{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:00:44Z","timestamp":1782313244165,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383571","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"133-140","source":"Crossref","is-referenced-by-count":16,"title":["Metric Learning for Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Jaesung","family":"Huh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heesoo","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seongkyu","family":"Mun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","first-page":"273","article-title":"Prototypical metric transfer learning for continuous speech keyword spotting with limited training data","author":"seth","year":"2019","journal-title":"International Workshop on Soft Computing Models in Industrial and Environmental Applications"},{"key":"ref32","article-title":"Few-shot keyword spotting with prototypical networks","author":"parnami","year":"2020"},{"key":"ref31","article-title":"Meta learning for few-shot key-word spotting","author":"chen","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2762080"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref36","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"platt","year":"1999","journal-title":"Advances in Large Margin Classifiers"},{"key":"ref35","first-page":"3221","article-title":"Accelerating t-sne using tree-based algorithms","volume":"15","author":"van der maaten","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref34","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref40","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015"},{"key":"ref11","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"zhang","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1045","article-title":"Depthwise separable convolutional resnet with squeeze-and-excitation blocks for small-footprint keyword spotting","author":"xu","year":"2020"},{"key":"ref14","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3320288.3320304"},{"key":"ref16","first-page":"166","article-title":"Laika: A 5uw programmable lstm accelerator for always-on keyword spotting in 65nm cmos","author":"sebastian","year":"2018","journal-title":"ESSCIRC 2018 - IEEE 44th European Solid State Circuits Conference (ESSCIRC)"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3328907","article-title":"An optimized recur-rent unit for ultra-low-power keyword spotting","volume":"3","author":"amoh","year":"2019","journal-title":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies"},{"key":"ref18","article-title":"Siamese neural networks for one-shot image recognition","volume":"2","author":"koch","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"ref19","first-page":"539","article-title":"Learning a similarity metric discriminatively, with ap-plication to face verification","author":"chopra","year":"2005","journal-title":"Proc CVPR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref27","first-page":"4077","article-title":"Proto-typical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891838"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.725322"},{"key":"ref7","article-title":"Keyword spotting result post-processing to reduce false alarms","volume":"9","author":"lubo\u0161","year":"2009","journal-title":"Recent Advances in Signals ans Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-352","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref45","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Deep face recognition","author":"parkhi","year":"2015","journal-title":"Proc BMVC"},{"key":"ref21","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"chechik","year":"2010","journal-title":"Journal of Machine Learning Re-search"},{"key":"ref42","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NIPS Autodiff Workshop"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref41","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref43","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383571.pdf?arnumber=9383571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:40Z","timestamp":1671715000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383571","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}