained. We propose a kind of Approximate Multiply and Accumulate Unit (AP-MAC) and a data reuse method called Streaming Convolution Reuse (SCR) and prove that the neural network with AP-MACs saves 37.7% ~ 42.6% of computing power and achieves similar Word Error Rate (WER) compared to the same model using traditional MAC units in KWS task. Also, SCR allows the model to reuse convolution results for multiple audio frames and saves 94% of activations storage. By combining these two methods, the computing power and memory storage per audio frame of the baseline model are reduced by 98.5% ~ 98.7% and 94% respectively.
Year
DOI
Venue
2019
10.1109/APCCAS47518.2019.8953096
2019 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)
Keywords
Field
DocType
Keyword spotting,Approximate computing,Data resue,Depthwise separable convolution
Reuse,Convolutional neural network,Convolution,Computer science,Word error rate,Real-time computing,Electronic engineering,Keyword spotting,Footprint,Artificial neural network,Fold (higher-order function)
Conference
ISBN
Citations 
PageRank 
978-1-7281-2941-9
0
0.34
References 
Authors
3
3
Name
Order
Citations
PageRank
Yi-Cheng Lu152.23
Weiwei Shan242.46
Jiaming Xu328435.34