Low Parameter and FLOPs1Speech Densely Connected Convolutional Networks for Keyword Spotting

Tsung Han Tsai; Xin Hui Lin

doi:10.1109/ICCE-Taiwan55306.2022.9869290

Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting

Tsung Han Tsai
, Xin Hui Lin

電機工程學系

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

摘要

Due to the fast-paced nature of technology, people focus on keyword spotting technology for the use of human-computer interaction (HCI). In this paper, a keyword spotting technique based on the Convolutional neural network (CNN) method is proposed. This network model is modified with the densely connected convolutional network (DenseNet) and uses grouped convolution and deep separable convolution to construct complete keyword spotting tasks. Besides, we change the width and depth of the network to construct a compact variation of the network. We established the network using the Google Speech Command Dataset V2. Compared to different networks, our proposed network sacrifices a small quantity of precision to have a low number of parameters and floating-point operations (FLOPs).

原文	???core.languages.en_GB???
主出版物標題	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	271-272
頁數	2
ISBN（電子）	9781665470506
DOIs	https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869290
出版狀態	已出版 - 2022
事件	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, Taiwan 持續時間: 6 7月 2022 → 8 7月 2022

出版系列

名字	Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
國家/地區	Taiwan
城市	Taipei
期間	6/07/22 → 8/07/22

UN SDG

此研究成果有助於以下永續發展目標

SDG 7 經濟實惠的清潔能源

存取文件

10.1109/ICCE-Taiwan55306.2022.9869290

引用此

Tsai, T. H., & Lin, X. H. (2022). Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 (頁 271-272). (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869290

Tsai, Tsung Han ; Lin, Xin Hui. / Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. 頁 271-272 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

@inproceedings{e112868d01b84d539509c4da9a58be53,

title = "Low Parameter and FLOPs1Speech Densely Connected Convolutional Networks for Keyword Spotting",

abstract = "Due to the fast-paced nature of technology, people focus on keyword spotting technology for the use of human-computer interaction (HCI). In this paper, a keyword spotting technique based on the Convolutional neural network (CNN) method is proposed. This network model is modified with the densely connected convolutional network (DenseNet) and uses grouped convolution and deep separable convolution to construct complete keyword spotting tasks. Besides, we change the width and depth of the network to construct a compact variation of the network. We established the network using the Google Speech Command Dataset V2. Compared to different networks, our proposed network sacrifices a small quantity of precision to have a low number of parameters and floating-point operations (FLOPs).",

author = "Tsai, \{Tsung Han\} and Lin, \{Xin Hui\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 ; Conference date: 06-07-2022 Through 08-07-2022",

year = "2022",

doi = "10.1109/ICCE-Taiwan55306.2022.9869290",

language = "???core.languages.en\_GB???",

series = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "271--272",

booktitle = "Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022",

}

Tsai, TH & Lin, XH 2022, Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Institute of Electrical and Electronics Engineers Inc., 頁 271-272, 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022, Taipei, Taiwan, 6/07/22. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869290

Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting. / Tsai, Tsung Han; Lin, Xin Hui.
Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 271-272 (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022).

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

TY - GEN

T1 - Low Parameter and FLOPs1Speech Densely Connected Convolutional Networks for Keyword Spotting

AU - Tsai, Tsung Han

AU - Lin, Xin Hui

PY - 2022

Y1 - 2022

N2 - Due to the fast-paced nature of technology, people focus on keyword spotting technology for the use of human-computer interaction (HCI). In this paper, a keyword spotting technique based on the Convolutional neural network (CNN) method is proposed. This network model is modified with the densely connected convolutional network (DenseNet) and uses grouped convolution and deep separable convolution to construct complete keyword spotting tasks. Besides, we change the width and depth of the network to construct a compact variation of the network. We established the network using the Google Speech Command Dataset V2. Compared to different networks, our proposed network sacrifices a small quantity of precision to have a low number of parameters and floating-point operations (FLOPs).

AB - Due to the fast-paced nature of technology, people focus on keyword spotting technology for the use of human-computer interaction (HCI). In this paper, a keyword spotting technique based on the Convolutional neural network (CNN) method is proposed. This network model is modified with the densely connected convolutional network (DenseNet) and uses grouped convolution and deep separable convolution to construct complete keyword spotting tasks. Besides, we change the width and depth of the network to construct a compact variation of the network. We established the network using the Google Speech Command Dataset V2. Compared to different networks, our proposed network sacrifices a small quantity of precision to have a low number of parameters and floating-point operations (FLOPs).

UR - https://www.scopus.com/pages/publications/85138724643

U2 - 10.1109/ICCE-Taiwan55306.2022.9869290

DO - 10.1109/ICCE-Taiwan55306.2022.9869290

M3 - 會議論文篇章

AN - SCOPUS:85138724643

T3 - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

SP - 271

EP - 272

BT - Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Y2 - 6 July 2022 through 8 July 2022

ER -

Tsai TH, Lin XH. Low Parameter and FLOPs¹Speech Densely Connected Convolutional Networks for Keyword Spotting. 於 Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 271-272. (Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022). doi: 10.1109/ICCE-Taiwan55306.2022.9869290