AN EXPERIMENTAL ANALYSIS OF THE POWER CONSUMPTION OF CONVOLUTIONAL NEURAL NETWORKS FOR KEYWORD SPOTTING

被引：0

作者：

Tang, Raphael ^{[1
]}

Wang, Weijie ^{[1
]}

Tu, Zhucheng ^{[1
]}

Lin, Jimmy ^{[1
]}

机构：

[1] Univ Waterloo, David R Cheriton Sch Comp Sci, Waterloo, ON, Canada

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年

关键词：

keyword spotting; power consumption;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Nearly all previous work on small-footprint keyword spotting with neural networks quantify model footprint in terms of the number of parameters and multiply operations for a feedforward inference pass. These values are, however, proxy measures since empirical performance in actual deployments is determined by many factors. In this paper, we study the power consumption of a family of convolutional neural networks for keyword spotting on a Raspberry Pi. We find that both proxies are good predictors of energy usage, although the number of multiplies is more predictive than the number of model parameters. We also confirm that models with the highest accuracies are, unsurprisingly, the most power hungry.

引用

页码：5479 / 5483

页数：5

共 50 条

[1] Deep Convolutional Spiking Neural Networks for Keyword Spotting
Yilmaz, Emre
Gevrek, Ozgur Bora
Wu, Jibin
Chen, Yuxiang
Meng, Xuanbo
Li, Haizhou
[J]. INTERSPEECH 2020, 2020, : 2557 - 2561
[2] Convolutional Neural Networks for Small-footprint Keyword Spotting
Sainath, Tara N.
Parada, Carolina
[J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1478 - 1482
[3] Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Arik, Sercan O.
Kliegl, Markus
Child, Rewon
Hestness, Joel
Gibiansky, Andrew
Fougner, Chris
Prenger, Ryan
Coates, Adam
[J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1606 - 1610
[4] Keyword spotting in continuous speech using convolutional neural network
Rostami, Amir Mohammad
Karimi, Ali
Akhaee, Mohammad Ali
[J]. Speech Communication, 2022, 142 : 15 - 21
[5] Keyword spotting in continuous speech using convolutional neural network
Rostami, Amir Mohammad
Karimi, Ali
Akhaee, Mohammad Ali
[J]. SPEECH COMMUNICATION, 2022, 142 : 15 - 21
[6] Efficient Execution of Temporal Convolutional Networks for Embedded Keyword Spotting
Giraldo, J. S. P.
Jain, Vikram
Verhelst, Marian
[J]. IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2021, 29 (12) : 2220 - 2228
[7] Reduced Model Size Deep Convolutional Neural Networks for Small-Footprint Keyword Spotting
Tsai, Tsung Han
Lin, Xin Hui
[J]. 2021 28TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS (IEEE ICECS 2021), 2021,
[8] An application of recurrent neural networks to discriminative keyword spotting
Fernandez, Santiago
Graves, Alex
Schmidhuber, Juergen
[J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2007, PT 2, PROCEEDINGS, 2007, 4669 : 220 - +
[9] Small-footprint Spiking Neural Networks for Power-efficient Keyword Spotting
Pedroni, Bruno U.
Sheik, Sadique
Mostafa, Hesham
Paul, Somnath
Augustine, Charles
Cauwenberghs, Gert
[J]. 2018 IEEE BIOMEDICAL CIRCUITS AND SYSTEMS CONFERENCE (BIOCAS): ADVANCED SYSTEMS FOR ENHANCING HUMAN HEALTH, 2018, : 591 - 594
[10] A depthwise separable convolutional neural network for keyword spotting on an embedded system
Sorensen, Peter Molgaard
Epp, Bastian
May, Tobias
[J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2020, 2020 (01)

← 1 2 3 4 5 →