{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:34Z","timestamp":1776886714542,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096596","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":14,"title":["Metric Learning for User-Defined Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Jaemin","family":"Jung","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youkyum","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihwan","family":"Park","sequence":"additional","affiliation":[{"name":"Hyundai Motor Company"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youshin","family":"Lim","sequence":"additional","affiliation":[{"name":"Hyundai Motor Company"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"Hyundai Motor Company"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjoon","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1395"},{"key":"ref12","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref34","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1966"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref30","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref33","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683393"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-00176-2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.012"},{"key":"ref18","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"zhang","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref23","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3529399.3529443"},{"key":"ref22","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref29","article-title":"Korean Speech Commands","author":"hwang","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref7","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"29","author":"sohn","year":"2016","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-383"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383571"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096596.pdf?arnumber=10096596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:18Z","timestamp":1700507298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096596","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}