{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:16:05Z","timestamp":1775913365915,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414643","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"835-839","source":"Crossref","is-referenced-by-count":15,"title":["Domestic Activities Clustering From Audio Recordings Using Convolutional Capsule Autoencoder Network"],"prefix":"10.1109","author":[{"given":"Ziheng","family":"Lin","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanxiong","family":"Li","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangjin","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Tan","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichun","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianhua","family":"He","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"15512","article-title":"Stacked capsule autoencoders","author":"kosiorek","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"ref31","first-page":"965","article-title":"Mobile phone clustering from speech recordings using deep embedding and spectral clustering","volume":"13","author":"li","year":"2018","journal-title":"IEEE TIFS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref34","first-page":"1996","article-title":"A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks","author":"marchi","year":"2005","journal-title":"Proc of ICASSP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053519"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690569"},{"key":"ref13","first-page":"98","article-title":"Acoustic scene classification based on convolutional neural network using double image features","author":"park","year":"2017","journal-title":"Proc DCAS Workshop"},{"key":"ref14","first-page":"142","article-title":"Histogram of gradients of time-frequency representations for audio scene classification","volume":"23","author":"rakotomamonjy","year":"2015","journal-title":"IEEE\/ACM TASLP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553314"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2854861"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690570"},{"key":"ref28","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","first-page":"39","article-title":"Attention-based convolutional neural networks for acoustic scene classification","author":"ren","year":"2018","journal-title":"Proc DCAS Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICALIP.2018.8455765"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2016.12.012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053582"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33682\/wgyb-bt40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001969"},{"key":"ref1","first-page":"32","article-title":"The SINS database for detection of daily activities in a home environment using an acoustic sensor network","author":"dekkers","year":"2017","journal-title":"Proc DCAS Workshop"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690561"},{"key":"ref22","first-page":"7","article-title":"Acoustic scene classification by combining autoencoder-based dimensionality reduction and convolutional neural networks","author":"abe\u00dfer","year":"2017","journal-title":"Proc DCAS Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4332-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_39"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553225"},{"key":"ref26","first-page":"1","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref25","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume":"48","author":"xie","year":"2016","journal-title":"Proc of ICML"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414643.pdf?arnumber=9414643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:46:51Z","timestamp":1764701211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414643","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}