Small-Footprint Keyword Spotting for Controlling Smart Home Appliances Using TCN and CRNN Models

Hemalatha Alapati, C. Paolini, S. Chinara, M. Sarkar
{"title":"Small-Footprint Keyword Spotting for Controlling Smart Home Appliances Using TCN and CRNN Models","authors":"Hemalatha Alapati, C. Paolini, S. Chinara, M. Sarkar","doi":"10.4018/ijitn.299365","DOIUrl":null,"url":null,"abstract":"Smart homes feature automatic fire/smoke detection, voice-operated assets and appliances etc. More often, smart home appliances like lights, fans, etc., can be controlled through voice commands. Voice-operated devices like Alexa, Siri, and Google Assistant, are not new in the current age concerning voice command execution. However, working with these supports requires a global connection with the internet that costs time and bandwidth. Controlling home appliances need concise commands involving keywords on/off. Further, to operate the home appliances, bandwidth consumption for internet is not a wise idea. Through this paper, models based on Temporal Convolutional Networks (TCN) and Convolutional Recurrent Neural Networks (CRNN) have been studied for Keyword Spotting (KWS) by training models with keywords pronounced in different accents. The performance of these models is compared, and their ability to detect unknown words is studied. Finally, how these models are suitable for building Smart Home assistants to control home utilities with minimum bandwidth consumption is discussed.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Interdiscip. Telecommun. Netw.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijitn.299365","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Smart homes feature automatic fire/smoke detection, voice-operated assets and appliances etc. More often, smart home appliances like lights, fans, etc., can be controlled through voice commands. Voice-operated devices like Alexa, Siri, and Google Assistant, are not new in the current age concerning voice command execution. However, working with these supports requires a global connection with the internet that costs time and bandwidth. Controlling home appliances need concise commands involving keywords on/off. Further, to operate the home appliances, bandwidth consumption for internet is not a wise idea. Through this paper, models based on Temporal Convolutional Networks (TCN) and Convolutional Recurrent Neural Networks (CRNN) have been studied for Keyword Spotting (KWS) by training models with keywords pronounced in different accents. The performance of these models is compared, and their ability to detect unknown words is studied. Finally, how these models are suitable for building Smart Home assistants to control home utilities with minimum bandwidth consumption is discussed.
基于TCN和CRNN模型控制智能家电的小足迹关键字识别
智能家居具有自动火灾/烟雾探测,语音操作资产和设备等。更常见的是,像灯、风扇等智能家电可以通过语音命令来控制。像Alexa、Siri和Google Assistant这样的语音操作设备,在当前的语音命令执行时代并不新鲜。然而,使用这些支持需要与互联网进行全球连接,这需要花费时间和带宽。控制家用电器需要简洁的命令,包括关键字on/off。此外,为了操作家用电器,将带宽消耗在互联网上并不是一个明智的主意。本文研究了基于时间卷积网络(TCN)和卷积递归神经网络(CRNN)的关键字识别模型,通过训练不同口音的关键字模型进行关键字识别。比较了这些模型的性能,并研究了它们对未知词的检测能力。最后,讨论了这些模型如何适用于构建智能家居助手,以最小的带宽消耗控制家庭公用事业。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信