{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T15:08:31Z","timestamp":1767452911082,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Civil Military Technology Cooperation funded by the Defense Acquisition Program Administration and the Ministry of Trade, Industry and Energy of Korean Government","award":["UM22409RD4","BrainKorea21 (BK21) FOUR Program of the National Research Foundation Korea (NRF)"],"award-info":[{"award-number":["UM22409RD4","BrainKorea21 (BK21) FOUR Program of the National Research Foundation Korea (NRF)"]}]},{"name":"Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3378096","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T18:29:38Z","timestamp":1710872978000},"page":"42279-42294","source":"Crossref","is-referenced-by-count":5,"title":["Real-Time Sound Recognition System for Human Care Robot Considering Custom Sound Events"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3101-8732","authenticated-orcid":false,"given":"Seong-Hu","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1169-5640","authenticated-orcid":false,"given":"Hyeonuk","family":"Nam","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-Min","family":"Choi","sequence":"additional","affiliation":[{"name":"Samsung Electronics Company Ltd., Gyeonggi-do, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3519-1321","authenticated-orcid":false,"given":"Yong-Hwa","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4017\/gt.2009.08.02.002.00"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116287"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114195"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ48456.2019.8960963"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2016.2615329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR49639.2020.9108054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref8","article-title":"A report on sound event detection with different binaural features","volume-title":"arXiv:1710.02997","author":"Adavanne","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"article-title":"Cht+ nsysu sound event detection system with multiscale channel attention and multiple consistency training for dcase 2021 task 4","year":"2021","author":"Wang","key":"ref13"},{"article-title":"Convolutional network with conformer for semi-supervised sound event detection","year":"2021","author":"Na","key":"ref14"},{"article-title":"Integrating advantages of recurrent and transformer structures for sound event detection in multiple scenarios","year":"2021","author":"Lu","key":"ref15"},{"article-title":"Convolution-augmented conformer for sound event detection","year":"2021","author":"Chen","key":"ref16"},{"article-title":"Sound event detection based on self-supervised learning of wav2vec 2.0","year":"2021","author":"Koo","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747421"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10127"},{"key":"ref22","article-title":"Heavily augmented sound event detection utilizing weak predictions","author":"Nam","year":"2021","journal-title":"arXiv:2107.03649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651506"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2015.7150593"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354057"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2618218"},{"article-title":"Deep learning-based personalized sound event recognition for human care robot","volume-title":"Proc. 24th Int. Congr. Acoust. (ICA)","author":"Kim","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3322240"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_12"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s17040854"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IES50839.2020.9231702"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2020.101238"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11455-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.08.020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref40","first-page":"1","article-title":"The SINS database for detection of daily activities in a home environment using an acoustic sensor network","volume":"2017","author":"Dekkers","year":"2017","journal-title":"Detection Classification Acoustic Scenes Events"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3381014"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117811"},{"article-title":"DCASE 2017 challenge setup: Tasks, datasets and baseline system","volume-title":"Proc. DCASE Workshop Detection Classification Acoustic Scenes Events","author":"Mesaros","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"article-title":"Sound event detection with resnet and self-mask module for dcase 2019 task 4","year":"2019","author":"Kiyokawa","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref53","article-title":"Decomposed temporal dynamic CNN: Efficient time-adaptive network for text-independent speaker verification explained with speaker activation map","author":"Kim","year":"2022","journal-title":"arXiv:2203.15277"},{"key":"ref54","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10473039.pdf?arnumber=10473039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T20:50:09Z","timestamp":1711659009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10473039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3378096","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}