{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:52:38Z","timestamp":1772905958493,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022697","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"414-421","source":"Crossref","is-referenced-by-count":5,"title":["On the Efficiency of Integrating Self-Supervised Learning and Meta-Learning for User-Defined Few-Shot Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Wei-Tsung","family":"Kao","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Kuei","family":"Wu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"intelliGo Technology inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"intelliGo Technology inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Pao","family":"Tsai","sequence":"additional","affiliation":[{"name":"intelliGo Technology inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2568"},{"key":"ref2","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref3","article-title":"Few-shot keyword spotting with prototypical networks","author":"Parnami","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Pro-totypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414156"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1395"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1966"},{"key":"ref11","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref12","first-page":"4218","article-title":"Common voice: A massively-multilingual speech cor-pus","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3078715"},{"key":"ref14","article-title":"wav2vec 2. 0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01091"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3208"},{"key":"ref18","article-title":"Rep-resentation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3095662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref23","article-title":"Rapid learning or feature reuse? towards understanding the effectiveness of maml","volume-title":"International Conference on Learning Representations","author":"Raghu"},{"key":"ref24","article-title":"Boil: Towards representation change for few-shot learning","volume-title":"International Conference on Learning Representations","author":"Oh"},{"key":"ref25","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref27","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"Warden","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"issue":"201","key":"ref31","first-page":"1","article-title":"Understanding how dimension re-duction tools work: An empirical approach to deciphering t-sne, umap, trimap, and pacmap for data visualization","volume":"22","author":"Wang","year":"2021","journal-title":"Journal of Machine Learning Research"},{"issue":"11","key":"ref32","article-title":"Visu-alizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022697.pdf?arnumber=10022697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:06:19Z","timestamp":1738263979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022697","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}